{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LC5NIJSY7Q7FSUOUYNFPE6MEPY","short_pith_number":"pith:LC5NIJSY","canonical_record":{"source":{"id":"2405.08448","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-14T09:12:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c4cfb6a0633ea9911b3b27204728cab702a3e6850a8d8a4c99910b0b4ee43a0d","abstract_canon_sha256":"627c3366a71ab4a95e9295c2e039ebd9c4c2f4e068c4a52ef9a006d799e7ac0f"},"schema_version":"1.0"},"canonical_sha256":"58bad42658fc3e5951d4c34af279847e06c1700b3dc089e2f2516757497c46d5","source":{"kind":"arxiv","id":"2405.08448","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.08448","created_at":"2026-07-05T08:19:00Z"},{"alias_kind":"arxiv_version","alias_value":"2405.08448v1","created_at":"2026-07-05T08:19:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.08448","created_at":"2026-07-05T08:19:00Z"},{"alias_kind":"pith_short_12","alias_value":"LC5NIJSY7Q7F","created_at":"2026-07-05T08:19:00Z"},{"alias_kind":"pith_short_16","alias_value":"LC5NIJSY7Q7FSUOU","created_at":"2026-07-05T08:19:00Z"},{"alias_kind":"pith_short_8","alias_value":"LC5NIJSY","created_at":"2026-07-05T08:19:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LC5NIJSY7Q7FSUOUYNFPE6MEPY","target":"record","payload":{"canonical_record":{"source":{"id":"2405.08448","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-14T09:12:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c4cfb6a0633ea9911b3b27204728cab702a3e6850a8d8a4c99910b0b4ee43a0d","abstract_canon_sha256":"627c3366a71ab4a95e9295c2e039ebd9c4c2f4e068c4a52ef9a006d799e7ac0f"},"schema_version":"1.0"},"canonical_sha256":"58bad42658fc3e5951d4c34af279847e06c1700b3dc089e2f2516757497c46d5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:00.562614Z","signature_b64":"qDQ8L4WklT2jveY4yGetHbBAL21lN2VjeaGhQLjB96N09xcELRMDJrrp6UejyvjCd+vhBoWatraBiGathDPUDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58bad42658fc3e5951d4c34af279847e06c1700b3dc089e2f2516757497c46d5","last_reissued_at":"2026-07-05T08:19:00.562112Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:00.562112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.08448","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":"2026-07-05T08:19:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yYrVNgoEYZn1lUGRfEsZrPVDfDx05+dAxHx/BHlXxspUDjU7/wLMMPrjzGr61u1lTpFBy6XhDdLeC2QnW1kLCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:18:20.547534Z"},"content_sha256":"8eed788283226a3e6cbdc6c9d46f2705ad70ddf9a0987743880bfe6296bb4a1f","schema_version":"1.0","event_id":"sha256:8eed788283226a3e6cbdc6c9d46f2705ad70ddf9a0987743880bfe6296bb4a1f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LC5NIJSY7Q7FSUOUYNFPE6MEPY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding the performance gap between online and offline alignment algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bernardo \\'Avila Pires, Daniele Calandriello, Daniel Zhaohan Guo, Eugene Tarassov, Michal Valko, R\\'emi Munos, Will Dabney, Yong Cheng, Yuan Cao, Yunhao Tang, Zeyu Zheng","submitted_at":"2024-05-14T09:12:30Z","abstract_excerpt":"Reinforcement learning from human feedback (RLHF) is the canonical framework for large language model alignment. However, rising popularity in offline alignment algorithms challenge the need for on-policy sampling in RLHF. Within the context of reward over-optimization, we start with an opening set of experiments that demonstrate the clear advantage of online methods over offline methods. This prompts us to investigate the causes to the performance discrepancy through a series of carefully designed experimental ablations. We show empirically that hypotheses such as offline data coverage and da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.08448","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/2405.08448/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":"2026-07-05T08:19:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XLlGuiHWBY/nSxlCvpZF86pJHbslOFR37FX8e1mxBMJkr+EIp0s+qaV5QmSD9xNt9rzwWoQDe9yre1ufGPxBCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:18:20.547912Z"},"content_sha256":"77f7aa1986aa7c6c372c28c7357c41cdba7e7e40498717e47c3aad06ed8a847c","schema_version":"1.0","event_id":"sha256:77f7aa1986aa7c6c372c28c7357c41cdba7e7e40498717e47c3aad06ed8a847c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LC5NIJSY7Q7FSUOUYNFPE6MEPY/bundle.json","state_url":"https://pith