{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XSBWRUHFB4XPNWLST7SKM6M26B","short_pith_number":"pith:XSBWRUHF","schema_version":"1.0","canonical_sha256":"bc8368d0e50f2ef6d9729fe4a6799af074256e5eb22e8b962945f43ef4d76aa1","source":{"kind":"arxiv","id":"2310.16035","version":1},"attestation_state":"computed","paper":{"title":"What's Left? Concept Grounding with Logic-Enhanced Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Jiajun Wu, Jiayuan Mao, Joshua B. Tenenbaum, Joy Hsu","submitted_at":"2023-10-24T17:50:20Z","abstract_excerpt":"Recent works such as VisProg and ViperGPT have smartly composed foundation models for visual reasoning-using large language models (LLMs) to produce programs that can be executed by pre-trained vision-language models. However, they operate in limited domains, such as 2D images, not fully exploiting the generalization of language: abstract concepts like \"left\" can also be grounded in 3D, temporal, and action data, as in moving to your left. This limited generalization stems from these inference-only methods' inability to learn or adapt pre-trained models to a new domain. We propose the Logic-En"},"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":"2310.16035","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-24T17:50:20Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","stat.ML"],"title_canon_sha256":"93e57feaf8232a2939bfbdb21846f49cd8d03b3b46082365fb55359579ad56d9","abstract_canon_sha256":"48a297a356d6a52cb54eb430f082e702f6c12b136178ebe11ab8d2bdfeb583e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:34.095592Z","signature_b64":"RpLyCy7YA8YqdQcaFrcIz1h/HS7kUa/iyMg63L2T2JEErfoSjc1R0bDZf6lh18Win2gkHM5/1pHxIc1gxxNmAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc8368d0e50f2ef6d9729fe4a6799af074256e5eb22e8b962945f43ef4d76aa1","last_reissued_at":"2026-07-05T07:04:34.095108Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:34.095108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What's Left? Concept Grounding with Logic-Enhanced Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Jiajun Wu, Jiayuan Mao, Joshua B. Tenenbaum, Joy Hsu","submitted_at":"2023-10-24T17:50:20Z","abstract_excerpt":"Recent works such as VisProg and ViperGPT have smartly composed foundation models for visual reasoning-using large language models (LLMs) to produce programs that can be executed by pre-trained vision-language models. However, they operate in limited domains, such as 2D images, not fully exploiting the generalization of language: abstract concepts like \"left\" can also be grounded in 3D, temporal, and action data, as in moving to your left. This limited generalization stems from these inference-only methods' inability to learn or adapt pre-trained models to a new domain. We propose the Logic-En"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16035","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/2310.16035/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":"2310.16035","created_at":"2026-07-05T07:04:34.095169+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.16035v1","created_at":"2026-07-05T07:04:34.095169+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16035","created_at":"2026-07-05T07:04:34.095169+00:00"},{"alias_kind":"pith_short_12","alias_value":"XSBWRUHFB4XP","created_at":"2026-07-05T07:04:34.095169+00:00"},{"alias_kind":"pith_short_16","alias_value":"XSBWRUHFB4XPNWLS","created_at":"2026-07-05T07:04:34.095169+00:00"},{"alias_kind":"pith_short_8","alias_value":"XSBWRUHF","created_at":"2026-07-05T07:04:34.095169+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.10928","citing_title":"Generative Physical AI in Vision: A Survey","ref_index":248,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XSBWRUHFB4XPNWLST7SKM6M26B","json":"https://pith.science/pith/XSBWRUHFB4XPNWLST7SKM6M26B.json","graph_json":"https://pith.science/api/pith-number/XSBWRUHFB4XPNWLST7SKM6M26B/graph.json","events_json":"https://pith.science/api/pith-number/XSBWRUHFB4XPNWLST7SKM6M26B/events.json","paper":"https://pith.science/paper/XSBWRUHF"},"agent_actions":{"view_html":"https://pith.science/pith/XSBWRUHFB4XPNWLST7SKM6M26B","download_json":"https://pith.science/pith/XSBWRUHFB4XPNWLST7SKM6M26B.json","view_paper":"https://pith.science/paper/XSBWRUHF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.16035&json=true","fetch_graph":"https://pith.science/api/pith-number/XSBWRUHFB4XPNWLST7SKM6M26B/graph.json","fetch_events":"https://pith.science/api/pith-number/XSBWRUHFB4XPNWLST7SKM6M26B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XSBWRUHFB4XPNWLST7SKM6M26B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XSBWRUHFB4XPNWLST7SKM6M26B/action/storage_attestation","attest_author":"https://pith.science/pith/XSBWRUHFB4XPNWLST7SKM6M26B/action/author_attestation","sign_citation":"https://pith.science/pith/XSBWRUHFB4XPNWLST7SKM6M26B/action/citation_signature","submit_replication":"https://pith.science/pith/XSBWRUHFB4XPNWLST7SKM6M26B/action/replication_record"}},"created_at":"2026-07-05T07:04:34.095169+00:00","updated_at":"2026-07-05T07:04:34.095169+00:00"}