{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TMADNTH7DLZDBZWCVYIRJXO4DM","short_pith_number":"pith:TMADNTH7","schema_version":"1.0","canonical_sha256":"9b0036ccff1af230e6c2ae1114dddc1b20ad6b9f74da7376075f5c4b6737ce05","source":{"kind":"arxiv","id":"2505.03181","version":1},"attestation_state":"computed","paper":{"title":"VLM Q-Learning: Aligning Vision-Language Models for Interactive Decision-Making","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jake Grigsby, Juan Carlos Niebles, Michael Ryoo, Yuke Zhu","submitted_at":"2025-05-06T04:51:57Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.03181","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-06T04:51:57Z","cross_cats_sorted":[],"title_canon_sha256":"52861e3114f5162ac6351ede617c0fb39b304ab870cb6e4f8608a1c831450429","abstract_canon_sha256":"71890ac457844ef6888a12bdae001f2fbfcffb3ac88fbe3bf40e94fc5250cf0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:11.602794Z","signature_b64":"rDAjun8TS0VaU6jQYI01JkSQXYWUkKxP5d304esddKNQKWZKoqQnCeu2kcAl1yJDleCv0MzVgkalabMoIY2sBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b0036ccff1af230e6c2ae1114dddc1b20ad6b9f74da7376075f5c4b6737ce05","last_reissued_at":"2026-07-05T10:59:11.602208Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:11.602208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLM Q-Learning: Aligning Vision-Language Models for Interactive Decision-Making","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jake Grigsby, Juan Carlos Niebles, Michael Ryoo, Yuke Zhu","submitted_at":"2025-05-06T04:51:57Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03181","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/2505.03181/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.03181","created_at":"2026-07-05T10:59:11.602268+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.03181v1","created_at":"2026-07-05T10:59:11.602268+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03181","created_at":"2026-07-05T10:59:11.602268+00:00"},{"alias_kind":"pith_short_12","alias_value":"TMADNTH7DLZD","created_at":"2026-07-05T10:59:11.602268+00:00"},{"alias_kind":"pith_short_16","alias_value":"TMADNTH7DLZDBZWC","created_at":"2026-07-05T10:59:11.602268+00:00"},{"alias_kind":"pith_short_8","alias_value":"TMADNTH7","created_at":"2026-07-05T10:59:11.602268+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TMADNTH7DLZDBZWCVYIRJXO4DM","json":"https://pith.science/pith/TMADNTH7DLZDBZWCVYIRJXO4DM.json","graph_json":"https://pith.science/api/pith-number/TMADNTH7DLZDBZWCVYIRJXO4DM/graph.json","events_json":"https://pith.science/api/pith-number/TMADNTH7DLZDBZWCVYIRJXO4DM/events.json","paper":"https://pith.science/paper/TMADNTH7"},"agent_actions":{"view_html":"https://pith.science/pith/TMADNTH7DLZDBZWCVYIRJXO4DM","download_json":"https://pith.science/pith/TMADNTH7DLZDBZWCVYIRJXO4DM.json","view_paper":"https://pith.science/paper/TMADNTH7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.03181&json=true","fetch_graph":"https://pith.science/api/pith-number/TMADNTH7DLZDBZWCVYIRJXO4DM/graph.json","fetch_events":"https://pith.science/api/pith-number/TMADNTH7DLZDBZWCVYIRJXO4DM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TMADNTH7DLZDBZWCVYIRJXO4DM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TMADNTH7DLZDBZWCVYIRJXO4DM/action/storage_attestation","attest_author":"https://pith.science/pith/TMADNTH7DLZDBZWCVYIRJXO4DM/action/author_attestation","sign_citation":"https://pith.science/pith/TMADNTH7DLZDBZWCVYIRJXO4DM/action/citation_signature","submit_replication":"https://pith.science/pith/TMADNTH7DLZDBZWCVYIRJXO4DM/action/replication_record"}},"created_at":"2026-07-05T10:59:11.602268+00:00","updated_at":"2026-07-05T10:59:11.602268+00:00"}