Pāriet uz galveno saturu
OpenAI

2025. gada 16. aprīlis

IzlaidumsProdukts

Introducing OpenAI o3 and o4-mini

Notiek ielāde…

2025. gada 10. jūnija atjauninājums: OpenAI o3‑pro tagad ir pieejams Pro lietotājiem ChatGPT, kā arī mūsu API. Tāpat kā OpenAI o1‑pro, arī o3‑pro ir mūsu inteliģentākā modeļa OpenAI o3 versija, kas izstrādāta, lai domātu ilgāk un sniegtu visuzticamākās atbildes. Sīkāka informācija atrodama mūsu izlaiduma piezīmēs(atveras jaunā logā).


Šodien mēs izlaižam OpenAI o3 un o4-mini, mūsu jaunākos o sērijas modeļus, kas ir apmācīti domāt ilgāk pirms atbildes sniegšanas. Tie ir mūsu visgudrākie modeļi, kādi līdz šim ir izlaisti, piedāvājot kardinālas izmaiņas ikvienam ChatGPT lietotājam, sākot no ziņkārīgiem lietotājiem līdz progresīviem pētniekiem. Pirmo reizi mūsu loģiskās domāšanas modeļi var aģentiski izmantot un apvienot visus ChatGPT rīkus, ietverot meklēšanu tīmeklī, augšupielādēto failu un citu datu analīzi ar Python, padziļinātu vizuālās ievades apskati un pat attēlu ģenerēšanu. Būtiski ir tas, ka šie modeļi ir apmācīti izvēlēties, kad un kā izmantot rīkus, lai sagatavotu detalizētas un pārdomātas atbildes pareizajos izejas formātos, lai atrisinātu sarežģītus jautājumus—parasti mazāk nekā minūtes laikā. Tas ļauj efektīvāk risināt daudzpusīgus jautājumus, kas ir solis ceļā uz aģentīgāku ChatGPT, kas var patstāvīgi izpildīt uzdevumus tavā vietā. Apvienojot uzlabotu argumentāciju un pilnīgu piekļuvi rīku izmantošanai tiek panākta ievērojami augstāka veiktspēja akadēmiskajos kritērijos un reālās pasaules uzdevumos, nosakot jaunu modeļu standartu gan inteliģences, gan lietderības jomā.

Kas ir mainījies

OpenAI o3 ir mūsu visjaudīgākais spriestspējas modelis, kas paplašina iespējas programmēšanā, matemātikā, zinātnē, vizuālajā uztverē un citās jomās. Tas nosaka jaunu SOTA standartu, tostarp Codeforces, SWE-bench (bez pielāgotas modeļa sastatnes izveides) un MMMU. Tas ir ideāli piemērots sarežģītiem vaicājumiem, kuriem nepieciešama daudzpusīga analīze un gadījumos, kad atbildes var nebūt uzreiz acīmredzamas. Šis modelis īpaši labi darbojas vizuālu uzdevumu veikšanā, piemēram, attēlu, diagrammu un grafiku analīzē. Saskaņā ar ārējo ekspertu vērtējumu, o3 pieļauj par 20 procentiem mazāk lielu kļūdu nekā OpenAI o1, risinot sarežģītus reālās dzīves uzdevumos, un īpaši izceļas tādās jomās kā programmēšana, uzņēmējdarbība/konsultācijas un radošu ideju izstrāde. Agrīnie testētāji izceļ tā analītisko precizitāti un partnerību domāšanas procesā un uzsver tā spēju ģenerēt un kritiski izvērtēt jaunas hipotēzes, īpaši bioloģijas, matemātikas un inženierzinātņu kontekstos.

OpenAI o4-mini ir mazāks modelis, kas optimizēts ātrai un rentablai spriešanai — tā veiktspēja ir ievērojama, ņemot vērā izmēru un cenas, jo īpaši matemātikā, kodēšanā un vizuālajos uzdevumos. Tas ir vislabāk novērtētais AIME modelis 2024. un 2025. gadā. Lai gan piekļuve datoram būtiski samazina AIME eksāmena grūtības, mēs vēlamies atzīmēt, ka o4-mini sasniedz 99.5% pass@1 (100% consensus@8) AIME 2025, ja tiek piešķirta piekļuve Python Interpreter rīkam. Lai gan šos rezultātus nevajadzētu salīdzināt ar modeļu veiktspēju bez piekļuves rīkiem, tie ir viens no piemēriem tam, kā o4-mini efektīvi izmanto pieejamos rīkus; o3 ar rīku izmantošanu uzrāda līdzīgus uzlabojumus AIME 2025. gada versijā (98,4% pass@1, 100% consensus@8).

Ekspertu novērtējumos o4-mini pārspēj savu priekšgājēju o3‑mini arī uzdevumos, kas nav saistīti ar STEM, kā arī tādās jomās kā datu zinātne. Pateicoties tā efektivitātei, o4-mini atbalsta ievērojami augstākus lietošanas ierobežojumus nekā o3, un tas padara šo modeli par ražīgu liela apjoma datu apstrādes opciju jautājumos, kas gūst labumu no argumentācijas. Ārējie eksperti novērtē abus modeļus kā tādus, kas, pateicoties uzlabotai inteliģencei un tīmekļa avotu iekļaušanai, demonstrē labāku norādījumu izpildi un sniedz noderīgākas, vieglāk pārbaudāmas atbildes nekā to priekšgājēji. Salīdzinājumā ar mūsu argumentācijas modeļu iepriekšējām iterācijām, šie divi modeļi ir arī dabiskāki un sarunvalodīgāki, jo īpaši tad, ka tie atsaucas uz savu atmiņu un iepriekšējām sarunām, lai padarītu savas atbildes personalizētākas un atbilstošākas.

Multimodāls

Programmēšana

Visos SWE-bench novērtēšanas testos tiek izmantota fiksēta n=477 verificētu uzdevumu apakškopa, kas ir apstiprināta mūsu iekšējā infrastruktūrā.

Instrukciju ievērošana un aģentisko rīku izmantošana

Visi modeļi tiek novērtēti pie augstiem "loģiskās piepūles" iestatījumiem, līdzīgi kā ChatGPT modeļi, piemēram, "o4-mini-high".

