{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:NCCRXVO6FZG66XB2INGL63Y5RV","short_pith_number":"pith:NCCRXVO6","schema_version":"1.0","canonical_sha256":"68851bd5de2e4def5c3a434cbf6f1d8d51630fafecc593edf85035e89a2d349a","source":{"kind":"arxiv","id":"1412.6563","version":2},"attestation_state":"computed","paper":{"title":"Self-informed neural network structure learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Andrew Rabinovich, David Warde-Farley, Dragomir Anguelov","submitted_at":"2014-12-20T00:05:57Z","abstract_excerpt":"We study the problem of large scale, multi-label visual recognition with a large number of possible classes. We propose a method for augmenting a trained neural network classifier with auxiliary capacity in a manner designed to significantly improve upon an already well-performing model, while minimally impacting its computational footprint. Using the predictions of the network itself as a descriptor for assessing visual similarity, we define a partitioning of the label space into groups of visually similar entities. We then augment the network with auxilliary hidden layer pathways with connec"},"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":"1412.6563","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-12-20T00:05:57Z","cross_cats_sorted":["cs.CV","cs.LG","cs.NE"],"title_canon_sha256":"34c602cb15bcc0064b152c8b1e6ac5e689da762d2b1beec8a14fa6ed5dbed16c","abstract_canon_sha256":"682ae22b5be076470a5826a510435581beec47b4c46def4378d232eeff7552da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:18:58.222056Z","signature_b64":"kJFRgZYSiBzBu1RRx2tzOQkrsPCq1VQNBGG+q3erSyiGZXv4p+7cV4w5NzjpWuSc/e30VDVvzbz0Mmsm2ZFdBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68851bd5de2e4def5c3a434cbf6f1d8d51630fafecc593edf85035e89a2d349a","last_reissued_at":"2026-05-18T02:18:58.221505Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:18:58.221505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-informed neural network structure learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Andrew Rabinovich, David Warde-Farley, Dragomir Anguelov","submitted_at":"2014-12-20T00:05:57Z","abstract_excerpt":"We study the problem of large scale, multi-label visual recognition with a large number of possible classes. We propose a method for augmenting a trained neural network classifier with auxiliary capacity in a manner designed to significantly improve upon an already well-performing model, while minimally impacting its computational footprint. Using the predictions of the network itself as a descriptor for assessing visual similarity, we define a partitioning of the label space into groups of visually similar entities. We then augment the network with auxilliary hidden layer pathways with connec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.6563","kind":"arxiv","version":2},"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":"1412.6563","created_at":"2026-05-18T02:18:58.221584+00:00"},{"alias_kind":"arxiv_version","alias_value":"1412.6563v2","created_at":"2026-05-18T02:18:58.221584+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.6563","created_at":"2026-05-18T02:18:58.221584+00:00"},{"alias_kind":"pith_short_12","alias_value":"NCCRXVO6FZG6","created_at":"2026-05-18T12:28:41.024544+00:00"},{"alias_kind":"pith_short_16","alias_value":"NCCRXVO6FZG66XB2","created_at":"2026-05-18T12:28:41.024544+00:00"},{"alias_kind":"pith_short_8","alias_value":"NCCRXVO6","created_at":"2026-05-18T12:28:41.024544+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/NCCRXVO6FZG66XB2INGL63Y5RV","json":"https://pith.science/pith/NCCRXVO6FZG66XB2INGL63Y5RV.json","graph_json":"https://pith.science/api/pith-number/NCCRXVO6FZG66XB2INGL63Y5RV/graph.json","events_json":"https://pith.science/api/pith-number/NCCRXVO6FZG66XB2INGL63Y5RV/events.json","paper":"https://pith.science/paper/NCCRXVO6"},"agent_actions":{"view_html":"https://pith.science/pith/NCCRXVO6FZG66XB2INGL63Y5RV","download_json":"https://pith.science/pith/NCCRXVO6FZG66XB2INGL63Y5RV.json","view_paper":"https://pith.science/paper/NCCRXVO6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1412.6563&json=true","fetch_graph":"https://pith.science/api/pith-number/NCCRXVO6FZG66XB2INGL63Y5RV/graph.json","fetch_events":"https://pith.science/api/pith-number/NCCRXVO6FZG66XB2INGL63Y5RV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NCCRXVO6FZG66XB2INGL63Y5RV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NCCRXVO6FZG66XB2INGL63Y5RV/action/storage_attestation","attest_author":"https://pith.science/pith/NCCRXVO6FZG66XB2INGL63Y5RV/action/author_attestation","sign_citation":"https://pith.science/pith/NCCRXVO6FZG66XB2INGL63Y5RV/action/citation_signature","submit_replication":"https://pith.science/pith/NCCRXVO6FZG66XB2INGL63Y5RV/action/replication_record"}},"created_at":"2026-05-18T02:18:58.221584+00:00","updated_at":"2026-05-18T02:18:58.221584+00:00"}