{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MR6TTSE64MCEPVSQ5JGGFXXQIM","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":"1156f7e448a746f6fffe44615fdef48a3f0aa83131175d4e37b198ded790bc71","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T10:12:11Z","title_canon_sha256":"3699f4342aaaee7615122fe223cfbdcdd3697eab7c8ea293a44986899e52180d"},"schema_version":"1.0","source":{"id":"2505.11081","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11081","created_at":"2026-07-05T11:04:10Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11081v1","created_at":"2026-07-05T11:04:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11081","created_at":"2026-07-05T11:04:10Z"},{"alias_kind":"pith_short_12","alias_value":"MR6TTSE64MCE","created_at":"2026-07-05T11:04:10Z"},{"alias_kind":"pith_short_16","alias_value":"MR6TTSE64MCEPVSQ","created_at":"2026-07-05T11:04:10Z"},{"alias_kind":"pith_short_8","alias_value":"MR6TTSE6","created_at":"2026-07-05T11:04:10Z"}],"graph_snapshots":[{"event_id":"sha256:3790080cf7327296ca40949915ae858263755880b332f9719c79421afc97e208","target":"graph","created_at":"2026-07-05T11:04:10Z","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/2505.11081/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The fine-tuning of pre-trained large language models (LLMs) using reinforcement learning (RL) is generally formulated as direct policy optimization. This approach was naturally favored as it efficiently improves a pretrained LLM, seen as an initial policy. Another RL paradigm, Q-learning methods, has received far less attention in the LLM community while demonstrating major success in various non-LLM RL tasks. In particular, Q-learning effectiveness comes from its sample efficiency and ability to learn offline, which is particularly valuable given the high computational cost of sampling with L","authors_text":"Eugene Tarassov, Florian Strub, Irem Ergun, Matthieu Geist, Nathan Grinsztajn, Olivier Pietquin, Omar D. Domingues, Pierre Clavier, Pierre H. Richemond, Raphael Avalos, Yannis Flet-Berliac","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T10:12:11Z","title":"ShiQ: Bringing back Bellman to LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11081","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":"sha256:18f853e14d106f45d42e6476790288a007ab7c85393fe94ddc4d5dfdd632a7b1","target":"record","created_at":"2026-07-05T11:04:10Z","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":"1156f7e448a746f6fffe44615fdef48a3f0aa83131175d4e37b198ded790bc71","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T10:12:11Z","title_canon_sha256":"3699f4342aaaee7615122fe223cfbdcdd3697eab7c8ea293a44986899e52180d"},"schema_version":"1.0","source":{"id":"2505.11081","kind":"arxiv","version":1}},"canonical_sha256":"647d39c89ee30447d650ea4c62def0433db3dcf64edb2b7b54cd3821bf7794d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"647d39c89ee30447d650ea4c62def0433db3dcf64edb2b7b54cd3821bf7794d8","first_computed_at":"2026-07-05T11:04:10.472296Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:10.472296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bo1i0G0da6wiBjskVQWCfogNdbWStNfFO1J5b7pe5TlBmhVU/mZt4bzLzjE1Axef+1gW1bnAEJ1XFufP5Z2NCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:10.472840Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11081","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:18f853e14d106f45d42e6476790288a007ab7c85393fe94ddc4d5dfdd632a7b1","sha256:3790080cf7327296ca40949915ae858263755880b332f9719c79421afc97e208"],"state_sha256":"3dece986aafe984980c30c0e25fc4bcfa874e2db14c30e7787651fafb109775c"}