Turpinām paplašināt stimulētas mācīšanās mērogu

Visā OpenAI o3 izstrādes gaitā esam novērojuši, ka liela mēroga stimulēta mācīšanās uzrāda tādu pašu tendenci “vairāk skaitļošanas resursu = labāka veiktspēja”, kas novērota GPT sērijas pirmsapmācībā. Izmantojot mērogošanas ceļu - šoreiz RL režīmā -, mēs esam palielinājuši gan apmācības skaitļošanas, gan secinājumu izdarīšanas laika argumentācijas apjomu, tomēr joprojām redzam nepārprotamu veiktspējas pieaugumu, kas apliecina, ka modeļu veiktspēja turpina uzlaboties proporcionāli tam, cik daudz tiem atļaut domāt. Ar vienādu OpenAI o1 latentumu un izmaksām, o3 nodrošina augstāku veiktspēju ChatGPT, turklāt esam atklājuši, ka šī modeļa veiktspēja turpina pieaugt, ja atļaujam tam domāt ilgāk.

Mēs arī apmācījām abus modeļus izmantot rīkus stimulētas apmācības laikā—iemācot tiem ne tikai šos rīkus pielietot, bet arī izlemt, kad to darīt. Šo modeļu spēja izmantot rīkus atbilstīgi vēlamajam rezultātam padara tos spējīgākus atklātās situācijās, īpaši tādās, kas saistītas ar vizuālo izpēti un daudzpakāpju darbplūsmām. Agrīnie testētāji apliecina, ka šis uzlabojums ir redzams gan akadēmiskajos standartos, gan reālās pasaules uzdevumos.

Domāšana ar attēliem

ChatGPT thinking with images

Tagad pirmo reizi šie modeļi var integrēt attēlus tieši savā domu ķēdē. Tie ne tikai redz attēlu—modeļi var to izmantot savā domāšanas procesā. Tādējādi tiek atklāta jauna problēmu risināšanas klase, kas apvieno vizuālo un tekstuālo argumentāciju, rezultātā nodrošinot augstu veiktspēju dažādu multimodālo kritēriju izpildē.

Cilvēki var augšupielādēt tāfeles fotoattēlu, mācību grāmatas diagrammu vai ar roku zīmētu skici, un modelis to var interpretēt — pat tad, ja attēls ir izplūdis, apgriezts vai zemas kvalitātes. Izmantojot rīkus, modeļi var nekavējoties manipulēt ar attēliem, tos pagriežot, palielinot vai pārveidojot kā daļu no domāšanas procesa.

Šie modeļi nodrošina visaugstāko precizitāti savā klasē, risinot vizuālās uztveres uzdevumus un tādējādi atrisinot jautājumus, kas iepriekš nebija izpildāmi. Lai uzzinātu vairāk, izlasi vizuālās argumentācijas izpētes emuāru.

Ceļā uz aģentisku rīku izmantošanu

OpenAI o3 un o4-mini ir pilnīga piekļuve ChatGPT rīkiem, kā arī jūsu pašu pielāgotajiem rīkiem, izmantojot funkciju izsaukšanu API. Šie modeļi ir apmācīti spriest par to, kā risināt problēmas, izvēloties, kad un kā izmantot rīkus, lai ātri sagatavotu detalizētas un pārdomātas atbildes pareizajos izvades formātos — parasti ātrāk nekā minūtes laikā.

Piemēram, lietotājs var uzdot jautājumu: "Kāds ir vasaras enerģijas patēriņš Kalifornijā salīdzinājumā ar pagājušo gadu?" Modelis var meklēt tīmeklī komunālo pakalpojumu datus, sagatavot Python kodu, lai izveidotu prognozi, ģenerēt diagrammu vai attēlu un izskaidrot galvenos prognozes faktorus, sasaistot kopā vairāku rīku izsaukumus. Spriestspēja ļauj modeļiem reaģēt un mainīt domāšanas virzienu atbilstoši informācijai, ar kuru tie saskaras. Piemēram, tie var veikt vairākas meklēšanas tīmeklī, izmantojot meklēšanas pakalpojumu sniedzējus, apskatīt rezultātus un veikt jaunus meklējumus, ja nepieciešama papildu informācija.

Šī elastīgā, stratēģiskā pieeja ļauj modeļiem risināt uzdevumus, kuru izpildei nepieciešama piekļuve atjauninātai informācijai, kas pārsniedz modeļa iebūvētās zināšanas, pieeja paplašinātai argumentācijai, sintēzei un izvades ģenerēšanai dažādās modalitātēs.

Visi piemēri tika veikti ar OpenAI o3.

OpenAI o3

Solve the following very hard math problem using your in-built knowledge of the literature:

Construct a degree 19 polynomial \ (p(x)) \ in \ mathbb{C}[x] such that \ (X := \ {\, p(x) = p(y) \, \} \ subset \ mathbb{P}^{1} \ times \ mathbb{P}^{1}\ ) has at least 3 (but not all linear) irreducible components over \ mathbb{C}. Choose \ (p(x)\ ) to be odd, monic, have real coefficients and linear coefficient \ (-19\ ) and calculate \ (p(19)\ ).

