{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TMADNTH7DLZDBZWCVYIRJXO4DM","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":"71890ac457844ef6888a12bdae001f2fbfcffb3ac88fbe3bf40e94fc5250cf0a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-06T04:51:57Z","title_canon_sha256":"52861e3114f5162ac6351ede617c0fb39b304ab870cb6e4f8608a1c831450429"},"schema_version":"1.0","source":{"id":"2505.03181","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03181","created_at":"2026-07-05T10:59:11Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03181v1","created_at":"2026-07-05T10:59:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03181","created_at":"2026-07-05T10:59:11Z"},{"alias_kind":"pith_short_12","alias_value":"TMADNTH7DLZD","created_at":"2026-07-05T10:59:11Z"},{"alias_kind":"pith_short_16","alias_value":"TMADNTH7DLZDBZWC","created_at":"2026-07-05T10:59:11Z"},{"alias_kind":"pith_short_8","alias_value":"TMADNTH7","created_at":"2026-07-05T10:59:11Z"}],"graph_snapshots":[{"event_id":"sha256:89b56cd649ae0d60fabba73b25259cbc69ea0c5e6ccf1184706cb70715428cac","target":"graph","created_at":"2026-07-05T10:59:11Z","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/2505.03181/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent research looks to harness the general knowledge and reasoning of large language models (LLMs) into agents that accomplish user-specified goals in interactive environments. Vision-language models (VLMs) extend LLMs to multi-modal data and provide agents with the visual reasoning necessary for new applications in areas such as computer automation. However, agent tasks emphasize skills where accessible open-weight VLMs lag behind their LLM equivalents. For example, VLMs are less capable of following an environment's strict output syntax requirements and are more focused on open-ended quest","authors_text":"Jake Grigsby, Juan Carlos Niebles, Michael Ryoo, Yuke Zhu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-06T04:51:57Z","title":"VLM Q-Learning: Aligning Vision-Language Models for Interactive Decision-Making"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03181","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":"sha256:19423907d614360b62f00d530a24a93cddae0b369e4d20018ea08f1b2e2b4b93","target":"record","created_at":"2026-07-05T10:59:11Z","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":"71890ac457844ef6888a12bdae001f2fbfcffb3ac88fbe3bf40e94fc5250cf0a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-06T04:51:57Z","title_canon_sha256":"52861e3114f5162ac6351ede617c0fb39b304ab870cb6e4f8608a1c831450429"},"schema_version":"1.0","source":{"id":"2505.03181","kind":"arxiv","version":1}},"canonical_sha256":"9b0036ccff1af230e6c2ae1114dddc1b20ad6b9f74da7376075f5c4b6737ce05","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b0036ccff1af230e6c2ae1114dddc1b20ad6b9f74da7376075f5c4b6737ce05","first_computed_at":"2026-07-05T10:59:11.602208Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:59:11.602208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rDAjun8TS0VaU6jQYI01JkSQXYWUkKxP5d304esddKNQKWZKoqQnCeu2kcAl1yJDleCv0MzVgkalabMoIY2sBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:59:11.602794Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.03181","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19423907d614360b62f00d530a24a93cddae0b369e4d20018ea08f1b2e2b4b93","sha256:89b56cd649ae0d60fabba73b25259cbc69ea0c5e6ccf1184706cb70715428cac"],"state_sha256":"14756af0571cbeccd49862a36fb3f6d9542c2c7b28662e32fa5fc9e2d9092f86"}