{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ALKGED3GELRH62R4BWYPR5M2WZ","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":"dfa55a55757c8a1757a0b0700205408cc0df1ed566f735a94b84f9f40a7f1475","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-04T05:38:44Z","title_canon_sha256":"dfa58ca2aad5d9cc6ae05358d18a617ce2eca118086436aca132d388a0bc2e06"},"schema_version":"1.0","source":{"id":"2404.04291","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.04291","created_at":"2026-07-05T08:05:14Z"},{"alias_kind":"arxiv_version","alias_value":"2404.04291v1","created_at":"2026-07-05T08:05:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04291","created_at":"2026-07-05T08:05:14Z"},{"alias_kind":"pith_short_12","alias_value":"ALKGED3GELRH","created_at":"2026-07-05T08:05:14Z"},{"alias_kind":"pith_short_16","alias_value":"ALKGED3GELRH62R4","created_at":"2026-07-05T08:05:14Z"},{"alias_kind":"pith_short_8","alias_value":"ALKGED3G","created_at":"2026-07-05T08:05:14Z"}],"graph_snapshots":[{"event_id":"sha256:7e2bd64486ed787f72626ed3182a52018ad09d6badb2786b7a1c58f42dd48f74","target":"graph","created_at":"2026-07-05T08:05:14Z","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/2404.04291/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper explores the effects of various forms of regularization in the context of language model alignment via self-play. While both reinforcement learning from human feedback (RLHF) and direct preference optimization (DPO) require to collect costly human-annotated pairwise preferences, the self-play fine-tuning (SPIN) approach replaces the rejected answers by data generated from the previous iterate. However, the SPIN method presents a performance instability issue in the learning phase, which can be mitigated by playing against a mixture of the two previous iterates. In the same vein, we ","authors_text":"Abdalgader Abubaker, Mastane Achab, Mohamed El Amine Seddik, Reda Alami, Salem Lahlou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-04T05:38:44Z","title":"Investigating Regularization of Self-Play Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04291","kind":"arxiv","version":1},"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":"sha256:81b9063e3bb10ef888f3c38b73aec67cb9fa7137444bc377bd212a09e361e21c","target":"record","created_at":"2026-07-05T08:05:14Z","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":"dfa55a55757c8a1757a0b0700205408cc0df1ed566f735a94b84f9f40a7f1475","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-04T05:38:44Z","title_canon_sha256":"dfa58ca2aad5d9cc6ae05358d18a617ce2eca118086436aca132d388a0bc2e06"},"schema_version":"1.0","source":{"id":"2404.04291","kind":"arxiv","version":1}},"canonical_sha256":"02d4620f6622e27f6a3c0db0f8f59ab6750aceb75fd8de4e174434e04cada5d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"02d4620f6622e27f6a3c0db0f8f59ab6750aceb75fd8de4e174434e04cada5d6","first_computed_at":"2026-07-05T08:05:14.503594Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:05:14.503594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xrNkGKev4Yn1iA4fpajQpVD4SJo6TeeYNxvkKRvXHUjE1pbdD8f8opjTfQVUD3QXQGrvO3U2Wv5SxYn6y8E2Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:05:14.504046Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.04291","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81b9063e3bb10ef888f3c38b73aec67cb9fa7137444bc377bd212a09e361e21c","sha256:7e2bd64486ed787f72626ed3182a52018ad09d6badb2786b7a1c58f42dd48f74"],"state_sha256":"8aefd37fd2488fc3d4e044e861b2f8ac3e9b4c5f6f3a0ca34e0889db998993a8"}