{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2L4FAKGGEOR2HTPLICLDDAS6WF","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":"5b2e27ddc7ea6a265d790907172ae82d31964b8e26bd29d1326fcf4c253266bf","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-13T20:52:13Z","title_canon_sha256":"aff3059869cd36b4e19efb4f131b57952fd244b5ba2881d3e756d11de12b1848"},"schema_version":"1.0","source":{"id":"2408.07199","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.07199","created_at":"2026-05-20T09:35:08Z"},{"alias_kind":"arxiv_version","alias_value":"2408.07199v1","created_at":"2026-05-20T09:35:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07199","created_at":"2026-05-20T09:35:08Z"},{"alias_kind":"pith_short_12","alias_value":"2L4FAKGGEOR2","created_at":"2026-05-20T09:35:08Z"},{"alias_kind":"pith_short_16","alias_value":"2L4FAKGGEOR2HTPL","created_at":"2026-05-20T09:35:08Z"},{"alias_kind":"pith_short_8","alias_value":"2L4FAKGG","created_at":"2026-05-20T09:35:08Z"}],"graph_snapshots":[{"event_id":"sha256:613e095d06cb03b7bc009c95660b7c606ec416c8f94e453a078ce31b471eb370","target":"graph","created_at":"2026-05-20T09:35:08Z","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/2408.07199/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have shown remarkable capabilities in natural language tasks requiring complex reasoning, yet their application in agentic, multi-step reasoning within interactive environments remains a difficult challenge. Traditional supervised pre-training on static datasets falls short in enabling autonomous agent capabilities needed to perform complex decision-making in dynamic settings like web navigation. Previous attempts to bridge this ga-through supervised fine-tuning on curated expert demonstrations-often suffer from compounding errors and limited exploration data, resu","authors_text":"Chelsea Finn, Divyansh Garg, Edmund Mills, Naman Garg, Pranav Putta, Rafael Rafailov, Sumeet Motwani","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-13T20:52:13Z","title":"Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07199","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":"sha256:6650972d8fa32b10348aff29ac4320e2b06b2d731da3b9bbbd08692f6ce66471","target":"record","created_at":"2026-05-20T09:35:08Z","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":"5b2e27ddc7ea6a265d790907172ae82d31964b8e26bd29d1326fcf4c253266bf","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-13T20:52:13Z","title_canon_sha256":"aff3059869cd36b4e19efb4f131b57952fd244b5ba2881d3e756d11de12b1848"},"schema_version":"1.0","source":{"id":"2408.07199","kind":"arxiv","version":1}},"canonical_sha256":"d2f85028c623a3a3cdeb409631825eb1571db53863612425ae10a455f16d4184","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2f85028c623a3a3cdeb409631825eb1571db53863612425ae10a455f16d4184","first_computed_at":"2026-05-20T09:35:08.612677Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T09:35:08.612677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gYVYnw6fQVTn1Ss3jPjd+kwyWiz1HS80d34jADhC0Te37ANAYv0ujBYGCDcLBS/E7d6XIUeSVm9QumNFQ91LAA==","signature_status":"signed_v1","signed_at":"2026-05-20T09:35:08.614305Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.07199","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6650972d8fa32b10348aff29ac4320e2b06b2d731da3b9bbbd08692f6ce66471","sha256:613e095d06cb03b7bc009c95660b7c606ec416c8f94e453a078ce31b471eb370"],"state_sha256":"4de88e938bfb275b032b81fcaf254e3cb6390e4663c12770a441c02659472751"}