55 sekundes apsvēra polinomu konstrukciju
  • The curve defined by p(x) = p(y) factors if p(x) is decomposable or has repeated factors. Actually, p(x)-p(y) always factors, and it’s divisible by (x-y). This gives one factor, and the rest is a degree d-1 polynomial in x and y. For the curve to have at least three irreducible components, p(x)-p(y) must factor into at least three nontrivial factors. Each factor corresponds to a component in projective space, and at least one must be nonlinear.
  • I’m checking the Dickson polynomials D_n(x,a) and focusing on their coefficients. With a=1, it seems the leading coefficient is always 1, confirming that Dickson polynomials are monic. The linear coefficient for odd n is following a predictable sign pattern: for n=19, it gives a coefficient of -19, which is exactly what I need. So the Dickson polynomial D_n(x,1) with odd n fits nicely with the linear coefficient I was looking for.
  • I've confirmed that the linear coefficient for p(x)=D19(x)p(x) = D_{19}(x)p(x)=D19​(x) is correct, with the necessary scaling factor to match. Now for the next step, I need to compute D19(19)D_{19}(19)D19​(19). Since Tn(z)T_n(z)Tn​(z) grows quickly for real z>1z > 1z>1, I plan to compute this value using Python, leveraging the recurrence to avoid mistakes—it's going to be a big number. I'll make sure to present the numeric result neatly so it's understandable since the coefficients are integers.
  • The Dickson polynomial D_{19}(x,1) is confirmed to have the required properties: monic, odd, real coefficients, and a linear coefficient of -19. The factorization of D_{19}(x) into irreducible components is also verified and satisfies the condition of having at least 10 components (1 linear + 9 quadratics). To compute p(19), we'll use the recurrence relation for Dickson polynomials, but there's also a closed-form expression involving cosine that could be handy here. I'll proceed accordingly!
  • I confirmed the linear coefficient is working correctly, which means now I need to calculate p(19)=D19(19)p(19) = D_{19}(19)p(19)=D19​(19). This involves evaluating T19(9.5)T_{19}(9.5)T19​(9.5), which grows rapidly. To ensure I get an accurate result, I'll compute this using recurrence in Python. The result is a large number: 1,876,572,071,974,094,803,391,179. I'll use the commas to make it easier to read: p(19)=1,876,572,071,974,094,803,391,179p(19) = 1,876,572,071,974,094,803,391,179p(19)=1,876,572,071,974,094,803,391,179.
  • For a = 1, there’s a relationship between Dickson polynomials and Chebyshev polynomials: D_n(x, 1) = 2^(n-1) T_n(x/2). Checking this, we see that the definition of D_n(u + 1/u) aligns well with Chebyshev’s formula. By setting x = 2 cos(θ), we find that D_n(x) equals 2 T_n(x/2). Importantly, the leading coefficient works out to 1, confirming the identity holds. This is nice!
  • Now, I need to verify that p(x)−p(y)p(x) - p(y)p(x)−p(y) factors as desired, relying on the known Dickson polynomial factorization. According to the literature (like Fried and Jarden), the difference Dn(x)−Dn(y)D_n(x) - D_n(y)Dn​(x)−Dn​(y) factors into a product involving (x−y)(x - y)(x−y) and other expressions. I'll provide the explicit polynomial D19(x,1)D_{19}(x, 1)D19​(x,1), list the coefficients, and explain how it satisfies the desired properties: monic, odd, etc. Lastly, I'll compute p(19)p(19)p(19).

Analyzed

Python

1
from math import comb, cos, acos
2
# Let's compute Dickson D_n(x,a=1) recursively
3
def dickson(n,x,a=1):
4
if n==0:
5
return 2
6
if n==1:
7
return x
8
Dm2=2
9
Dm1=x
10
for k in range(2,n+1):
11
D= x*Dm1 - a*Dm2
12
Dm2, Dm1 = Dm1, D
13
return Dm1
14

15
d19 = dickson(19,19,1)
16
d19

1876572071974094803391179

Analyzed

Python

1
d19

1876572071974094803391179

Analyzed

Python

1
import locale, sys, math, json, textwrap, re, decimal

Analyzed

Python

1
"{:,}".format(d19)

'1 876 572 071 974 094 803 391 179'

Analyzed

Python

1
# compute coefficients of Dickson polynomial D_n(x,1) via recurrence polynomial representation
2
from sympy import symbols, Poly
3

4
x = symbols('x')
5
def dickson_poly(n):

Poly(x**19 - 19*x**17 + 152*x**15 - 665*x**13 + 1729*x**11 - 2717*x**9 + 2508*x**7 - 1254*x**5 + 285*x**3 - 19*x, x,

Analyzed

Python

1
poly19.as_expr()

x**19 - 19*x**17 + 152*x**15 - 665*x**13 + 1729*x**11 - 2717*x**9 + 2508*x**7 - 1254*x**5 + 285*x**3 - 19*x

Done

A convenient way to force many factors in
p(x)    p(y)p(x) \;-\; p(y) is to use a Dickson polynomial of the first kind.
For a parameter
aCa \in \mathbb{C} in math these are defined by

D0 ⁣(x,a)=2,  D1 ⁣(x,a)=x,  Dn ⁣(x,a)=xDn1 ⁣(x,a)aDn2 ⁣(x,a)(n2),D_0\!\left(x,\, a\right) = 2,\; D_1\!\left(x,\, a\right) = x,\; D_n\!\left(x,\, a\right) = x\,D_{n-1}\!\left(x,\, a\right) - a\,D_{n-2}\!\left(x,\, a\right)\quad (n \ge 2),

and satisfy the functional identity

Dn ⁣(u+au,a)=un+anun.D_n\!\left(u + \frac{a}{u},\, a\right) = u^{n} + \frac{a^{n}}{u^{n}}.


1. Choosing the polynomial

Take a=1a = 1 and n=19n=19.
Because
nn is odd, D19 ⁣(x,1)D_{19}\!\left(x,\, 1\right) is an odd polynomial; the recurrence immediately shows it is monic and has integer (hence real) coefficients.
The coefficient of
xx is x=(1)n12n=19,x = (-1)^{\frac{n-1}{2}}\,n = -19, so all requested normalisations are satisfied.

Writing it out gives

p(x)=D19 ⁣(x,1)=x1919x17+152x15665x13+1729x112717x9+2508x71254x5+285x319x. \boxed{% p(x) = D_{19}\!\left(x,1\right) = x^{19} - 19x^{17} + 152x^{15} - 665x^{13} + 1729x^{11} - 2717x^{9} + 2508x^{7} - 1254x^{5} + 285x^{3} - 19x% }\,.


2. Irreducible components of fX  =  {p(x)=p(y)}fX \;=\; \bigl\{\, p(x) = p(y) \,\bigr\}

For Dickson polynomials one has the classical factorisation

Dn ⁣(x,1)    Dn ⁣(y,1)  =  (xy)j=1n12(x2+y22cos ⁣(2πjn)xy4sin2 ⁣(πjn)),D_n\!\left(x,1\right) \;-\; D_n\!\left(y,1\right) \;=\; (x - y)\, \prod_{j=1}^{\frac{n-1}{2}} \Bigl( x^{2} + y^{2} - 2\cos\!\bigl(\tfrac{2\pi j}{n}\bigr)\,xy - 4\sin^{2}\!\bigl(\tfrac{\pi j}{n}\bigr) \Bigr),

where each quadratic factor is irreducible over C\mathbb{C} (see, e.g., Lidl–Niederreiter, Finite Fields, §3.6).
For
n=19n=19 this gives

  • one linear component x=y;x=y;
  • nine quadratic components (corresponding to (j=1,,9).\bigl(j = 1,\,\ldots,\,9\bigr).

Hence XP1×P1X \subset \mathbb{P}^{1} \times \mathbb{P}^{1} has 1010 irreducible components, at least three of them and not all linear, as required.


