{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ALKGED3GELRH62R4BWYPR5M2WZ","short_pith_number":"pith:ALKGED3G","canonical_record":{"source":{"id":"2404.04291","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-04T05:38:44Z","cross_cats_sorted":[],"title_canon_sha256":"dfa58ca2aad5d9cc6ae05358d18a617ce2eca118086436aca132d388a0bc2e06","abstract_canon_sha256":"dfa55a55757c8a1757a0b0700205408cc0df1ed566f735a94b84f9f40a7f1475"},"schema_version":"1.0"},"canonical_sha256":"02d4620f6622e27f6a3c0db0f8f59ab6750aceb75fd8de4e174434e04cada5d6","source":{"kind":"arxiv","id":"2404.04291","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ALKGED3GELRH62R4BWYPR5M2WZ","target":"record","payload":{"canonical_record":{"source":{"id":"2404.04291","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-04T05:38:44Z","cross_cats_sorted":[],"title_canon_sha256":"dfa58ca2aad5d9cc6ae05358d18a617ce2eca118086436aca132d388a0bc2e06","abstract_canon_sha256":"dfa55a55757c8a1757a0b0700205408cc0df1ed566f735a94b84f9f40a7f1475"},"schema_version":"1.0"},"canonical_sha256":"02d4620f6622e27f6a3c0db0f8f59ab6750aceb75fd8de4e174434e04cada5d6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:14.504046Z","signature_b64":"xrNkGKev4Yn1iA4fpajQpVD4SJo6TeeYNxvkKRvXHUjE1pbdD8f8opjTfQVUD3QXQGrvO3U2Wv5SxYn6y8E2Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02d4620f6622e27f6a3c0db0f8f59ab6750aceb75fd8de4e174434e04cada5d6","last_reissued_at":"2026-07-05T08:05:14.503594Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:14.503594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.04291","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:05:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I2NMyTgGauMoAPbb0ZCzT+18BHmVOE0szp4Ur5eYOhtdvSgR2TWzE2UJtG51zrbon/HsGnELUlyCO1qCVr42Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:20:54.898404Z"},"content_sha256":"81b9063e3bb10ef888f3c38b73aec67cb9fa7137444bc377bd212a09e361e21c","schema_version":"1.0","event_id":"sha256:81b9063e3bb10ef888f3c38b73aec67cb9fa7137444bc377bd212a09e361e21c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ALKGED3GELRH62R4BWYPR5M2WZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Investigating Regularization of Self-Play Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Abdalgader Abubaker, Mastane Achab, Mohamed El Amine Seddik, Reda Alami, Salem Lahlou","submitted_at":"2024-04-04T05:38:44Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04291","kind":"arxiv","version":1},"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/2404.04291/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":"2026-07-05T08:05:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5jAoUnpsRXxiKgvW/Gyf6gs2zHKYyTIbvgydjvWTQfRBHxs0u5jBxY8iv5P1SLW7e5FXC4KvJxTBocDQrGSXAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:20:54.898794Z"},"content_sha256":"7e2bd64486ed787f72626ed3182a52018ad09d6badb2786b7a1c58f42dd48f74","schema_version":"1.0","event_id":"sha256:7e2bd64486ed787f72626ed3182a52018ad09d6badb2786b7a1c58f42dd48f74"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ALKGED3GELRH62R4BWYPR5M2WZ/bundle.json","state_url":"https://pith.science/pith/ALKGED3GELRH62R4BWYPR5M2WZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ALKGED3GELRH62R4BWYPR5M2WZ/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":"2026-07-09T02:20:54Z","links":{"resolver":"https://pith.science/pith/ALKGED3GELRH62R4BWYPR5M2WZ","bundle":"https://pith.science/pith/ALKGED3GELRH62R4BWYPR5M2WZ/bundle.json","state":"https://pith.science/pith/ALKGED3GELRH62R4BWYPR5M2WZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ALKGED3GELRH62R4BWYPR5M2WZ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gHSkqxiY1mzIoJLHTYzLEVk1Rjyat4o/QIgtvjlVG7VHyQRk46E0XlwFL9MXzNVedzlQDaDHGLWc4RjZfccpDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T02:20:54.900835Z","bundle_sha256":"0e0903c40dfd245360c5f2bb8e9d66256fe15f250abc78bf31b35549718d3d9f"}}