{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:W7J5BAKA7ZMBEENX4LM3KRP6IH","short_pith_number":"pith:W7J5BAKA","canonical_record":{"source":{"id":"2502.06533","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T14:56:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fbc7a6a6fd3c407d3362244298d538e1937265f14276285b99c8e10110c8d638","abstract_canon_sha256":"f6ab39ca04b893e16e46f21dbd82cda17cda4289b6e6692009f7eabdabe665f8"},"schema_version":"1.0"},"canonical_sha256":"b7d3d08140fe581211b7e2d9b545fe41c59d121481d24accc851ef8ffaaeb3d2","source":{"kind":"arxiv","id":"2502.06533","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06533","created_at":"2026-07-05T10:12:08Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06533v1","created_at":"2026-07-05T10:12:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06533","created_at":"2026-07-05T10:12:08Z"},{"alias_kind":"pith_short_12","alias_value":"W7J5BAKA7ZMB","created_at":"2026-07-05T10:12:08Z"},{"alias_kind":"pith_short_16","alias_value":"W7J5BAKA7ZMBEENX","created_at":"2026-07-05T10:12:08Z"},{"alias_kind":"pith_short_8","alias_value":"W7J5BAKA","created_at":"2026-07-05T10:12:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:W7J5BAKA7ZMBEENX4LM3KRP6IH","target":"record","payload":{"canonical_record":{"source":{"id":"2502.06533","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T14:56:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fbc7a6a6fd3c407d3362244298d538e1937265f14276285b99c8e10110c8d638","abstract_canon_sha256":"f6ab39ca04b893e16e46f21dbd82cda17cda4289b6e6692009f7eabdabe665f8"},"schema_version":"1.0"},"canonical_sha256":"b7d3d08140fe581211b7e2d9b545fe41c59d121481d24accc851ef8ffaaeb3d2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:08.117365Z","signature_b64":"1/deQA9qdoLvjAni+EscVerciGGnRs371PJgR+nkJ7ZqssV1S/OrSZZ5A1oxTOjSt1hkf5w2uzf7LnJrrZhtAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7d3d08140fe581211b7e2d9b545fe41c59d121481d24accc851ef8ffaaeb3d2","last_reissued_at":"2026-07-05T10:12:08.116924Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:08.116924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.06533","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":"2026-07-05T10:12:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fSa5SSVKLbP1/Q4g2lBWvadRcrp4nBS6eG/3BbK8IrTcoqVYRqEiHpCBBmqvhmo+hHaHU7h76c30xbycEvyJBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:00:06.216702Z"},"content_sha256":"ef585e91af522e3ab2f2338a5e63d59691b5daf2b1abf639f1f214facc7b9533","schema_version":"1.0","event_id":"sha256:ef585e91af522e3ab2f2338a5e63d59691b5daf2b1abf639f1f214facc7b9533"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:W7J5BAKA7ZMBEENX4LM3KRP6IH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jean Vassoyan, Nathana\\\"el Beau, Roman Plaud","submitted_at":"2025-02-10T14:56:25Z","abstract_excerpt":"The ability to achieve long-term goals is a key challenge in the current development of large language models (LLMs). To address this, pre-trained LLMs can be fine-tuned with reinforcement learning (RL) to explore solutions that optimize a given goal. However, exploration with LLMs is difficult, as a balance has to be struck between discovering new solutions and staying close enough to the pre-trained model, so as not to degrade basic capabilities. This is typically controlled with a Kullback-Leibler (KL) penalty. In this paper, we investigate the exploration dynamics of a small language model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06533","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/2502.06533/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":"2026-07-05T10:12:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ia4dOhxIXjO1u/VTaXfXzmR/Ndd+CpYbemF2nddoDWTPXxOZKHbt1pLB0nmPMUwqp7urIq0ZPCpZLr731bSFBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:00:06.217204Z"},"content_sha256":"8d30254ac44fa470def82dafc87a28f2b6a0826d6660231bf002f1a925ecc28b","schema_version":"1.0","event_id":"sha256:8d30254ac44fa470def82dafc87a28f2b6a0826d6660231bf002f1a925ecc28b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W7J5BAKA7ZMBEENX4LM3KRP6IH/bundle.json","state_url":"https://pith.science/pith/W7J5