3. Evaluating p(19)p(19)

Using the recurrence (or the identity Dn ⁣(x,1)  =  2Tn ⁣(x2)D_n\!\left(x,\,1\right) \;=\; 2\,T_n\!\bigl(\tfrac{x}{2}\bigr) with Chebyshev TnT_n one obtains

p(19)  =  D19 ⁣(19,1)  =  1876572071974094803391179.p(19) \;=\; D_{19}\!\left(19,\,1\right) \;=\; 1\,876\,572\,071\,974\,094\,803\,391\,179.


Thus the polynomial above fulfils every condition, and

p(19)  =  1,876,572,071,974,094,803,391,179.\boxed{% p(19) \;=\; 1{,}876{,}572{,}071{,}974{,}094{,}803{,}391{,}179 }.

OpenAI o1

Solve the following very hard math problem using your in-built knowledge of the literature:

Construct a degree 19 polynomial \ (p(x)) \ in \ mathbb{C}[x] such that \ (X := \ {\, p(x) = p(y) \, \} \ subset \ mathbb{P}^{1} \ times \ mathbb{P}^{1}\ ) has at least 3 (but not all linear) irreducible components over \ mathbb{C}. Choose \ (p(x)\ ) to be odd, monic, have real coefficients and linear coefficient \ (-19\ ) and calculate \ (p(19)\ ).

Domāja 1 m 19 s

I’m piecing together a degree 19 polynomial with only odd powers and a linear coefficient of -19, like: p(x)=x19+a17x17+…+a1xp(x) = x^{19} + a_{17}x^{17} + \ldots + a_1xp(x)=x19+a17​x17+…+a1​x.

I'm examining if the polynomial p(x)=x19+a17x17+…+a3x3−19xp(x) = x^{19} + a_{17}x^{17} + \ldots + a_3x^3 - 19xp(x)=x19+a17​x17+…+a3​x3−19x has a notable classical form, considering symmetry or factorization for multiple irreducible components.

To ensure p(x)p(x)p(x) has three or more irreducible components, I’m considering the factorization of p(x)−p(y)p(x) - p(y)p(x)−p(y) into at least three irreducible factors in C[x,y]\mathbb{C}[x,y]C[x,y].

I'm working through x19−y19x^{19} - y^{19}x19−y19 to ensure it balances linear and nonlinear factors, aiming for a polynomial with at least three irreducible components that aren't all linear.

Taking a closer look at how p(x)−p(y)p(x) - p(y)p(x)−p(y) can be factored into three distinct polynomials in xxx, aiming to achieve the desired irreducible components.

I'm thinking about how composing ppp with simpler polynomials, like xm−cx^m - cxm−c, could result in multiple irreducible components, achieving at least three distinct factors.

I’m exploring the factorization of p(x)−p(y)p(x) - p(y)p(x)−p(y) with cyclotomic polynomials. This method generates nnn linear irreducible factors, which might not achieve the required three distinct components.

I'm focusing on constructing an "odd" and monic polynomial, ensuring all exponents are odd and the leading term is x19x^{19}x19. This approach aims to achieve the desired factorization.

I'm working with the Chebyshev polynomials to ensure p(x)−p(y)p(x) - p(y)p(x)−p(y) has at least three irreducible components, leveraging their even or odd properties to manage coefficients.

Considering the odd Chebyshev polynomial T19(x)T_{19}(x)T19​(x) for potential factorization, while also examining composite polynomials of lower degrees to enhance factorization properties.

I'm analyzing how a polynomial composed of lower-degree polynomials, like (x3−3x)k(x^3 - 3x)^k(x3−3x)k, could yield p(x)−p(y)p(x) - p(y)p(x)−p(y) with at least three irreducible components.

Piecing together polynomials with integer coefficients, like (x3−3x)k(x^3 - 3x)^k(x3−3x)k, to achieve factorization in p(x)−p(y)p(x) - p(y)p(x)−p(y) with at least three irreducible components, aiming for degree 19.

I’m examining how p(x)=(x3−3x)kp(x) = (x^3 - 3x)^kp(x)=(x3−3x)k or p(x)=x19−19xp(x) = x^19 - 19xp(x)=x19−19x might yield p(x)−p(y)p(x) - p(y)p(x)−p(y) with three irreducible components, focusing on ensuring the polynomial is of degree 19.

I’m analyzing p(x)−p(y)p(x) - p(y)p(x)−p(y) into (x−y)(x18+x17y+…+y18−19)(x-y)(x^{18} + x^{17}y + \ldots + y^{18} - 19)(x−y)(x18+x17y+…+y18−19) to identify irreducible components. The polynomial factor x18+x17y+…+y18−19x^{18} + x^{17}y + \ldots + y^{18} - 19x18+x17y+…+y18−19 remains challenging to factor further.

I’m thinking through a new approach: adjusting the Chebyshev polynomial T19(x)T_{19}(x)T19​(x) to make it monic, aiming to achieve at least three irreducible components in p(x)−p(y)p(x) - p(y)p(x)−p(y).

OK, let's think through. I’m tweaking T19(x)T_{19}(x)T19​(x)'s coefficients to keep the polynomial monic and check if it simplifies into multiple irreducible components.

I'm thinking over various factorization strategies for a monic polynomial of degree 19. The goal is to ensure at least one non-linear factor and achieve at least three irreducible components in p(x)−p(y)p(x) - p(y)p(x)−p(y).

I’m updating my approach to factor x2+xy+y2−1x^2 + xy + y^2 - 1x2+xy+y2−1 over complex numbers by exploring change of variables and third roots of unity. This helps in achieving the desired polynomial structure.

I'm combining x3−xx^3 - xx3−x with x19−19xx^{19} - 19xx19−19x to tweak the polynomial's coefficients and complexity, aiming to include more non-linear factors for the desired irreducibility.

Piecing together p(x)=x19−x3−19xp(x) = x^{19} - x^3 - 19xp(x)=x19−x3−19x to ensure it’s odd, monic, and has the required linear coefficient. This targets the desired irreducible factorizations.

I’m mapping out the second factor x18+…+y18−x2−xy−y2−19x^{18} + \ldots + y^{18} - x^2 - xy - y^2 - 19x18+…+y18−x2−xy−y2−19 to see if it can split into three irreducible components.

I’m considering methods to factorize the polynomial by making it divisible by x−yx - yx−y and ensuring the remaining factor splits into exactly two irreducible components, aiming for a less complex factorization.

