{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6CPCANAG7QD26DSTPM7XQJKKBM","short_pith_number":"pith:6CPCANAG","schema_version":"1.0","canonical_sha256":"f09e203406fc07af0e537b3f78254a0b169c078e66c3f16fa311b679fe1afc75","source":{"kind":"arxiv","id":"2502.20237","version":1},"attestation_state":"computed","paper":{"title":"Teasing Apart Architecture and Initial Weights as Sources of Inductive Bias in Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gianluca Bencomo, Ioana Marinescu, Max Gupta, R. Thomas McCoy, Thomas L. Griffiths","submitted_at":"2025-02-27T16:22:18Z","abstract_excerpt":"Artificial neural networks can acquire many aspects of human knowledge from data, making them promising as models of human learning. But what those networks can learn depends upon their inductive biases -- the factors other than the data that influence the solutions they discover -- and the inductive biases of neural networks remain poorly understood, limiting our ability to draw conclusions about human learning from the performance of these systems. Cognitive scientists and machine learning researchers often focus on the architecture of a neural network as a source of inductive bias. In this "},"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":"2502.20237","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-27T16:22:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e599bece7401a1d7c7fe82e5ed94b187ac9c54a6ca1df1fa495d5ca2347d6d80","abstract_canon_sha256":"318b68b568080bfa12f257942107cc16d8bfb8e3dd4703d5a444dda49c894354"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:11.539871Z","signature_b64":"U3rI8wQBmOn1h2Mw/e+Sjb1qXU3Q/wGPAQT4mqlYhoqUkS+j2LEUfjSx4BmQ/r5sZf9cAeX8i7igjquvLn+vAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f09e203406fc07af0e537b3f78254a0b169c078e66c3f16fa311b679fe1afc75","last_reissued_at":"2026-07-05T10:21:11.539368Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:11.539368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Teasing Apart Architecture and Initial Weights as Sources of Inductive Bias in Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gianluca Bencomo, Ioana Marinescu, Max Gupta, R. Thomas McCoy, Thomas L. Griffiths","submitted_at":"2025-02-27T16:22:18Z","abstract_excerpt":"Artificial neural networks can acquire many aspects of human knowledge from data, making them promising as models of human learning. But what those networks can learn depends upon their inductive biases -- the factors other than the data that influence the solutions they discover -- and the inductive biases of neural networks remain poorly understood, limiting our ability to draw conclusions about human learning from the performance of these systems. Cognitive scientists and machine learning researchers often focus on the architecture of a neural network as a source of inductive bias. In this "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20237","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/2502.20237/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":"2502.20237","created_at":"2026-07-05T10:21:11.539431+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.20237v1","created_at":"2026-07-05T10:21:11.539431+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20237","created_at":"2026-07-05T10:21:11.539431+00:00"},{"alias_kind":"pith_short_12","alias_value":"6CPCANAG7QD2","created_at":"2026-07-05T10:21:11.539431+00:00"},{"alias_kind":"pith_short_16","alias_value":"6CPCANAG7QD26DST","created_at":"2026-07-05T10:21:11.539431+00:00"},{"alias_kind":"pith_short_8","alias_value":"6CPCANAG","created_at":"2026-07-05T10:21:11.539431+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28380","citing_title":"Distilling a Modular Reservoir Through a Genomic Bottleneck","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6CPCANAG7QD26DSTPM7XQJKKBM","json":"https://pith.science/pith/6CPCANAG7QD26DSTPM7XQJKKBM.json","graph_json":"https://pith.science/api/pith-number/6CPCANAG7QD26DSTPM7XQJKKBM/graph.json","events_json":"https://pith.science/api/pith-number/6CPCANAG7QD26DSTPM7XQJKKBM/events.json","paper":"https://pith.science/paper/6CPCANAG"},"agent_actions":{"view_html":"https://pith.science/pith/6CPCANAG7QD26DSTPM7XQJKKBM","download_json":"https://pith.science/pith/6CPCANAG7QD26DSTPM7XQJKKBM.json","view_paper":"https://pith.science/paper/6CPCANAG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.20237&json=true","fetch_graph":"https://pith.science/api/pith-number/6CPCANAG7QD26DSTPM7XQJKKBM/graph.json","fetch_events":"https://pith.science/api/pith-number/6CPCANAG7QD26DSTPM7XQJKKBM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6CPCANAG7QD26DSTPM7XQJKKBM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6CPCANAG7QD26DSTPM7XQJKKBM/action/storage_attestation","attest_author":"https://pith.science/pith/6CPCANAG7QD26DSTPM7XQJKKBM/action/author_attestation","sign_citation":"https://pith.science/pith/6CPCANAG7QD26DSTPM7XQJKKBM/action/citation_signature","submit_replication":"https://pith.science/pith/6CPCANAG7QD26DSTPM7XQJKKBM/action/replication_record"}},"created_at":"2026-07-05T10:21:11.539431+00:00","updated_at":"2026-07-05T10:21:11.539431+00:00"}