.science/pith/LC5NIJSY7Q7FSUOUYNFPE6MEPY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LC5NIJSY7Q7FSUOUYNFPE6MEPY/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":"2026-07-07T09:18:20Z","links":{"resolver":"https://pith.science/pith/LC5NIJSY7Q7FSUOUYNFPE6MEPY","bundle":"https://pith.science/pith/LC5NIJSY7Q7FSUOUYNFPE6MEPY/bundle.json","state":"https://pith.science/pith/LC5NIJSY7Q7FSUOUYNFPE6MEPY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LC5NIJSY7Q7FSUOUYNFPE6MEPY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LC5NIJSY7Q7FSUOUYNFPE6MEPY","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":"627c3366a71ab4a95e9295c2e039ebd9c4c2f4e068c4a52ef9a006d799e7ac0f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-14T09:12:30Z","title_canon_sha256":"c4cfb6a0633ea9911b3b27204728cab702a3e6850a8d8a4c99910b0b4ee43a0d"},"schema_version":"1.0","source":{"id":"2405.08448","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.08448","created_at":"2026-07-05T08:19:00Z"},{"alias_kind":"arxiv_version","alias_value":"2405.08448v1","created_at":"2026-07-05T08:19:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.08448","created_at":"2026-07-05T08:19:00Z"},{"alias_kind":"pith_short_12","alias_value":"LC5NIJSY7Q7F","created_at":"2026-07-05T08:19:00Z"},{"alias_kind":"pith_short_16","alias_value":"LC5NIJSY7Q7FSUOU","created_at":"2026-07-05T08:19:00Z"},{"alias_kind":"pith_short_8","alias_value":"LC5NIJSY","created_at":"2026-07-05T08:19:00Z"}],"graph_snapshots":[{"event_id":"sha256:77f7aa1986aa7c6c372c28c7357c41cdba7e7e40498717e47c3aad06ed8a847c","target":"graph","created_at":"2026-07-05T08:19:00Z","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/2405.08448/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning from human feedback (RLHF) is the canonical framework for large language model alignment. However, rising popularity in offline alignment algorithms challenge the need for on-policy sampling in RLHF. Within the context of reward over-optimization, we start with an opening set of experiments that demonstrate the clear advantage of online methods over offline methods. This prompts us to investigate the causes to the performance discrepancy through a series of carefully designed experimental ablations. We show empirically that hypotheses such as offline data coverage and da","authors_text":"Bernardo \\'Avila Pires, Daniele Calandriello, Daniel Zhaohan Guo, Eugene Tarassov, Michal Valko, R\\'emi Munos, Will Dabney, Yong Cheng, Yuan Cao, Yunhao Tang, Zeyu Zheng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-14T09:12:30Z","title":"Understanding the performance gap between online and offline alignment algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.08448","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":"sha256:8eed788283226a3e6cbdc6c9d46f2705ad70ddf9a0987743880bfe6296bb4a1f","target":"record","created_at":"2026-07-05T08:19:00Z","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":"627c3366a71ab4a95e9295c2e039ebd9c4c2f4e068c4a52ef9a006d799e7ac0f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-14T09:12:30Z","title_canon_sha256":"c4cfb6a0633ea9911b3b27204728cab702a3e6850a8d8a4c99910b0b4ee43a0d"},"schema_version":"1.0","source":{"id":"2405.08448","kind":"arxiv","version":1}},"canonical_sha256":"58bad42658fc3e5951d4c34af279847e06c1700b3dc089e2f2516757497c46d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58bad42658fc3e5951d4c34af279847e06c1700b3dc089e2f2516757497c46d5","first_computed_at":"2026-07-05T08:19:00.562112Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:19:00.562112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qDQ8L4WklT2jveY4yGetHbBAL21lN2VjeaGhQLjB96N09xcELRMDJrrp6UejyvjCd+vhBoWatraBiGathDPUDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:19:00.562614Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.08448","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8eed788283226a3e6cbdc6c9d46f2705ad70ddf9a0987743880bfe6296bb4a1f","sha256:77f7aa1986aa7c6c372c28c7357c41cdba7e7e40498717e47c3aad06ed8a847c"],"state_sha256":"23b9ec9b38ebc5a269066f7d1a14f1155452f7e30f77d52f1f9b92de8690931e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rUusamY5rdDYe9RqX8zawN6jd+jXveamhl+sRV+sL4QPK8aH3sIMRjsB4dNpjkSQwi5gqOQj6j3luYHAI2DQDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T09:18:20.551976Z","bundle_sha256":"559b39cd0353dd050cdb53a1b8770bfa88206fbbdfa60596c389e7c1e8273924"}}