Paper Citation Record · LEDGER

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text

As of 4 August 2026, this Paper Citation Record lists 78 of 78 outbound references and 2 inbound Pith citation observations for arXiv:2604.20051.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2604.20051 v2

Coverage vector

measured 78 of 78 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T01:51:00.913166Z

measured 80 of 80 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T01:47:18.868835Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

78 of 78 outbound references displayed

verified exact23
verified fuzzy41
unresolved10
parse uncertain0
malformed identifier1
metadata mismatch3

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c16066c7-4b69-46b8-80e6-d3f021fd5220 · outbound

This paper cites HealthBench: Evaluating Large Language Models Towards Improved Human Health.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text HealthBench: Evaluating Large Language Models Towards Improved Human Health

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:18:21.444858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b8b22f47-daa5-455e-80bb-bc43f4b79248 · outbound

This paper cites SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:21:18.201366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9b305eee-49a1-4e18-b7ad-5f8008fd23ad · outbound

This paper cites Self-playing Adversarial Language Game Enhances LLM Reasoning.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Self-playing Adversarial Language Game Enhances LLM Reasoning

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:21:16.065828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation cad5ea11-a550-4ee0-88cf-28b1382f298d · outbound

This paper cites Scaling Instruction-Finetuned Language Models.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Scaling Instruction-Finetuned Language Models

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T01:23:37.463337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5ed87529-ca00-4062-963b-8737ce276527 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Training Verifiers to Solve Math Word Problems

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-11T13:21:16.791554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ee773845-5881-47a3-aa5b-3c7013d6cb71 · outbound

This paper cites DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-11T13:21:16.865950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1b4f9982-637e-4fc4-b90c-afdd0c0ea026 · outbound

This paper cites Qa-lign: Aligning llms through constitutionally decomposed qa.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Qa-lign: Aligning llms through constitutionally decomposed qa

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.332412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 13ee7d65-ed37-46ce-85f8-ba1621619c42 · outbound

This paper cites Openwebtext corpus.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Openwebtext corpus

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.335087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4b045794-9b96-4880-9d6f-2330be434a01 · outbound

This paper cites Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:07:56.884714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a50147df-d2eb-4762-bf22-a40cc296e96f · outbound

This paper cites Lighteval: A lightweight framework for llm evaluation.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Lighteval: A lightweight framework for llm evaluation

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.356439Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f6e52eaa-d0ce-4952-b903-f137865b1e89 · outbound

This paper cites arXiv preprint arXiv:2511.10507 , year=.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text arXiv preprint arXiv:2511.10507 , year=

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:21:17.432193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ead073ee-97ef-44fa-9525-ef81d57423d6 · outbound

This paper cites Measuring mathematical problem solving with the math dataset.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Measuring mathematical problem solving with the math dataset

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.320248Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 16ef9c3e-12c6-4542-bc13-dc746c5cc050 · outbound

This paper cites R-Zero: Self-Evolving Reasoning LLM from Zero Data.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text R-Zero: Self-Evolving Reasoning LLM from Zero Data

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-14T19:23:29.765778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 35977edc-4327-404e-9af5-ab41d386ea9c · outbound

This paper cites Dcrm: A heuristic to measure response pair quality in preference optimization.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Dcrm: A heuristic to measure response pair quality in preference optimization

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.314439Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e6e2648b-8406-4f60-a171-efc2ff33a10e · outbound

This paper cites Large language models can self-improve.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Large language models can self-improve

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.317630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation df2ee1d2-1693-4e1f-85b2-8b40ec090896 · outbound

This paper cites Reinforcement Learning with Rubric Anchors.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Reinforcement Learning with Rubric Anchors

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:21:15.766370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 46953652-3dbc-4c3c-b4ce-d0cec873f233 · outbound

This paper cites TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-11T15:00:28.883814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a918c201-3f10-4d45-90eb-574ba0ab1a87 · outbound

This paper cites Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.322811Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 13561926-7329-4bec-a0c7-7d0a9ae73aef · outbound

This paper cites Truthfulqa: Measuring how models mimic human falsehoods.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Truthfulqa: Measuring how models mimic human falsehoods

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.306823Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 44782e97-3381-4c8d-bcce-60eb2d38ca20 · outbound

This paper cites Spice: Self-play in corpus environments improves reasoning.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Spice: Self-play in corpus environments improves reasoning