BAKA7ZMBEENX4LM3KRP6IH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W7J5BAKA7ZMBEENX4LM3KRP6IH/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":"2026-08-08T06:00:06Z","links":{"resolver":"https://pith.science/pith/W7J5BAKA7ZMBEENX4LM3KRP6IH","bundle":"https://pith.science/pith/W7J5BAKA7ZMBEENX4LM3KRP6IH/bundle.json","state":"https://pith.science/pith/W7J5BAKA7ZMBEENX4LM3KRP6IH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W7J5BAKA7ZMBEENX4LM3KRP6IH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:W7J5BAKA7ZMBEENX4LM3KRP6IH","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":"f6ab39ca04b893e16e46f21dbd82cda17cda4289b6e6692009f7eabdabe665f8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T14:56:25Z","title_canon_sha256":"fbc7a6a6fd3c407d3362244298d538e1937265f14276285b99c8e10110c8d638"},"schema_version":"1.0","source":{"id":"2502.06533","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06533","created_at":"2026-07-05T10:12:08Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06533v1","created_at":"2026-07-05T10:12:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06533","created_at":"2026-07-05T10:12:08Z"},{"alias_kind":"pith_short_12","alias_value":"W7J5BAKA7ZMB","created_at":"2026-07-05T10:12:08Z"},{"alias_kind":"pith_short_16","alias_value":"W7J5BAKA7ZMBEENX","created_at":"2026-07-05T10:12:08Z"},{"alias_kind":"pith_short_8","alias_value":"W7J5BAKA","created_at":"2026-07-05T10:12:08Z"}],"graph_snapshots":[{"event_id":"sha256:8d30254ac44fa470def82dafc87a28f2b6a0826d6660231bf002f1a925ecc28b","target":"graph","created_at":"2026-07-05T10:12:08Z","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/2502.06533/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ability to achieve long-term goals is a key challenge in the current development of large language models (LLMs). To address this, pre-trained LLMs can be fine-tuned with reinforcement learning (RL) to explore solutions that optimize a given goal. However, exploration with LLMs is difficult, as a balance has to be struck between discovering new solutions and staying close enough to the pre-trained model, so as not to degrade basic capabilities. This is typically controlled with a Kullback-Leibler (KL) penalty. In this paper, we investigate the exploration dynamics of a small language model","authors_text":"Jean Vassoyan, Nathana\\\"el Beau, Roman Plaud","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T14:56:25Z","title":"Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06533","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:ef585e91af522e3ab2f2338a5e63d59691b5daf2b1abf639f1f214facc7b9533","target":"record","created_at":"2026-07-05T10:12:08Z","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":"f6ab39ca04b893e16e46f21dbd82cda17cda4289b6e6692009f7eabdabe665f8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T14:56:25Z","title_canon_sha256":"fbc7a6a6fd3c407d3362244298d538e1937265f14276285b99c8e10110c8d638"},"schema_version":"1.0","source":{"id":"2502.06533","kind":"arxiv","version":1}},"canonical_sha256":"b7d3d08140fe581211b7e2d9b545fe41c59d121481d24accc851ef8ffaaeb3d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7d3d08140fe581211b7e2d9b545fe41c59d121481d24accc851ef8ffaaeb3d2","first_computed_at":"2026-07-05T10:12:08.116924Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:08.116924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1/deQA9qdoLvjAni+EscVerciGGnRs371PJgR+nkJ7ZqssV1S/OrSZZ5A1oxTOjSt1hkf5w2uzf7LnJrrZhtAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:08.117365Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.06533","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef585e91af522e3ab2f2338a5e63d59691b5daf2b1abf639f1f214facc7b9533","sha256:8d30254ac44fa470def82dafc87a28f2b6a0826d6660231bf002f1a925ecc28b"],"state_sha256":"baf8c6e96042bb00609fdcdd19f15d599316868e9dcac05d121001f19e3ce2ca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iyxw7VYTnZAhtyHT/gtj9nLgbPu2C8R7mlPhnAh7WySOljCznSPfv1GhNQtXB+p54scN4ADldSeAaWXqj3cMCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T06:00:06.220476Z","bundle_sha256":"dd1d81190ba6876dcff6fa3f85d06022ef9ec55e3e2a01e89be0a6bee8e492a6"}}