{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2R3J4VMHDW5LF5EZYSBW4HN75B","short_pith_number":"pith:2R3J4VMH","canonical_record":{"source":{"id":"2410.16714","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-22T05:51:34Z","cross_cats_sorted":[],"title_canon_sha256":"e4ab27bc63c95a05f209769637a66a3c3a8981725f911b7ff538144f2d1a6972","abstract_canon_sha256":"f60023bbcddccb37c05013e6e138f20b15103080280b1afc1f2f80aa9d1dcbae"},"schema_version":"1.0"},"canonical_sha256":"d4769e55871dbab2f499c4836e1dbfe87aff2a9b35295e6ba00d1f737695ac1a","source":{"kind":"arxiv","id":"2410.16714","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16714","created_at":"2026-07-05T10:51:27Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16714v3","created_at":"2026-07-05T10:51:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16714","created_at":"2026-07-05T10:51:27Z"},{"alias_kind":"pith_short_12","alias_value":"2R3J4VMHDW5L","created_at":"2026-07-05T10:51:27Z"},{"alias_kind":"pith_short_16","alias_value":"2R3J4VMHDW5LF5EZ","created_at":"2026-07-05T10:51:27Z"},{"alias_kind":"pith_short_8","alias_value":"2R3J4VMH","created_at":"2026-07-05T10:51:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2R3J4VMHDW5LF5EZYSBW4HN75B","target":"record","payload":{"canonical_record":{"source":{"id":"2410.16714","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-22T05:51:34Z","cross_cats_sorted":[],"title_canon_sha256":"e4ab27bc63c95a05f209769637a66a3c3a8981725f911b7ff538144f2d1a6972","abstract_canon_sha256":"f60023bbcddccb37c05013e6e138f20b15103080280b1afc1f2f80aa9d1dcbae"},"schema_version":"1.0"},"canonical_sha256":"d4769e55871dbab2f499c4836e1dbfe87aff2a9b35295e6ba00d1f737695ac1a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:27.164036Z","signature_b64":"cIwRm+uv7RUkSUPqKTckVwYs8XuzhGLpzRwxn55HhVCGAH7PFd880vBlGVtG6AXYhB7+6wGbp6XIQH30dpKzDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4769e55871dbab2f499c4836e1dbfe87aff2a9b35295e6ba00d1f737695ac1a","last_reissued_at":"2026-07-05T10:51:27.163552Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:27.163552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.16714","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":"2026-07-05T10:51:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xhOnahpthY/cujYSaXmumHa8dqxp3gkD5YlisNubEV+GSiGT1HNSUO1S9rzF0VZvlJo33LxmvLodlMJ1txTAAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:16:57.085992Z"},"content_sha256":"21e29ec9a5e0ebe52a3375ff3f6be15fdd4415ef62194cb098a95822a83c3fc7","schema_version":"1.0","event_id":"sha256:21e29ec9a5e0ebe52a3375ff3f6be15fdd4415ef62194cb098a95822a83c3fc7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2R3J4VMHDW5LF5EZYSBW4HN75B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Magnetic Preference Optimization: Achieving Last-iterate Convergence for Language Model Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengdong Ma, Jiancong Xiao, Jing Huo, Linjian Meng, Mingzhi Wang, Qizhi Chen, Weijie J. Su, Yang Han, Yaodong Yang, Zhaowei Zhang","submitted_at":"2024-10-22T05:51:34Z","abstract_excerpt":"Self-play methods have demonstrated remarkable success in enhancing model capabilities across various domains. In the context of Reinforcement Learning from Human Feedback (RLHF), self-play not only boosts Large Language Model (LLM) performance but also overcomes the limitations of traditional Bradley-Terry (BT) model assumptions by finding the Nash equilibrium (NE) of a preference-based, two-player constant-sum game. However, existing methods either guarantee only average-iterate convergence, incurring high storage and inference costs, or converge to the NE of a regularized game, failing to a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16714","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/2410.16714/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":"2026-07-05T10:51:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8nmOcwlpMdMN9fi5MX5J/fdHiQVRuq1Q7u1UaR4icl7SHEIyOxtjknFI1xZdkid8Ma246rHFnknza1EDYEqkAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:16:57.086637Z"},"content_sha256":"d8f74935275b2bba383d061267b8a2bb65b06926243ef5df218e98b6e28b9a77","schema_version":"1.0","event_id":"sha256:d8f74935275b2bba383d061267b8a2bb65b06926243ef5df218e98b6e28b9a77"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2R3J4VMHDW5LF5EZYSBW4HN75B/bundle.json","state_url":"https://pith