I’m examining the polynomial x18+x17y+…+y18x^{18} + x^{17}y + \ldots + y^{18}x18+x17y+…+y18 and noting it simplifies to x19−y19x−y\frac{x^{19} - y^{19}}{x - y}x−yx19−y19​, which might reveal further irreducible factors.

I’m mapping out the polynomial x(x18−1)−y(y18−1)x−y\frac{x(x^{18}-1) - y(y^{18}-1)}{x-y}x−yx(x18−1)−y(y18−1)​ for further factorization. This might yield just two irreducible components, which falls short of three.

I’m exploring whether the polynomial p(x)=x19−(x3)p(x) = x^19 - (x^3)p(x)=x19−(x3) can be expressed as the composition of a smaller polynomial with xkx^kxk, potentially revealing multiple irreducible components.

I'm examining if the polynomial T19(x)T_{19}(x)T19​(x) can be factored using trigonometric identities, seeking partial factorization without fully linearizing, to gain multiple irreducible components.

OK, let me see. Trigonometric identities show multiple solutions for θ\thetaθ and ϕ\phiϕ, likely leading to 19 or 38 linear factors for T19(x)T_{19}(x)T19​(x).

I’m examining how the equation arccos⁡x=±arccos⁡y+2kπ19\arccos x = \pm \arccos y + \frac{2k\pi}{19}arccosx=±arccosy+192kπ​ leads to possible multiple branches, potentially irreducible in the algebraic sense, and needing an example with at least three non-linear irreducible components.

OK, let me see. I’m pulling together details on the polynomial x3(x2−1)8+xx^3 (x^2 - 1)^8 + xx3(x2−1)8+x. It’s monic, with x19x^{19}x19 as the leading term, ensuring it meets key criteria.

I’m noting that the polynomial p(x)=x3(x2−1)8+xp(x) = x^3 (x^2 - 1)^8 + xp(x)=x3(x2−1)8+x is odd, with its linear coefficient patterning to -19.

I’m figuring out how to adjust the linear coefficient of polynomial p(x)p(x)p(x) to -19 by adding a constant factor ccc in front of xxx to ensure it’s adequately modified.

By tweaking the linear coefficient of p(x)=x3(x2−1)8+cxp(x) = x^3 (x^2 - 1)^8 + c xp(x)=x3(x2−1)8+cx to -19, it ensures the polynomial remains monic, odd, and real.

I’m working on adding a constant factor ccc to xxx in p(x)=x3(x2−1)8+cxp(x) = x^3 (x^2 - 1)^8 + c xp(x)=x3(x2−1)8+cx to ensure the linear coefficient is -19, making the polynomial monic, odd, and real.

I'm piecing together the polynomial p(x)=x3(x−1)8(x+1)8p(x) = x^3 (x-1)^8 (x+1)^8p(x)=x3(x−1)8(x+1)8 and considering how p(x)−p(y)p(x) - p(y)p(x)−p(y) might factor with factors like x−yx-yx−y.

I’m confirming p(x)p(x)p(x) is monic, odd, and real, with a linear coefficient of -19, by expanding x3(x2−1)8x^3 (x^2 -1)^8x3(x2−1)8 to set the constant ccc.

I found that for p(x) to have a coefficient of -19 for the x term, c must be -19. The polynomial, p(x), incorporates this constant and preserves the original polynomial's structure.

Below is one concrete example (over the reals) of an odd, monic, degree 19 polynomial with linear coefficient 19-19 whose zero-locus relation {p(x)=p(y)} in P1×P1\{\,p(x)=p(y)\,\}\ \text{in }\mathbb{P}^{1}\times\mathbb{P}^{1} splits into at least three irreducible components (and not all components are linear). We then compute p(19)p(19).


1. The polynomial

Consider

p(x)  =  x3(x21)8    19x.p(x) \;=\; x^{3}\,\bigl(x^{2}-1\bigr)^{8} \;-\; 19x.

We can expand

x3(x21)8  =  x19    8x17  +  28x15    56x13  +  70x11    56x9  +  28x7    8x5  +  x3.x^{3}\,\bigl(x^{2}-1\bigr)^{8} \;=\; x^{19}\;-\;8x^{17}\;+\;28x^{15}\;-\;56x^{13}\;+\;70x^{11} \;-\;56x^{9}\;+\;28x^{7}\;-\;8x^{5}\;+\;x^{3}.

Hence

p(x)  =  x19    8x17  +  28x15    56x13  +  70x11    56x9  +  28x7    8x5  +  x3    19x.p(x) \;=\; x^{19} \;-\; 8x^{17} \;+\; 28x^{15} \;-\; 56x^{13} \;+\; 70x^{11} \;-\; 56x^{9} \;+\; 28x^{7} \;-\; 8x^{5} \;+\; x^{3} \;-\; 19x.

Checking the required properties

Degree 19, monic:
The leading term is
x19x^{19}with coefficient 11.

Odd polynomial:
All exponents are odd
(19,17,,3,1),\bigl(19,\,17,\,\ldots,\,3,\,1\bigr), and the constant term is 00. Indeed,

p(x)  =  p(x),p(-x) \;=\; -\,p(x),

which makes pp an odd polynomial.

Real coefficients:
All coefficients are real integers.

Linear coefficient 19-19:
The coefficient of
xx is clearly 19-19.

At least three irreducible components, not all linear:
Over
C\mathbb{C}, the locus

X  =  {(x,y):p(x)=p(y)}    P1×P1X \;=\; \bigl\{\, (x,y) : p(x)=p(y) \,\bigr\} \;\subset\; \mathbb{P}^{1}\times\mathbb{P}^{1}

factors in part because p(x)p(x) has (for instance) the repeated factors (x21)8\bigl(x^{2}-1\bigr)^{8} in the big piece x3(x21)8x^{3}\,\bigl(x^{2}-1\bigr)^{8}. One sees that {p(x)=p(y)}\{\,p(x)=p(y)\,\} contains (at least) the divisor $${x=y\}$$ plus further factors coming from the roots x=0  or  x=±1,x = 0 \;\text{or}\; x = \pm 1, ensuring multiple irreducible components (and not all of them are hyperplanes).


2. Computing p(19)p(19)

A direct substitution x=19x=19 gives a large integer. Symbolic expansion or a computer algebra system yields

p(19)  =  1934999285524070399999639.p(19) \;=\; 1934999285524070399999639.

