{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XBQT6FT3VMYLLVZJPFJDCV6H6C","short_pith_number":"pith:XBQT6FT3","schema_version":"1.0","canonical_sha256":"b8613f167bab30b5d72979523157c7f085345e4ec6ca87c4b0e359ae497f915f","source":{"kind":"arxiv","id":"2311.12890","version":3},"attestation_state":"computed","paper":{"title":"De-fine: Decomposing and Refining Visual Programs with Auto-Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guoming Wang, Hao Fei, Juncheng Li, Liang Pang, Minghe Gao, Siliang Tang, Wei Ji, Wenqiao Zhang, Yueting Zhuang, Zheqi Lv","submitted_at":"2023-11-21T06:24:09Z","abstract_excerpt":"Visual programming, a modular and generalizable paradigm, integrates different modules and Python operators to solve various vision-language tasks. Unlike end-to-end models that need task-specific data, it advances in performing visual processing and reasoning in an unsupervised manner. Current visual programming methods generate programs in a single pass for each task where the ability to evaluate and optimize based on feedback, unfortunately, is lacking, which consequentially limits their effectiveness for complex, multi-step problems. Drawing inspiration from benders decomposition, we intro"},"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":"2311.12890","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-21T06:24:09Z","cross_cats_sorted":[],"title_canon_sha256":"c4b9aa7912ddb267c3dfdbdcb05c7b076fba0b38dbec592b7f3b3e62ef719966","abstract_canon_sha256":"60d7ac0e934b4c4e475561e123091e896be2833284b0785a03da198ad954596a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:51:44.829890Z","signature_b64":"jyXrnDCpZzjGa9ScSul1kaX1/pn1HZR2X/KeNQQo4v62l+BGSPpnyxcxOQWW1A2LfqbX5oaCc8Docpa6FIxZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8613f167bab30b5d72979523157c7f085345e4ec6ca87c4b0e359ae497f915f","last_reissued_at":"2026-07-05T08:51:44.829407Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:51:44.829407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"De-fine: Decomposing and Refining Visual Programs with Auto-Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guoming Wang, Hao Fei, Juncheng Li, Liang Pang, Minghe Gao, Siliang Tang, Wei Ji, Wenqiao Zhang, Yueting Zhuang, Zheqi Lv","submitted_at":"2023-11-21T06:24:09Z","abstract_excerpt":"Visual programming, a modular and generalizable paradigm, integrates different modules and Python operators to solve various vision-language tasks. Unlike end-to-end models that need task-specific data, it advances in performing visual processing and reasoning in an unsupervised manner. Current visual programming methods generate programs in a single pass for each task where the ability to evaluate and optimize based on feedback, unfortunately, is lacking, which consequentially limits their effectiveness for complex, multi-step problems. Drawing inspiration from benders decomposition, we intro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.12890","kind":"arxiv","version":3},"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/2311.12890/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":"2311.12890","created_at":"2026-07-05T08:51:44.829465+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.12890v3","created_at":"2026-07-05T08:51:44.829465+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.12890","created_at":"2026-07-05T08:51:44.829465+00:00"},{"alias_kind":"pith_short_12","alias_value":"XBQT6FT3VMYL","created_at":"2026-07-05T08:51:44.829465+00:00"},{"alias_kind":"pith_short_16","alias_value":"XBQT6FT3VMYLLVZJ","created_at":"2026-07-05T08:51:44.829465+00:00"},{"alias_kind":"pith_short_8","alias_value":"XBQT6FT3","created_at":"2026-07-05T08:51:44.829465+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.19473","citing_title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","ref_index":256,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XBQT6FT3VMYLLVZJPFJDCV6H6C","json":"https://pith.science/pith/XBQT6FT3VMYLLVZJPFJDCV6H6C.json","graph_json":"https://pith.science/api/pith-number/XBQT6FT3VMYLLVZJPFJDCV6H6C/graph.json","events_json":"https://pith.science/api/pith-number/XBQT6FT3VMYLLVZJPFJDCV6H6C/events.json","paper":"https://pith.science/paper/XBQT6FT3"},"agent_actions":{"view_html":"https://pith.science/pith/XBQT6FT3VMYLLVZJPFJDCV6H6C","download_json":"https://pith.science/pith/XBQT6FT3VMYLLVZJPFJDCV6H6C.json","view_paper":"https://pith.science/paper/XBQT6FT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.12890&json=true","fetch_graph":"https://pith.science/api/pith-number/XBQT6FT3VMYLLVZJPFJDCV6H6C/graph.json","fetch_events":"https://pith.science/api/pith-number/XBQT6FT3VMYLLVZJPFJDCV6H6C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XBQT6FT3VMYLLVZJPFJDCV6H6C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XBQT6FT3VMYLLVZJPFJDCV6H6C/action/storage_attestation","attest_author":"https://pith.science/pith/XBQT6FT3VMYLLVZJPFJDCV6H6C/action/author_attestation","sign_citation":"https://pith.science/pith/XBQT6FT3VMYLLVZJPFJDCV6H6C/action/citation_signature","submit_replication":"https://pith.science/pith/XBQT6FT3VMYLLVZJPFJDCV6H6C/action/replication_record"}},"created_at":"2026-07-05T08:51:44.829465+00:00","updated_at":"2026-07-05T08:51:44.829465+00:00"}