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:21:16.426077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0cebd866-f376-4158-9a07-dd5a5d0450fd · outbound

This paper cites Decoupled weight decay regularization.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Decoupled weight decay regularization

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.297173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 23004da3-0573-4573-80d6-05c6ebcc779f · outbound

This paper cites Advanced version of gemini with deep think officially achieves gold-medal standard at the international mathematical olympiad.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Advanced version of gemini with deep think officially achieves gold-medal standard at the international mathematical olympiad

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.354128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6cc02ad7-93fe-46f2-a834-5e82891d9f13 · outbound

This paper cites Building trust in clinical llms: Bias analysis and dataset transparency.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Building trust in clinical llms: Bias analysis and dataset transparency

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.289794Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f58203d7-0612-46ac-beab-f7a969ec5519 · outbound

This paper cites Eq-bench creative writing benchmark v3.https://github.com/EQ-bench/ creative-writing-bench.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Eq-bench creative writing benchmark v3.https://github.com/EQ-bench/ creative-writing-bench

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.368160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 87aef807-ba0a-4b09-9a75-1a2b97409d78 · outbound

This paper cites Medmcqa: A large-scale multi-subject multi-choice dataset for medical domain question answering.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Medmcqa: A large-scale multi-subject multi-choice dataset for medical domain question answering

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.294895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ecc7d154-0fe6-434c-b2ec-717878a2d5df · outbound

This paper cites van Duijn, Niki Stein, Mike Preuss, Peter van der Putten, and Kees Joost Batenburg.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text van Duijn, Niki Stein, Mike Preuss, Peter van der Putten, and Kees Joost Batenburg

Reference 27

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T13:21:15.039504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a9194573-f9b1-4726-a93e-d20276e60934 · outbound

This paper cites Direct Preference Optimization: Your Language Model is Secretly a Reward Model.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Reference 28

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T13:21:15.477936Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b906ade4-0446-4b02-979d-2b8156a451d0 · outbound

This paper cites an unresolved cited work.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-05-23T01:52:24.299211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3cf4977f-485d-41f4-aaa5-3b550ffc7f41 · outbound

This paper cites Sutherland.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Sutherland

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.351536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b446829e-512a-4c08-b734-14fa0f269c19 · outbound

This paper cites Karl: Knowledge agentsvial reinforcement learning.arXiv preprint.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Karl: Knowledge agentsvial reinforcement learning.arXiv preprint

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:21:15.049063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation baea06cd-7924-41b9-9015-7b0e5ff2c439 · outbound

This paper cites Online rubrics elicitation from pairwise comparisons.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Online rubrics elicitation from pairwise comparisons

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:21:17.015919Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation fcba67ff-a40e-41c0-a2c7-7c2a4c532907 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Proximal Policy Optimization Algorithms

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-05-11T13:21:17.128690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8f0b2e61-a066-4b38-b789-48f668c93a99 · outbound

This paper cites DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-20T00:00:28.487879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0fdb52c6-4825-4dc1-bab5-1f2408888556 · outbound

This paper cites v 1: Unifying generation and self-verification for parallel reasoners.arXiv preprint arXiv:2603.04304, 2026a.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text v 1: Unifying generation and self-verification for parallel reasoners.arXiv preprint arXiv:2603.04304, 2026a

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:21:15.655944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 882aaab8-7a17-4de6-8f88-86d8b69a5d45 · outbound

This paper cites Book titles and abstracts.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Book titles and abstracts

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.345305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 004af272-0f62-4965-88bb-d0c37e4a3a2b · outbound

This paper cites Mind the gap: Examining the self-improvement capabilities of large language models.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Mind the gap: Examining the self-improvement capabilities of large language models

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.278955Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a16b9864-e86d-454b-844b-7afae12100a8 · outbound

This paper cites Understanding the performance gap between online and offline alignment algorithms.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Understanding the performance gap between online and offline alignment algorithms

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:21:16.758349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d3c19b3e-ed8b-411a-8b86-303893dc19c8 · outbound

This paper cites GPT-4 Technical Report.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text GPT-4 Technical Report

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-05-11T13:21:17.585101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2d8c22e1-6318-4674-b612-7b551211262f · outbound

This paper cites Qwen2.5 Technical Report.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Qwen2.5 Technical Report

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-05-11T13:21:17.816751Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 181960ab-b1c2-485c-8966-4aba5b9046ab · outbound