Hence the required value is

\boxed{\,p(19) \;=\; 1934999285524070399999639\,}. \] ​:contentReference[oaicite:0]{index=0}​

OpenAI o3 piedāvā pareizu atbildi bez meklēšanas, savukārt o1 nespēj sniegt pareizu atbildi.

Izmaksu ziņā efektīvas argumentācijas veicināšana

Izmaksas salīdzinājumā ar veiktspēju: o3‑mini un o4-mini
OpenAI o3-mini un o4-mini AIME novērtējumi
OpenAI o3-mini un o4-mini GPQA novērtējumi
Izmaksas salīdzinājumā ar veiktspēju: o1 un o3
OpenAI o3 un o4 AIME novērtējumi
OpenAI o3 un o4 GPQA novērtējumi

OpenAI o3 un o4-mini ir visinteliģentākie modeļi, kādus mēs jebkad esam izlaiduši, un tie bieži ir arī efektīvāki nekā to priekšgājēji, OpenAI o1 un o3‑mini. Piemēram, 2025. gada AIME matemātikas sacensībās o3 izmaksu-veiktspējas robežvērtība bija ievērojami augstāka par o1. Tāpat arī o4-mini robežvērtība ir pārāka salīdzinājumā ar o3‑mini. Vispārīgi runājot, mēs sagaidām, ka lielākajā daļā reālās pasaules lietojumu o3 un o4-mini modeļi būs gan gudrāki, gan lētāki nekā o1 un o3‑mini.

Drošība

Katrs modeļa iespēju uzlabojums prasa samērīgus drošības uzlabojumus. Attiecībā uz OpenAI o3 un o4-mini mēs esam pilnībā pārbūvējuši mūsu drošības apmācību datus, pievienojot jaunus atteikuma ieteikumus tādās jomās kā bioloģiskie draudi (biorisk), ļaunprātīgas programmatūras ģenerēšana un ierobežojumu apiešana. Šie atjauninātie dati ir ļāvuši o3 un o4-mini panākt spēcīgu veiktspēju mūsu iekšējos atteikumu kritērijos (piemēram, instrukciju hierarhija, ierobežojumu apiešana). Papildus labiem modeļu atteikumu rādītājiem esam izstrādājuši arī sistēmas līmeņa riska samazināšanas pasākumus, lai atzīmētu bīstamas uzvednes galvenajās riska zonās. Līdzīgi kā mūsu iepriekšējā darbā ar attēlu ģenerēšanu, mēs apmācījām LLM monitoru domāšanā, kas darbojas, pamatojoties uz cilvēka rakstītām un interpretētām drošības specifikācijām. Piemērojot šo monitoru bioriska atpazīšanā, tas veiksmīgi atzīmēja ~99% sarunu mūsu darbinieku “sarkanās komandas” kampaņas laikā.

Mēs veicām abu modeļu slodzes testus, izmantojot mūsu līdz šim spēcīgāko drošības programmu. Saskaņā ar mūsu atjaunināto Sagatavotības Sistēmu mēs izvērtējām o3 un o4-mini darbību trijās sistēmas spēju izpētes jomās: bioloģiskajā un ķīmiskajā, kiberdrošības un mākslīgā intelekta pašpilnveidošanās jomā. Pamatojoties uz šo novērtējumu rezultātiem, esam secinājuši, ka gan o3, gan o4‑mini joprojām nepārsniedz sistēmas noteikto augsto līmeni visās trīs kategorijās. Šo novērtējumu detalizēti rezultāti ir publicēti pievienotajā sistēmas kartē⁠.

Codex CLI: labākā spriestspēja terminālī

Mēs dalāmies arī ar jaunu eksperimentu: Codex CLI - ērti lietojamu kodēšanas aģentu, ko varai palaist no sava termināļa. Tas darbojas tieši tavā datorā un ir izstrādāts, lai maksimāli palielinātu tādu modeļu kā o3 un o4-mini spriešanas spējas un sniegtu turpmāku atbalstu papildu API modeļiem, piemēram, GPT‑4.1.

Tu vari izmantot multimodālās argumentācijas priekšrocības komandrindā ievadot ekrānuzņēmumus vai zemas precizitātes skices, pievienojot lokālu piekļuvi savam kodam. Mēs to uzskatām par nelielu saskarni, kas savieno mūsu modeļus ar lietotājiem un viņu datoriem. Codex CLI tagad ir pilnībā atvērta koda versija vietnē github.com/openai/codex(atveras jaunā logā) .

Vienlaikus mēs uzsākam 1 miljona ASV dolāru vērtu iniciatīvu, lai atbalstītu projektus, kuros tiek izmantoti Codex CLI un OpenAI modeļi. Mēs izvērtēsim un pieņemsim pieteikumus dotācijām 25 000 ASV dolāru apmērā API kredītu veidā. Priekšlikumus var iesniegt šeit.

Piekļuve

Sākot ar šodienu ChatGPT Plus, Pro un Team lietotāji modeļu atlasītājā redzēs o3, o4-mini un o4-mini-high, tiem aizstājot o1, o3‑mini un o3‑mini‑high modeļus. ChatGPT Enterprise un Edu lietotāji saņems piekļuvi pēc nedēļas. Free lietotāji var izmēģināt o4-mini, pirms vaicājuma iesniegšanas ziņojuma logā atlasot opciju "domāt". Tarifu ierobežojumi visos plānos paliek nemainīgi salīdzinājumā ar iepriekšējo modeļu kopumu.

Mēs plānojam izlaist OpenAI o3‑pro pēc dažām nedēļām ar pilnu rīku atbalstu. Pagaidām Pro lietotāji var piekļūt o1‑pro.

Gan o3, gan o4-mini modeļi jau šodien ir pieejami arī izstrādātājiem, izmantojot Chat Completions API un Responses API (dažiem izstrādātājiem būs jāpārbauda savas organizācijas(atveras jaunā logā), lai piekļūtu šiem modeļiem). Responses API atbalsta argumentācijas kopsavilkumus, iespēju saglabāt spriešanas tekstvienības funkciju izsaukumos, lai uzlabotu veiktspēju, un drīzumā atbalstīs arī tādus iebūvētos rīkus kā meklēšana tīmeklī, failu meklēšana un koda interpretēšana modeļa argumentācijā. Lai sāktu darbu, izpēti mūsu dokumentus(atveras jaunā logā) un seko līdzi jaunumiem.

Kas būs tālāk?