.science/pith/2R3J4VMHDW5LF5EZYSBW4HN75B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2R3J4VMHDW5LF5EZYSBW4HN75B/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":"2026-08-04T04:16:57Z","links":{"resolver":"https://pith.science/pith/2R3J4VMHDW5LF5EZYSBW4HN75B","bundle":"https://pith.science/pith/2R3J4VMHDW5LF5EZYSBW4HN75B/bundle.json","state":"https://pith.science/pith/2R3J4VMHDW5LF5EZYSBW4HN75B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2R3J4VMHDW5LF5EZYSBW4HN75B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2R3J4VMHDW5LF5EZYSBW4HN75B","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":"f60023bbcddccb37c05013e6e138f20b15103080280b1afc1f2f80aa9d1dcbae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-22T05:51:34Z","title_canon_sha256":"e4ab27bc63c95a05f209769637a66a3c3a8981725f911b7ff538144f2d1a6972"},"schema_version":"1.0","source":{"id":"2410.16714","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16714","created_at":"2026-07-05T10:51:27Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16714v3","created_at":"2026-07-05T10:51:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16714","created_at":"2026-07-05T10:51:27Z"},{"alias_kind":"pith_short_12","alias_value":"2R3J4VMHDW5L","created_at":"2026-07-05T10:51:27Z"},{"alias_kind":"pith_short_16","alias_value":"2R3J4VMHDW5LF5EZ","created_at":"2026-07-05T10:51:27Z"},{"alias_kind":"pith_short_8","alias_value":"2R3J4VMH","created_at":"2026-07-05T10:51:27Z"}],"graph_snapshots":[{"event_id":"sha256:d8f74935275b2bba383d061267b8a2bb65b06926243ef5df218e98b6e28b9a77","target":"graph","created_at":"2026-07-05T10:51:27Z","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/2410.16714/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-play methods have demonstrated remarkable success in enhancing model capabilities across various domains. In the context of Reinforcement Learning from Human Feedback (RLHF), self-play not only boosts Large Language Model (LLM) performance but also overcomes the limitations of traditional Bradley-Terry (BT) model assumptions by finding the Nash equilibrium (NE) of a preference-based, two-player constant-sum game. However, existing methods either guarantee only average-iterate convergence, incurring high storage and inference costs, or converge to the NE of a regularized game, failing to a","authors_text":"Chengdong Ma, Jiancong Xiao, Jing Huo, Linjian Meng, Mingzhi Wang, Qizhi Chen, Weijie J. Su, Yang Han, Yaodong Yang, Zhaowei Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-22T05:51:34Z","title":"Magnetic Preference Optimization: Achieving Last-iterate Convergence for Language Model Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16714","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":"sha256:21e29ec9a5e0ebe52a3375ff3f6be15fdd4415ef62194cb098a95822a83c3fc7","target":"record","created_at":"2026-07-05T10:51:27Z","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":"f60023bbcddccb37c05013e6e138f20b15103080280b1afc1f2f80aa9d1dcbae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-22T05:51:34Z","title_canon_sha256":"e4ab27bc63c95a05f209769637a66a3c3a8981725f911b7ff538144f2d1a6972"},"schema_version":"1.0","source":{"id":"2410.16714","kind":"arxiv","version":3}},"canonical_sha256":"d4769e55871dbab2f499c4836e1dbfe87aff2a9b35295e6ba00d1f737695ac1a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d4769e55871dbab2f499c4836e1dbfe87aff2a9b35295e6ba00d1f737695ac1a","first_computed_at":"2026-07-05T10:51:27.163552Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:27.163552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cIwRm+uv7RUkSUPqKTckVwYs8XuzhGLpzRwxn55HhVCGAH7PFd880vBlGVtG6AXYhB7+6wGbp6XIQH30dpKzDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:27.164036Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.16714","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21e29ec9a5e0ebe52a3375ff3f6be15fdd4415ef62194cb098a95822a83c3fc7","sha256:d8f74935275b2bba383d061267b8a2bb65b06926243ef5df218e98b6e28b9a77"],"state_sha256":"475c672142188b775ac5cbc9185379858b20a55fcd9c1800a69840daacbe3246"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FYMmYkryN0e9qdRRBSrlTK1eNDfLBr2q+IKJgF/ZuFlnIkXqoLjBZva0gSByIcALIPXWjgPBDlhSUfN5RXn3BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T04:16:57.091206Z","bundle_sha256":"8e6d8348bf77289fce09e010ad78dc8ebbd7551fd50d13bb46871f0d68f088e0"}}