{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7UF5AC5AWLMG6PX2Z6PTA2PWU5","short_pith_number":"pith:7UF5AC5A","schema_version":"1.0","canonical_sha256":"fd0bd00ba0b2d86f3efacf9f3069f6a7406e081e8d0a8d996ea1f01dc4f477b2","source":{"kind":"arxiv","id":"2211.11559","version":1},"attestation_state":"computed","paper":{"title":"Visual Programming: Compositional visual reasoning without training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Aniruddha Kembhavi, Tanmay Gupta","submitted_at":"2022-11-18T18:50:09Z","abstract_excerpt":"We present VISPROG, a neuro-symbolic approach to solving complex and compositional visual tasks given natural language instructions. VISPROG avoids the need for any task-specific training. Instead, it uses the in-context learning ability of large language models to generate python-like modular programs, which are then executed to get both the solution and a comprehensive and interpretable rationale. Each line of the generated program may invoke one of several off-the-shelf computer vision models, image processing routines, or python functions to produce intermediate outputs that may be consume"},"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":"2211.11559","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-18T18:50:09Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"641b1923feaa35616bc1763bdbed1e03df72e2bb3cc8c2d7b98dd2bada8332cc","abstract_canon_sha256":"9ac244522d3709d84096235c909f849b89611c44a943c0234e8f63a5e51409fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:55.051002Z","signature_b64":"+3f6m4n5kb/vJxLVLSlqpCqszp0DpQDzoRp2PoeK44jgAREphmx+2FgJqXYj+TfTcHeKgRwzGzI0y8xt4JM8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd0bd00ba0b2d86f3efacf9f3069f6a7406e081e8d0a8d996ea1f01dc4f477b2","last_reissued_at":"2026-07-05T05:17:55.050569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:55.050569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Programming: Compositional visual reasoning without training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Aniruddha Kembhavi, Tanmay Gupta","submitted_at":"2022-11-18T18:50:09Z","abstract_excerpt":"We present VISPROG, a neuro-symbolic approach to solving complex and compositional visual tasks given natural language instructions. VISPROG avoids the need for any task-specific training. Instead, it uses the in-context learning ability of large language models to generate python-like modular programs, which are then executed to get both the solution and a comprehensive and interpretable rationale. Each line of the generated program may invoke one of several off-the-shelf computer vision models, image processing routines, or python functions to produce intermediate outputs that may be consume"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.11559","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/2211.11559/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":"2211.11559","created_at":"2026-07-05T05:17:55.050623+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.11559v1","created_at":"2026-07-05T05:17:55.050623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.11559","created_at":"2026-07-05T05:17:55.050623+00:00"},{"alias_kind":"pith_short_12","alias_value":"7UF5AC5AWLMG","created_at":"2026-07-05T05:17:55.050623+00:00"},{"alias_kind":"pith_short_16","alias_value":"7UF5AC5AWLMG6PX2","created_at":"2026-07-05T05:17:55.050623+00:00"},{"alias_kind":"pith_short_8","alias_value":"7UF5AC5A","created_at":"2026-07-05T05:17:55.050623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00384","citing_title":"VESTA: Visual Exploration with Statistical Tool Agents","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2407.08101","citing_title":"What to Say and When to Say it: Live Fitness Coaching as a Testbed for Situated Interaction","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2505.23678","citing_title":"Grounded Reinforcement Learning for Visual Reasoning","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2303.08128","citing_title":"ViperGPT: Visual Inference via Python Execution for Reasoning","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10362","citing_title":"Visual Funnel: Resolving Contextual Blindness in Multimodal Large Language Models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2304.15010","citing_title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2303.17580","citing_title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2304.08485","citing_title":"Visual Instruction Tuning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09167","citing_title":"MAG-3D: Multi-Agent Grounded Reasoning for 3D Understanding","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7UF5AC5AWLMG6PX2Z6PTA2PWU5","json":"https://pith.science/pith/7UF5AC5AWLMG6PX2Z6PTA2PWU5.json","graph_json":"https://pith.science/api/pith-number/7UF5AC5AWLMG6PX2Z6PTA2PWU5/graph.json","events_json":"https://pith.science/api/pith-number/7UF5AC5AWLMG6PX2Z6PTA2PWU5/events.json","paper":"https://pith.science/paper/7UF5AC5A"},"agent_actions":{"view_html":"https://pith.science/pith/7UF5AC5AWLMG6PX2Z6PTA2PWU5","download_json":"https://pith.science/pith/7UF5AC5AWLMG6PX2Z6PTA2PWU5.json","view_paper":"https://pith.science/paper/7UF5AC5A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.11559&json=true","fetch_graph":"https://pith.science/api/pith-number/7UF5AC5AWLMG6PX2Z6PTA2PWU5/graph.json","fetch_events":"https://pith.science/api/pith-number/7UF5AC5AWLMG6PX2Z6PTA2PWU5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7UF5AC5AWLMG6PX2Z6PTA2PWU5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7UF5AC5AWLMG6PX2Z6PTA2PWU5/action/storage_attestation","attest_author":"https://pith.science/pith/7UF5AC5AWLMG6PX2Z6PTA2PWU5/action/author_attestation","sign_citation":"https://pith.science/pith/7UF5AC5AWLMG6PX2Z6PTA2PWU5/action/citation_signature","submit_replication":"https://pith.science/pith/7UF5AC5AWLMG6PX2Z6PTA2PWU5/action/replication_record"}},"created_at":"2026-07-05T05:17:55.050623+00:00","updated_at":"2026-07-05T05:17:55.050623+00:00"}