Šie atjauninājumi atspoguļo mūsu modeļu attīstības virzienu: mēs apvienojam o sērijas specializētās spriestspējas ar GPT sērijas dabiskās sarunvalodas un rīku izmantošanas potenciālu. Apvienojot šo izlaidumu stiprās puses, mūsu nākotnes modeļi atbalstīs nevainojamas, dabiskas sarunas līdzās proaktīvai rīku izmantošanai un progresīvai problēmu risināšanai.


2025. gada 28. jūlija atjauninājums: SWE-Lancer datu kopa un rezultāti atjaunināti 2025. gada 17. jūlijā un pieejami: https: //github.com/openai/preparedness(atveras jaunā logā) un mūsu sistēmas kartēs. Šis atjauninājums atrisina vairākas problēmas, kas ietekmēja maksas pakalpojumu rezultātus, un novērš prasību pēc interneta savienojamības izpildes laikā, novēršot galveno modeļa veiktspējas mainīguma avotu.

2025. gada 16. aprīlļa atjauninājums: tika atjaunināti o3 Charxiv-r un Mathvista rezultāti, lai atspoguļotu sistēmas uzvednes izmaiņas, kas nebija iekļautas sākotnējā novērtējumā.

Tiešraides atkārtojums

Autors

OpenAI

Zemsvītras piezīmes

* Lai samazinātu novirzi, tau-bench novērtējuma skaitļi tiek vidēji aprēķināti pēc piecām izpildēm un šis novērtējums tiek veikts bez pielāgotiem rīkiem vai uzvednēm. Mēs atklājām, ka tau-bench mazumtirdzniecības izlaidumi ir vairāk pakļauti lietotāja modeļa kļūdām. Iekrāsotā stabiņa skaitļi tiek sagatavoti ar GPT-4.1 kā lietotāja modeli, jo instrukciju izpildē tas ir ievērojami labāks par GPT-4o.

* SWE-bench maksimālais konteksta garums ir 256 tūkstoši, kas uzlabo o4-mini darbības ātrumu par aptuveni 3% un ietekmē o3 darbības ātrumu par <1%. Mēs arī izslēdzam 23 paraugus, kurus nav iespējams palaist mūsu iekšējā infrastruktūrā.

** Ja ir iespējota pārlūkošana, modelis dažkārt var atrast precīzas atbildes tiešsaistē, piemēram, izlasot emuāru ierakstus ar datu kopas uzdevumu paraugiem. Mēs mazinām bažas par modeļa krāpšanos pārlūkošanas laikā, izmantojot divas stratēģijas:

  • Bloķējot domēnus, kuros esam iepriekš novērojuši modeļa krāpšanos.

  • Kā uzraugu izmantojot spriestspējas modeli, lai pārbaudītu visas tekstvienības katrā mēģinājumā un identificētu aizdomīgu uzvedību. Aizdomīga uzvedība tiek definēta kā "lapa, fails vai fragments, kura galvenais mērķis ir sniegt precīzu atbildi uz šo konkrēto jautājumu, piemēram, oficiālā vērtēšanas atslēga, nopludināta "risinājuma" būtība vai diskusija, kurā burtiski citēta gatava atbilde." Labdabīga uzvedība tiek definēta kā "Jebkurš autoritatīvs resurss, kuru cilvēks var mēķtiecīgi izmantot (dokumentācija, rokasgrāmatas, zinātniski pētījumi, atzīti raksti), pat ja tajos nejauši atrodama pareizā atbilde." Par nepareiziem tiek uzskatīti visi mēģinājumi, kurus uzraugs ir atzinis par aizdomīgiem. Lielākā daļa paraugu, kas neizturēja šo pārbaudi, ietvēra problēmas, kuru precīzs risinājums bija pieejams vairākos interneta avotos, kas nav saistīti ar HLE.

Visbeidzot, mūsu pārlūkošanas novērtējumi var nebūt pilnībā reproducējami OpenAI API, jo ChatGPT un OpenAI API meklētājprogrammu aizmugures sistēmas atšķiras. Šie rezultāti ir paredzēti, lai atspoguļotu ChatGPT lietotāju pieredzi, taču atkarībā no pieprasījuma meklēšanas konfigurācija laika gaitā var mainīties.

