{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:EHYFXRUBNWQXWAJJQXEFYFCET7","short_pith_number":"pith:EHYFXRUB","schema_version":"1.0","canonical_sha256":"21f05bc6816da17b012985c85c14449fd9cf5f2b71649154a91e3e71c309b1c1","source":{"kind":"arxiv","id":"2008.03519","version":1},"attestation_state":"computed","paper":{"title":"Learning abstract structure for drawing by efficient motor program induction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-bio.NC"],"primary_cat":"cs.AI","authors_text":"Joshua B. Tenenbaum, Kevin Ellis, Lucas Y. Tian, Marta Kryven","submitted_at":"2020-08-08T13:31:14Z","abstract_excerpt":"Humans flexibly solve new problems that differ qualitatively from those they were trained on. This ability to generalize is supported by learned concepts that capture structure common across different problems. Here we develop a naturalistic drawing task to study how humans rapidly acquire structured prior knowledge. The task requires drawing visual objects that share underlying structure, based on a set of composable geometric rules. We show that people spontaneously learn abstract drawing procedures that support generalization, and propose a model of how learners can discover these reusable "},"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":"2008.03519","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-08-08T13:31:14Z","cross_cats_sorted":["cs.LG","q-bio.NC"],"title_canon_sha256":"325ce8a332981f643965abf28e281824b986abafddd41f30164e7911bf8c15d1","abstract_canon_sha256":"19e13b329b3b5be5b459b666697153249fc5e1d362b766488030a34831ab535e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:25:42.657535Z","signature_b64":"jeQs+bQ1aaoNXD8fx5yGmtusbBwzeqkXgbMSuNHumy7g4HG+GUqzi0FuJmKx3ZUJ8ewTufsB1+nj+UtvLA2HDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21f05bc6816da17b012985c85c14449fd9cf5f2b71649154a91e3e71c309b1c1","last_reissued_at":"2026-07-05T01:25:42.657162Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:25:42.657162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning abstract structure for drawing by efficient motor program induction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-bio.NC"],"primary_cat":"cs.AI","authors_text":"Joshua B. Tenenbaum, Kevin Ellis, Lucas Y. Tian, Marta Kryven","submitted_at":"2020-08-08T13:31:14Z","abstract_excerpt":"Humans flexibly solve new problems that differ qualitatively from those they were trained on. This ability to generalize is supported by learned concepts that capture structure common across different problems. Here we develop a naturalistic drawing task to study how humans rapidly acquire structured prior knowledge. The task requires drawing visual objects that share underlying structure, based on a set of composable geometric rules. We show that people spontaneously learn abstract drawing procedures that support generalization, and propose a model of how learners can discover these reusable "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.03519","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/2008.03519/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":"2008.03519","created_at":"2026-07-05T01:25:42.657218+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.03519v1","created_at":"2026-07-05T01:25:42.657218+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.03519","created_at":"2026-07-05T01:25:42.657218+00:00"},{"alias_kind":"pith_short_12","alias_value":"EHYFXRUBNWQX","created_at":"2026-07-05T01:25:42.657218+00:00"},{"alias_kind":"pith_short_16","alias_value":"EHYFXRUBNWQXWAJJ","created_at":"2026-07-05T01:25:42.657218+00:00"},{"alias_kind":"pith_short_8","alias_value":"EHYFXRUB","created_at":"2026-07-05T01:25:42.657218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.14104","citing_title":"Legal Rule Induction: Towards Generalizable Principle Discovery from Analogous Judicial Precedents","ref_index":2020,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EHYFXRUBNWQXWAJJQXEFYFCET7","json":"https://pith.science/pith/EHYFXRUBNWQXWAJJQXEFYFCET7.json","graph_json":"https://pith.science/api/pith-number/EHYFXRUBNWQXWAJJQXEFYFCET7/graph.json","events_json":"https://pith.science/api/pith-number/EHYFXRUBNWQXWAJJQXEFYFCET7/events.json","paper":"https://pith.science/paper/EHYFXRUB"},"agent_actions":{"view_html":"https://pith.science/pith/EHYFXRUBNWQXWAJJQXEFYFCET7","download_json":"https://pith.science/pith/EHYFXRUBNWQXWAJJQXEFYFCET7.json","view_paper":"https://pith.science/paper/EHYFXRUB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.03519&json=true","fetch_graph":"https://pith.science/api/pith-number/EHYFXRUBNWQXWAJJQXEFYFCET7/graph.json","fetch_events":"https://pith.science/api/pith-number/EHYFXRUBNWQXWAJJQXEFYFCET7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EHYFXRUBNWQXWAJJQXEFYFCET7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EHYFXRUBNWQXWAJJQXEFYFCET7/action/storage_attestation","attest_author":"https://pith.science/pith/EHYFXRUBNWQXWAJJQXEFYFCET7/action/author_attestation","sign_citation":"https://pith.science/pith/EHYFXRUBNWQXWAJJQXEFYFCET7/action/citation_signature","submit_replication":"https://pith.science/pith/EHYFXRUBNWQXWAJJQXEFYFCET7/action/replication_record"}},"created_at":"2026-07-05T01:25:42.657218+00:00","updated_at":"2026-07-05T01:25:42.657218+00:00"}