This paper cites Will we run out of data? limits of llm scaling based on human-generated data.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Will we run out of data? limits of llm scaling based on human-generated data

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.340812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation eb4e54e2-abdf-414b-b079-7117811a630e · outbound

This paper cites Checklists are better than reward models for aligning language models.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Checklists are better than reward models for aligning language models

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.338244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f2bd45f3-8fbb-42a1-912d-b190b80ed32e · outbound

This paper cites Mmlu-pro: A more robust and challenging multi-task language understanding benchmark.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Mmlu-pro: A more robust and challenging multi-task language understanding benchmark

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.276123Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c0593d53-32db-40ea-8e65-eccbeecc140f · outbound

This paper cites Self-rewarding language models.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Self-rewarding language models

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.281802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation fdfe0c9d-e0e2-414b-9b12-156e970004f7 · outbound

This paper cites Better llm reasoning via dual-play.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Better llm reasoning via dual-play

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:21:17.500054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 26d16d03-9b4c-430a-b486-f55d7916c973 · outbound

This paper cites Absolute Zero: Reinforced Self-play Reasoning with Zero Data.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Absolute Zero: Reinforced Self-play Reasoning with Zero Data

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-05-13T18:23:09.397455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d22ca3be-823c-4c42-84d8-f51a07a433b9 · outbound

This paper cites Xing, Hao Zhang, Joseph E.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Xing, Hao Zhang, Joseph E

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.284299Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c794d79d-057f-49d1-ad6a-e9b15a81eba8 · outbound

This paper cites Instruction-Following Evaluation for Large Language Models.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Instruction-Following Evaluation for Large Language Models

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-05-11T13:21:16.695019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c8b42532-f4e1-44ed-84cc-8cc5bb2445ca · outbound

This paper cites Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-08-04T02:23:17.018487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ec11e069-6aa6-4de0-9353-d988fd8028ef · outbound

This paper cites Self-Challenging Language Model Agents.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Self-Challenging Language Model Agents

Reference 50

Resolution: malformed identifier; arxiv_id, observed 2026-05-11T13:21:15.160379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8e7bbc34-6935-49cc-83fd-12c915292c90 · outbound

This paper cites an unresolved cited work.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Unresolved cited work

Reference 51

Resolution: unresolved; raw_fallback, observed 2026-05-23T01:52:24.271410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 400b7898-0135-480e-9c81-e19e4b02b72c · outbound

This paper cites an unresolved cited work.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Unresolved cited work

Reference 52

Resolution: unresolved; raw_fallback, observed 2026-05-23T01:52:24.359068Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b089ffea-c2bf-482c-ab3c-5383421a50ec · outbound

This paper cites an unresolved cited work.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Unresolved cited work

Reference 53

Resolution: unresolved; raw_fallback, observed 2026-05-23T01:52:24.273495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5383c140-1ba4-46a1-a067-85939b894728 · outbound

This paper cites Enzyme Identification.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Enzyme Identification

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.287023Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 924c6ae8-f303-4138-932e-be8ec1d40f06 · outbound

This paper cites an unresolved cited work.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Unresolved cited work

Reference 55

Resolution: unresolved; raw_fallback, observed 2026-05-23T01:52:24.304236Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f72c0fbb-70ca-4011-b8f8-c017c65e93d4 · outbound

This paper cites Figure 44: Query (Instruction Following).

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Figure 44: Query (Instruction Following)

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.325189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1feccc5b-73fa-4e8e-950f-4968331f9809 · outbound

This paper cites an unresolved cited work.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Unresolved cited work

Reference 57

Resolution: unresolved; raw_fallback, observed 2026-05-23T01:52:24.292393Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c7a45f16-28bc-4b44-b3bb-50d36e1f2d88 · outbound

This paper cites criterion_1.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text criterion_1

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.301430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2a659855-aabb-49c3-bad4-a3e3de8d1645 · outbound

This paper cites He stated that he would continue to work within the framework of the Philippine constitution and existing governmental structures.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text He stated that he would continue to work within the framework of the Philippine constitution and existing governmental structures

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.311963Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation bea8f7a6-a5f0-47e3-a56c-49d776582e49 · outbound

This paper cites name": "Correctness of the first part of the answer.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text name": "Correctness of the first part of the answer

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.266993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4c7e9617-7256-4cd4-88ef-a583aebe27bc · outbound

