{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:H7J245YJQG4POAE4YUD5LOEP25","short_pith_number":"pith:H7J245YJ","schema_version":"1.0","canonical_sha256":"3fd3ae770981b8f7009cc507d5b88fd749c2c1449e57a5f2b84cc8555d6e3372","source":{"kind":"arxiv","id":"1904.12584","version":1},"attestation_state":"computed","paper":{"title":"The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chuang Gan, Jiajun Wu, Jiayuan Mao, Joshua B. Tenenbaum, Pushmeet Kohli","submitted_at":"2019-04-26T06:50:54Z","abstract_excerpt":"We propose the Neuro-Symbolic Concept Learner (NS-CL), a model that learns visual concepts, words, and semantic parsing of sentences without explicit supervision on any of them; instead, our model learns by simply looking at images and reading paired questions and answers. Our model builds an object-based scene representation and translates sentences into executable, symbolic programs. To bridge the learning of two modules, we use a neuro-symbolic reasoning module that executes these programs on the latent scene representation. Analogical to human concept learning, the perception module learns"},"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":"1904.12584","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-26T06:50:54Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"2b986e0502b087dcf032332757ae361c9bba656934f8accf1030335e685ec41a","abstract_canon_sha256":"509b01abc477629115b79445f3cb0fd6d848831fc75e744f04810eaedccb03fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:34.755544Z","signature_b64":"nPyhSPnRh/449iITNJlhhB9PnUt38qIRjrbpu/MxaJNO0UAV/11fsDcApYgF6ZGtUCgcnRR6698YEqpWnkcoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fd3ae770981b8f7009cc507d5b88fd749c2c1449e57a5f2b84cc8555d6e3372","last_reissued_at":"2026-05-17T23:47:34.754956Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:34.754956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chuang Gan, Jiajun Wu, Jiayuan Mao, Joshua B. Tenenbaum, Pushmeet Kohli","submitted_at":"2019-04-26T06:50:54Z","abstract_excerpt":"We propose the Neuro-Symbolic Concept Learner (NS-CL), a model that learns visual concepts, words, and semantic parsing of sentences without explicit supervision on any of them; instead, our model learns by simply looking at images and reading paired questions and answers. Our model builds an object-based scene representation and translates sentences into executable, symbolic programs. To bridge the learning of two modules, we use a neuro-symbolic reasoning module that executes these programs on the latent scene representation. Analogical to human concept learning, the perception module learns"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.12584","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":""},"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":"1904.12584","created_at":"2026-05-17T23:47:34.755050+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.12584v1","created_at":"2026-05-17T23:47:34.755050+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.12584","created_at":"2026-05-17T23:47:34.755050+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7J245YJQG4P","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7J245YJQG4POAE4","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7J245YJ","created_at":"2026-05-18T12:33:18.533446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2409.01652","citing_title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2603.25903","citing_title":"Emergent Neural Automaton Policies: Learning Symbolic Structure from Visuomotor Trajectories","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15623","citing_title":"Overmind NSA: A Unified Neuro-Symbolic Computing Architecture with Approximate Nonlinear Activations and Preemptive Memory Bypass","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16871","citing_title":"GRAIL: Autonomous Concept Grounding for Neuro-Symbolic Reinforcement Learning","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H7J245YJQG4POAE4YUD5LOEP25","json":"https://pith.science/pith/H7J245YJQG4POAE4YUD5LOEP25.json","graph_json":"https://pith.science/api/pith-number/H7J245YJQG4POAE4YUD5LOEP25/graph.json","events_json":"https://pith.science/api/pith-number/H7J245YJQG4POAE4YUD5LOEP25/events.json","paper":"https://pith.science/paper/H7J245YJ"},"agent_actions":{"view_html":"https://pith.science/pith/H7J245YJQG4POAE4YUD5LOEP25","download_json":"https://pith.science/pith/H7J245YJQG4POAE4YUD5LOEP25.json","view_paper":"https://pith.science/paper/H7J245YJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.12584&json=true","fetch_graph":"https://pith.science/api/pith-number/H7J245YJQG4POAE4YUD5LOEP25/graph.json","fetch_events":"https://pith.science/api/pith-number/H7J245YJQG4POAE4YUD5LOEP25/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7J245YJQG4POAE4YUD5LOEP25/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7J245YJQG4POAE4YUD5LOEP25/action/storage_attestation","attest_author":"https://pith.science/pith/H7J245YJQG4POAE4YUD5LOEP25/action/author_attestation","sign_citation":"https://pith.science/pith/H7J245YJQG4POAE4YUD5LOEP25/action/citation_signature","submit_replication":"https://pith.science/pith/H7J245YJQG4POAE4YUD5LOEP25/action/replication_record"}},"created_at":"2026-05-17T23:47:34.755050+00:00","updated_at":"2026-05-17T23:47:34.755050+00:00"}