{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SO4VX2BG5HVLKWUQYK6RYAE6BY","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":"98c352dfcdf8386948fca0ff7a9a10f44fe6cc0544d07a6e70c2f6f2fcd70865","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-26T17:25:49Z","title_canon_sha256":"3455f0f4217bb737f3663ed1c5ab44d5a0812b7a2d48babf48d4523fe5f24973"},"schema_version":"1.0","source":{"id":"2506.21495","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21495","created_at":"2026-07-05T11:27:46Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21495v1","created_at":"2026-07-05T11:27:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21495","created_at":"2026-07-05T11:27:46Z"},{"alias_kind":"pith_short_12","alias_value":"SO4VX2BG5HVL","created_at":"2026-07-05T11:27:46Z"},{"alias_kind":"pith_short_16","alias_value":"SO4VX2BG5HVLKWUQ","created_at":"2026-07-05T11:27:46Z"},{"alias_kind":"pith_short_8","alias_value":"SO4VX2BG","created_at":"2026-07-05T11:27:46Z"}],"graph_snapshots":[{"event_id":"sha256:c1df555cc8ec1a88bb10a8223e0647060ab18c42818ebca9d6203c6c042e80e7","target":"graph","created_at":"2026-07-05T11:27:46Z","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/2506.21495/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate the effectiveness of reinforcement learning methods for finetuning large language models when transitioning from offline to semi-online to fully online regimes for both verifiable and non-verifiable tasks. Our experiments cover training on verifiable math as well as non-verifiable instruction following with a set of benchmark evaluations for both. Across these settings, we extensively compare online and semi-online Direct Preference Optimization and Group Reward Policy Optimization objectives, and surprisingly find similar performance and convergence between these variants, whic","authors_text":"Angelica Chen, Ilia Kulikov, Jack Lanchantin, Janice Lan, Jason E Weston, Jing Xu, Ping Yu, Sainbayar Sukhbaatar, Swarnadeep Saha, Tianlu Wang, Weizhe Yuan, Xian Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-26T17:25:49Z","title":"Bridging Offline and Online Reinforcement Learning for LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21495","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":"sha256:971e4f418b405db85c8a01a4478a0493b6e2579a36873683905b36987e6ef985","target":"record","created_at":"2026-07-05T11:27:46Z","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":"98c352dfcdf8386948fca0ff7a9a10f44fe6cc0544d07a6e70c2f6f2fcd70865","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-26T17:25:49Z","title_canon_sha256":"3455f0f4217bb737f3663ed1c5ab44d5a0812b7a2d48babf48d4523fe5f24973"},"schema_version":"1.0","source":{"id":"2506.21495","kind":"arxiv","version":1}},"canonical_sha256":"93b95be826e9eab55a90c2bd1c009e0e3a3f6c589ad1fd17792e0e2f54cd3637","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93b95be826e9eab55a90c2bd1c009e0e3a3f6c589ad1fd17792e0e2f54cd3637","first_computed_at":"2026-07-05T11:27:46.924461Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:46.924461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xHolkQpIGY93P5zljpHIWeIlJS9Cmnq3CEf1Qqw/eAT5NbUdzGNLvHoIHHjlP20FG73DAypaISb+A8VygknqBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:46.924920Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.21495","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:971e4f418b405db85c8a01a4478a0493b6e2579a36873683905b36987e6ef985","sha256:c1df555cc8ec1a88bb10a8223e0647060ab18c42818ebca9d6203c6c042e80e7"],"state_sha256":"e554214b43bc80e65ea97e4c93e478b0045680733851e27226eea5b15ac3e942"}