This paper cites He stated that the declaration was made under duress due to threats from opposing groups and to protect national interest.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text He stated that the declaration was made under duress due to threats from opposing groups and to protect national interest

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.348055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation abfbb882-59a3-4b30-b198-13856b5b3055 · outbound

This paper cites name": "Correctness of the first part of the answer.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text name": "Correctness of the first part of the answer

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.384418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e573b348-c5b5-4967-8abb-f7271f4bf106 · outbound

This paper cites an unresolved cited work.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Unresolved cited work

Reference 63

Resolution: unresolved; raw_fallback, observed 2026-05-23T01:52:24.262169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c6c0fe7b-fe19-416e-a416-8d538ddf34da · outbound

This paper cites Ensure that it is necessary and sufficient to use these facts to derive the correct answer to the problem.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Ensure that it is necessary and sufficient to use these facts to derive the correct answer to the problem

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.382216Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b908ea69-d599-4d05-a49e-8de5f4d22450 · outbound

This paper cites * Provide a reference answer within <answer>...</answer> tags.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text * Provide a reference answer within <answer>...</answer> tags

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.255746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a32a39af-36e9-4b1e-8309-4265a1689059 · outbound

This paper cites an unresolved cited work.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Unresolved cited work

Reference 67

Resolution: unresolved; raw_fallback, observed 2026-05-23T01:52:24.259907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ef5d8dc3-4013-404c-941c-8e7f960e1109 · outbound

This paper cites ## Format * Enclose the question statement within <problem>...</problem> tags.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text ## Format * Enclose the question statement within <problem>...</problem> tags

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.264469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 40fc4e96-66de-4203-b52b-5e63518f6c62 · outbound

This paper cites according to the text sample.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text according to the text sample

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.330038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8af7f8f5-6931-4834-a013-b780d491fdc4 · outbound

This paper cites an unresolved cited work.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Unresolved cited work

Reference 70

Resolution: unresolved; raw_fallback, observed 2026-05-23T01:52:24.363704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9ea86125-3e8a-4cca-893d-2c0ad75b6d66 · outbound

This paper cites Length: 1000 words.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Length: 1000 words

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.361507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4134d31f-b407-4820-a9b3-136d3806fb2b · outbound

This paper cites according to the knowledge.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text according to the knowledge

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.365723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d778a6bd-ac8f-48d8-9a0b-f68d07aa19fb · outbound

This paper cites criterion_1.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text criterion_1

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.386631Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation bf01da50-c8c1-499b-8678-5d123539d64e · outbound

This paper cites In general, the reference answer should have a high quality compared to the candidate answers, but this is not always true.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text In general, the reference answer should have a high quality compared to the candidate answers, but this is not always true

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.379607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 994a32f2-05a2-41e0-8a3f-2c3120e3b373 · outbound

This paper cites an unresolved cited work.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Unresolved cited work

Reference 75

Resolution: unresolved; raw_fallback, observed 2026-05-23T01:52:24.372941Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a7f4a737-b37d-4a43-80c2-08d93a67021d · outbound

This paper cites factuality.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text factuality

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.269116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e54c8d39-e205-41e6-98bf-944ee822c9c0 · outbound

This paper cites YYY" of.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text YYY" of

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.327410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 97e0a20b-77e7-4aca-ad10-aece5e24e217 · outbound

This paper cites Not applicable.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Not applicable

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.370694Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ccd96c6c-c2a5-401b-8cbe-6ffd1ce1abf2 · outbound

This paper cites XXX". To describe it, instead of saying.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text XXX". To describe it, instead of saying

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.375045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e80b7bcd-7cdf-42d8-bdbd-e244093b742c · outbound

This paper cites criterion_1.

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text criterion_1

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T01:52:24.377227Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Pith citing papers

Observation cbeba9fc-2602-4817-898f-741f2802f596 · inbound

SERPO: Self-Evolving Rubric Policy Optimization for Open-Ended Test-Time Reinforcement Learning cites this paper.

SERPO: Self-Evolving Rubric Policy Optimization for Open-Ended Test-Time Reinforcement Learning Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text

Reference 53

Resolution: unresolved; no resolver link, observed 2026-07-30T18:33:28.486944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4fc8f56-bfcf-4177-9ee4-d60d00d5ce5a · inbound

SERPO: Self-Evolving Rubric Policy Optimization for Open-Ended Test-Time Reinforcement Learning cites this paper.

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T01:47:18.868835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.