{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YLRP7RP5JFXWUHKRHOYT4VUHFY","short_pith_number":"pith:YLRP7RP5","canonical_record":{"source":{"id":"2411.00062","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T08:15:32Z","cross_cats_sorted":["cs.AI","physics.data-an","stat.ML"],"title_canon_sha256":"a60a53197c8e4dd519e031d0f7c86ecb9eb231eb786399fc446830b1de64d037","abstract_canon_sha256":"e75bcf5a0e3f7296ed4e65d0492d03fd13b461d073410576f0a61f4ef4413ebb"},"schema_version":"1.0"},"canonical_sha256":"c2e2ffc5fd496f6a1d513bb13e56872e3dc877509392a63e2bca047794e2aeb9","source":{"kind":"arxiv","id":"2411.00062","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.00062","created_at":"2026-07-05T10:46:58Z"},{"alias_kind":"arxiv_version","alias_value":"2411.00062v3","created_at":"2026-07-05T10:46:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00062","created_at":"2026-07-05T10:46:58Z"},{"alias_kind":"pith_short_12","alias_value":"YLRP7RP5JFXW","created_at":"2026-07-05T10:46:58Z"},{"alias_kind":"pith_short_16","alias_value":"YLRP7RP5JFXWUHKR","created_at":"2026-07-05T10:46:58Z"},{"alias_kind":"pith_short_8","alias_value":"YLRP7RP5","created_at":"2026-07-05T10:46:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YLRP7RP5JFXWUHKRHOYT4VUHFY","target":"record","payload":{"canonical_record":{"source":{"id":"2411.00062","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T08:15:32Z","cross_cats_sorted":["cs.AI","physics.data-an","stat.ML"],"title_canon_sha256":"a60a53197c8e4dd519e031d0f7c86ecb9eb231eb786399fc446830b1de64d037","abstract_canon_sha256":"e75bcf5a0e3f7296ed4e65d0492d03fd13b461d073410576f0a61f4ef4413ebb"},"schema_version":"1.0"},"canonical_sha256":"c2e2ffc5fd496f6a1d513bb13e56872e3dc877509392a63e2bca047794e2aeb9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:58.120768Z","signature_b64":"zgchgZ+VOmzoiwDsvZ0ln8VCnXQq155trhE3Ok7tTnLhfAINmPzdZKy03dfJfcsC1xGIhhcF2qD5K0KjDm4JBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2e2ffc5fd496f6a1d513bb13e56872e3dc877509392a63e2bca047794e2aeb9","last_reissued_at":"2026-07-05T10:46:58.120258Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:58.120258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.00062","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:46:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NfGOW+7b+SpEYNYVqeLa7bwtDgOc3qEYxhvnK+Xx/AidTd5XTGXfCVrAeIrIfRhlVXuL6Wzdo7u7KXiks/lxCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T22:57:35.045586Z"},"content_sha256":"0e3118742ffdaed1c6dad28a1c1435d1b40cbba9e3ad0c3aeab5730a32835a04","schema_version":"1.0","event_id":"sha256:0e3118742ffdaed1c6dad28a1c1435d1b40cbba9e3ad0c3aeab5730a32835a04"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YLRP7RP5JFXWUHKRHOYT4VUHFY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scalable Reinforcement Post-Training Beyond Static Human Prompts: Evolving Alignment via Asymmetric Self-Play","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","physics.data-an","stat.ML"],"primary_cat":"cs.CL","authors_text":"Qijun Tan, Quoc V. Le, Rishabh Agarwal, Rishabh Joshi, Sarmishta Velury, Tianqi Liu, Yuan Liu, Ziyu Ye","submitted_at":"2024-10-31T08:15:32Z","abstract_excerpt":"Current reinforcement learning (RL) frameworks for large language models (LLM) post-training typically assume a fixed prompt distribution, which is sub-optimal and bottlenecks scalability. Prior works have explored prompt evolving, but are often limited to the supervised fine-tuning stage, and prompts are sampled and evolved uniformly without signals. This empirical work presents a paradigm shift: Evolving Alignment via Asymmetric Self-Play (eva), that casts post-training as an infinite game with regret-based signals for 2 players: (i) a creator, who strategically samples and creates new infor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00062","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.00062/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:46:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d5GdQMlQfBT44PFyOIHFmQXHZ1I2V/ww6Hmmy92g+5rwfGxxly7m1CLMBesHVdNPOlwWImBEYIw6m7nNk6UkDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T22:57:35.046122Z"},"content_sha256":"0b82382ea57860559b8b251801588bc12debbeaf44bb9c0ac31a8554b8cc8fa5","schema_version":"1.0","event_id":"sha256:0b82382ea57860559b8b251801588bc12debbeaf44bb9c0ac31a8554b8cc8fa5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YLRP7RP5JFXWUHKRHOYT4VUHFY/bundle.json","state_url":"https://pith.science/pith/YLRP7RP5JFXWUHKRHOYT4VUHFY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YLRP7RP5JFXWUHKRHOYT4VUHFY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-19T22:57:35Z","links":{"resolver":"https://pith.science/pith/YLRP7RP5JFXWUHKRHOYT4VUHFY","bundle":"https://pith.science/pith/YLRP7RP5JFXWUHKRHOYT4VUHFY/bundle.json","state":"https://pith.science/pith/YLRP7RP5JFXWUHKRHOYT4VUHFY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YLRP7RP5JFXWUHKRHOYT4VUHFY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YLRP7RP5JFXWUHKRHOYT4VUHFY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e75bcf5a0e3f7296ed4e65d0492d03fd13b461d073410576f0a61f4ef4413ebb","cross_cats_sorted":["cs.AI","physics.data-an","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T08:15:32Z","title_canon_sha256":"a60a53197c8e4dd519e031d0f7c86ecb9eb231eb786399fc446830b1de64d037"},"schema_version":"1.0","source":{"id":"2411.00062","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.00062","created_at":"2026-07-05T10:46:58Z"},{"alias_kind":"arxiv_version","alias_value":"2411.00062v3","created_at":"2026-07-05T10:46:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00062","created_at":"2026-07-05T10:46:58Z"},{"alias_kind":"pith_short_12","alias_value":"YLRP7RP5JFXW","created_at":"2026-07-05T10:46:58Z"},{"alias_kind":"pith_short_16","alias_value":"YLRP7RP5JFXWUHKR","created_at":"2026-07-05T10:46:58Z"},{"alias_kind":"pith_short_8","alias_value":"YLRP7RP5","created_at":"2026-07-05T10:46:58Z"}],"graph_snapshots":[{"event_id":"sha256:0b82382ea57860559b8b251801588bc12debbeaf44bb9c0ac31a8554b8cc8fa5","target":"graph","created_at":"2026-07-05T10:46:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.00062/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current reinforcement learning (RL) frameworks for large language models (LLM) post-training typically assume a fixed prompt distribution, which is sub-optimal and bottlenecks scalability. Prior works have explored prompt evolving, but are often limited to the supervised fine-tuning stage, and prompts are sampled and evolved uniformly without signals. This empirical work presents a paradigm shift: Evolving Alignment via Asymmetric Self-Play (eva), that casts post-training as an infinite game with regret-based signals for 2 players: (i) a creator, who strategically samples and creates new infor","authors_text":"Qijun Tan, Quoc V. Le, Rishabh Agarwal, Rishabh Joshi, Sarmishta Velury, Tianqi Liu, Yuan Liu, Ziyu Ye","cross_cats":["cs.AI","physics.data-an","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T08:15:32Z","title":"Scalable Reinforcement Post-Training Beyond Static Human Prompts: Evolving Alignment via Asymmetric Self-Play"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00062","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0e3118742ffdaed1c6dad28a1c1435d1b40cbba9e3ad0c3aeab5730a32835a04","target":"record","created_at":"2026-07-05T10:46:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e75bcf5a0e3f7296ed4e65d0492d03fd13b461d073410576f0a61f4ef4413ebb","cross_cats_sorted":["cs.AI","physics.data-an","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T08:15:32Z","title_canon_sha256":"a60a53197c8e4dd519e031d0f7c86ecb9eb231eb786399fc446830b1de64d037"},"schema_version":"1.0","source":{"id":"2411.00062","kind":"arxiv","version":3}},"canonical_sha256":"c2e2ffc5fd496f6a1d513bb13e56872e3dc877509392a63e2bca047794e2aeb9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2e2ffc5fd496f6a1d513bb13e56872e3dc877509392a63e2bca047794e2aeb9","first_computed_at":"2026-07-05T10:46:58.120258Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:46:58.120258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zgchgZ+VOmzoiwDsvZ0ln8VCnXQq155trhE3Ok7tTnLhfAINmPzdZKy03dfJfcsC1xGIhhcF2qD5K0KjDm4JBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:46:58.120768Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.00062","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e3118742ffdaed1c6dad28a1c1435d1b40cbba9e3ad0c3aeab5730a32835a04","sha256:0b82382ea57860559b8b251801588bc12debbeaf44bb9c0ac31a8554b8cc8fa5"],"state_sha256":"f6694e63883bacb13c9bba4972317c8eb4e0512e79fc24084aba9e694a5adc53"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"buPoVUaheBuFv0Aqz9kVvoZ4DQeE7aMU+/jrI5yQMCfgZrYDTkDISlWbTtA0KSsSi1D5+gN8M0t1OOOLtrDPCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T22:57:35.051234Z","bundle_sha256":"fe355f8e3b3c5ff2d4a36bf3233d7554cd89e5700bf5945482b67db6d26616e4"}}