{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2PIH4F5NRQIAGIH52MMP6Z264O","short_pith_number":"pith:2PIH4F5N","schema_version":"1.0","canonical_sha256":"d3d07e17ad8c100320fdd318ff675ee382956b37c62f6ab609d15df55bb4c316","source":{"kind":"arxiv","id":"2305.19374","version":1},"attestation_state":"computed","paper":{"title":"Compositional diversity in visual concept learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Brenden M. Lake, Reuben Feinman, YanLi Zhou","submitted_at":"2023-05-30T19:30:50Z","abstract_excerpt":"Humans leverage compositionality to efficiently learn new concepts, understanding how familiar parts can combine together to form novel objects. In contrast, popular computer vision models struggle to make the same types of inferences, requiring more data and generalizing less flexibly than people do. Here, we study these distinctively human abilities across a range of different types of visual composition, examining how people classify and generate ``alien figures'' with rich relational structure. We also develop a Bayesian program induction model which searches for the best programs for gene"},"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":"2305.19374","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-30T19:30:50Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"436b61492883b83d422a1c20e6ee2bc31fcd128beefddb46cd05437ee402675b","abstract_canon_sha256":"d5090f265ec31dbdf47e643e03eea9b4dbba54a1424520f313246ac1ea103297"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:49.442371Z","signature_b64":"PS92UZeYBQ+ZVjlIlt1KroDxOYjrAVQhImICpR4x/+OVVkQSDwbnp/P1HBN2lzKgWfz3bKmk9duLrZoQFk/yDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3d07e17ad8c100320fdd318ff675ee382956b37c62f6ab609d15df55bb4c316","last_reissued_at":"2026-07-05T06:15:49.441864Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:49.441864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compositional diversity in visual concept learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Brenden M. Lake, Reuben Feinman, YanLi Zhou","submitted_at":"2023-05-30T19:30:50Z","abstract_excerpt":"Humans leverage compositionality to efficiently learn new concepts, understanding how familiar parts can combine together to form novel objects. In contrast, popular computer vision models struggle to make the same types of inferences, requiring more data and generalizing less flexibly than people do. Here, we study these distinctively human abilities across a range of different types of visual composition, examining how people classify and generate ``alien figures'' with rich relational structure. We also develop a Bayesian program induction model which searches for the best programs for gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19374","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/2305.19374/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":"2305.19374","created_at":"2026-07-05T06:15:49.441916+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.19374v1","created_at":"2026-07-05T06:15:49.441916+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19374","created_at":"2026-07-05T06:15:49.441916+00:00"},{"alias_kind":"pith_short_12","alias_value":"2PIH4F5NRQIA","created_at":"2026-07-05T06:15:49.441916+00:00"},{"alias_kind":"pith_short_16","alias_value":"2PIH4F5NRQIAGIH5","created_at":"2026-07-05T06:15:49.441916+00:00"},{"alias_kind":"pith_short_8","alias_value":"2PIH4F5N","created_at":"2026-07-05T06:15:49.441916+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/2PIH4F5NRQIAGIH52MMP6Z264O","json":"https://pith.science/pith/2PIH4F5NRQIAGIH52MMP6Z264O.json","graph_json":"https://pith.science/api/pith-number/2PIH4F5NRQIAGIH52MMP6Z264O/graph.json","events_json":"https://pith.science/api/pith-number/2PIH4F5NRQIAGIH52MMP6Z264O/events.json","paper":"https://pith.science/paper/2PIH4F5N"},"agent_actions":{"view_html":"https://pith.science/pith/2PIH4F5NRQIAGIH52MMP6Z264O","download_json":"https://pith.science/pith/2PIH4F5NRQIAGIH52MMP6Z264O.json","view_paper":"https://pith.science/paper/2PIH4F5N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.19374&json=true","fetch_graph":"https://pith.science/api/pith-number/2PIH4F5NRQIAGIH52MMP6Z264O/graph.json","fetch_events":"https://pith.science/api/pith-number/2PIH4F5NRQIAGIH52MMP6Z264O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2PIH4F5NRQIAGIH52MMP6Z264O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2PIH4F5NRQIAGIH52MMP6Z264O/action/storage_attestation","attest_author":"https://pith.science/pith/2PIH4F5NRQIAGIH52MMP6Z264O/action/author_attestation","sign_citation":"https://pith.science/pith/2PIH4F5NRQIAGIH52MMP6Z264O/action/citation_signature","submit_replication":"https://pith.science/pith/2PIH4F5NRQIAGIH52MMP6Z264O/action/replication_record"}},"created_at":"2026-07-05T06:15:49.441916+00:00","updated_at":"2026-07-05T06:15:49.441916+00:00"}