Līdzstrādnieki

Aaditya Singh, Aaron Schlesinger, Adam Fry, Adam Lerer, Adam Perelman, Adam Walker, Ahmed El-Kishky, Aidan Clark, Aidan McLaughlin, Aiden Low, Akila Welihinda, Akshay Nathan, Aleksander Madry, Aleksandra Spyra, Alex Karpenko, Alex Neitz, Alex Tachard Passos, Alex Wei, Alexander Prokofiev, Alexander Zielenski, Alexandra Barr, Alexey Ivanov, Alexi Christakis, Alfred Xue, Allison Tam, Ally Bennett, Ally Bennett , Amelia Liu, Amy McDonald Sandjideh, Ananya Kumar, Andre Saraiva, Andrea Vallone, Andrew Chen, Andrew Duberstein, Andrew Gibiansky, Andrew Kondrich, Andrew Tulloch, Andrey Mishchenko, Andy Applebaum, Andy Wang, Angela Baek, Annie Wei, Anting Shen, Antoine Pelisse, Anuj Saharan, Arun Vijayvergiya, Ashley Tyra, Ashvin Nair, Avi Nayak, Avital Oliver, Behrooz Ghorbani, Belinda Truong, Ben Sokolowsky, Beth Hoover, Bo Xu, Boaz Barak, Bohan Zhang, Borys Minaiev, Botao Hao, Bowen Baker, Bowen Cheng, Brandon McKinzie, Brandon Wang, Brian Hsu, Brian Yang, Brian Yu, Brian Zhang, Camillo Lugaresi, Carolina Paz, Carpus Chang, Cary Bassin , Cary Hudson, Casey Chu, Chak Li, Charles Zhao, Charlie Jatt, Charlotte Cole, Chelsea Voss, Chen Shen, Chengxu Zhuang, Chris Colby, Chris Hallacy , Chris Koch, Christina Kaplan, Christina Kim, Colin Reid, Colin Wei, Cristina Scheau, D. Sculley, Damien Deville, Dan Roberts, Dana Palmie, Dane Stuckey, Daniel Levine, David Hu, David Martin, David Robinson, David Sasaki, Davis Wu, Derek Chen, Dibya Bhattacharjee, Dimitris Tsipras, Dinghua Li, DJ Strouse, dmed Medina, Drew Hintz, Eddie Zhang, Edmund Wong, Elaine Ya Le, Eli Yani , Elizabeth Proehl, Emily Sokolova, Enoch Cheung, Eri Schwartz, Eric Mitchell, Eric Ning, Eric Sigler, Eric Wallace, Eugenio Panero, Evan Mays, Evgenii Nikishin, Fan Wang, Fangyuan Li, Filippo Raso, Foivos Tsimpourlas, Fouad Matin, Francis Song, Francis Zhang, Gary Yang, Gene Oden, Giambattista Parascandolo, Gildas Chabot, Grace Kim, Grace Zhao, Greg Brockman, Gregory Valiant, Guillaume Leclerc, Hadi Salman, Haitang Hu, Hannah Sheahan, Hao Sheng, Haoyu Wang, Henrique Ponde de Oliveira Pinto, Henry Aspegren, Heqing Yan, Hessam Bagherinezhad, Hongyu Ren, Hunter Lightman, Hyeonwoo Noh, Ian Kivlichan, Ian Sohl, Ignasi Clavera, Ikai Lan, Ilge Akkaya, Ilya Kostrikov, Irina Kofman, Isa Fulford, Jake Brill, Jakub Pachocki, James Betker, James Lee, James Qin, Jamie Kiros, Jason Ai, Jay Wang, Jean Harb, Jeff Mickey, Jeffrey Han, Jeffrey Wang, Jeremy Chen, Jerry Tworek, Jessica Liang, Jessica Shieh, Ji Lin, Jiahui Yu, Jianfeng Wang, Jie Tang, Jihan Yin, Jing Li, Joanne Jang, Joel Morris, Johannes Ferstad, Johannes Heidecke, John Fishbein, Jon Okun, Jonathan Gordon, Joost Huizinga, Jos Kraaijeveld, Joseph Mo, Josh Lawson , Josh Tobin, Junhua Mao, Kai Chen, Kai Hayashi, Karan Singhal, Karina Nguyen, Katy Shi, Kelly Stirman, Kenji Hata, Kenny Nguyen, Keren Gu-Lemberg, Kevin Gladstone, Kevin King, Kevin Liu, Kevin Lu, Kevin Park, Kevin Stone, Kevin Weil, Kevin Whinnery, Kevin Yu, Kote Mushegiani, Kristen Ying, Kristian Georgiev, Kshitij Gupta, Kyle Kosic, Lama Ahmad, Larry Lv, Lauren Itow, Lauren Yang, Lee Byron, Leo Chen, Leo Liu, Leon Maksin, Leyton Ho, Li Jing, Liang Xiong, Lin Yang, Linden Li, Lorenz Kuhn, Louis Feuvrier, Lu Zhang, Łukasz Kaiser, Mahmoud Eariby, Maja Trębacz, Manas Joglekar, Manoli Liodakis, Manuka Stratta, Mark Chen, Mark Hudnall, Mark Sun, Mark Wang, Martin Li, Marvin Zhang, Mateusz Litwin, Matt Jones, Matt Lim, Max Johnson, Max Schwarzer, Mayank Gupta, Meghan Shah, Mengqing Wang, Mengyuan Yan, Mia Glaese, Michael Bolin, Michael Lampe, Michael Malek, Michael Sharman, Michael Zhang, Michele Wang, Michelle Pokrass, Miguel Oom Temudo de Castro, Mihai Florian, Mike McClay, Mike Trpcic, Miki Habryn, Miles Wang, Ming Chen, Mingxuan Wang, Minnia Feng, Mitchell Gordon, Mo Bavarian, Mostafa Rohaninejad, Nacho Soto, Nakul Khanna, Nat McAleese, Natalie Staudacher, Natan LaFontaine, Neel Ajjarapu, Nick Felt, Nick Turley, Nikil Pancha, Nikita Mikhaylin, Niko Felix, Nikunj Handa, Ning Liu, Nishant Rai, Noah Jorgensen, Noam Brown, Oleg Boiko, Oleg Murk, Olivia Watkins, Olivier Godement, Oona Gleeson, Paul Ashbourne, Pavel Belov, Peter Flockhart, Peter Hoeschele, Peter Zhokhov, Philip Pronin, Phillip Guo, Phoebe Thacker, Prafulla Dhariwal, Prashanth R, Rachel Dias, Rahul Arora, Rajkumar Samuel, Rasmus Rygaard, Ravi Teja Mullapudi, Raymond Li, Raz Gaon, Reah Miyara, Reiichiro Nakano, Reimar Leike, Rennie Song, Rhythm Garg, RJ Marsan, Robert Xiong, Robin Brown, Roman Tsiupa, Rui Shu, Ruslan Nigmatullin, Saachi Jain, Saagar Patel, Sam Altman, Sam Toizer, Sam Toyer, Samir Ahmed, Samuel Miserendino, Samuel Wolrich , Sandhini Agarwal, Santiago Hernández, Sarah Dong, Savannah Heon, Scott Ethersmith, Scott Mayer McKinney, Sean Fitzgerald, Sever Banesiu, Shamez Hemani, Shengjia Zhao, Shengli Hu, Shibani Santurkar, Shreyas Krishnaswamy, Shuchao Bi, Shunyu Yao, Shuyuan Zhang, Simón Posada Fishman, Spencer Papay, Spug Golden, Srinivas Narayanan, Stanley Hsieh, Stephen Logsdon, Sundeep Tirumalareddy, Tal Stramer, Tao Wang, Tao Xin, Taylor Gordon, Tejal Patwardhan, Thibault Sottiaux, Tina Sriskandarajah, Tony Casparro, Tony Zhao, Trevor Creech, Uzair Navid Iftikhar, Valerie Qi, Vineet Kosaraju, Vishal Kuo, Vitchyr Pong, Vivek Verma, Vlad Petrov, Wenda Zhou, Wenlei Xie, Wenting Zhan, Will DePue, Will Ellsworth, William Sheu, Wyatt Thompson, Yaming Lin, Yann Dubois, Yaodong Yu, Yara Khakbaz, Yash Patil, Yifan Wu, Yilong Qin, Yining Chen, Yirui Zhang, Yo Shavit , Young Cha, Yunyun Wang, Yushi Wang, Zack Sultan, Zehao Dou, Zewei Chu, Zheng Shao, Zhigang Wang, Zhishuai Zhang, Zihao Zhang