{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:R76CPQVG33RMVWS5OJYT4GQQGB","short_pith_number":"pith:R76CPQVG","schema_version":"1.0","canonical_sha256":"8ffc27c2a6dee2cada5d72713e1a10306a783219719b3874f0a7b980a6682e9d","source":{"kind":"arxiv","id":"1804.02009","version":1},"attestation_state":"computed","paper":{"title":"Regularizing Deep Networks by Modeling and Predicting Label Structure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gregory Shakhnarovich, Michael Maire, Mohammadreza Mostajabi","submitted_at":"2018-04-05T18:17:18Z","abstract_excerpt":"We construct custom regularization functions for use in supervised training of deep neural networks. Our technique is applicable when the ground-truth labels themselves exhibit internal structure; we derive a regularizer by learning an autoencoder over the set of annotations. Training thereby becomes a two-phase procedure. The first phase models labels with an autoencoder. The second phase trains the actual network of interest by attaching an auxiliary branch that must predict output via a hidden layer of the autoencoder. After training, we discard this auxiliary branch.\n  We experiment in the"},"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":"1804.02009","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-05T18:17:18Z","cross_cats_sorted":[],"title_canon_sha256":"8c04c66df4f59b498000d4f8f9ac2bf9c2c40ce905aca8407cc3579b3f819704","abstract_canon_sha256":"5f69c00a0de2656b866b3f86cb3aedb1aa52d178e67388d253ab57b3e07cb2ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:08.092659Z","signature_b64":"8LKH2urpjkvlHBVFgwYfevTNBR8ttRDaxt/keSY1IawUx+EQhhuWFX13qUYHoZTN4/ii5GxugI5d7pRZ+kMxBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ffc27c2a6dee2cada5d72713e1a10306a783219719b3874f0a7b980a6682e9d","last_reissued_at":"2026-05-18T00:19:08.091909Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:08.091909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Regularizing Deep Networks by Modeling and Predicting Label Structure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gregory Shakhnarovich, Michael Maire, Mohammadreza Mostajabi","submitted_at":"2018-04-05T18:17:18Z","abstract_excerpt":"We construct custom regularization functions for use in supervised training of deep neural networks. Our technique is applicable when the ground-truth labels themselves exhibit internal structure; we derive a regularizer by learning an autoencoder over the set of annotations. Training thereby becomes a two-phase procedure. The first phase models labels with an autoencoder. The second phase trains the actual network of interest by attaching an auxiliary branch that must predict output via a hidden layer of the autoencoder. After training, we discard this auxiliary branch.\n  We experiment in the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.02009","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":"1804.02009","created_at":"2026-05-18T00:19:08.092038+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.02009v1","created_at":"2026-05-18T00:19:08.092038+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.02009","created_at":"2026-05-18T00:19:08.092038+00:00"},{"alias_kind":"pith_short_12","alias_value":"R76CPQVG33RM","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"R76CPQVG33RMVWS5","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"R76CPQVG","created_at":"2026-05-18T12:32:50.500415+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/R76CPQVG33RMVWS5OJYT4GQQGB","json":"https://pith.science/pith/R76CPQVG33RMVWS5OJYT4GQQGB.json","graph_json":"https://pith.science/api/pith-number/R76CPQVG33RMVWS5OJYT4GQQGB/graph.json","events_json":"https://pith.science/api/pith-number/R76CPQVG33RMVWS5OJYT4GQQGB/events.json","paper":"https://pith.science/paper/R76CPQVG"},"agent_actions":{"view_html":"https://pith.science/pith/R76CPQVG33RMVWS5OJYT4GQQGB","download_json":"https://pith.science/pith/R76CPQVG33RMVWS5OJYT4GQQGB.json","view_paper":"https://pith.science/paper/R76CPQVG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.02009&json=true","fetch_graph":"https://pith.science/api/pith-number/R76CPQVG33RMVWS5OJYT4GQQGB/graph.json","fetch_events":"https://pith.science/api/pith-number/R76CPQVG33RMVWS5OJYT4GQQGB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R76CPQVG33RMVWS5OJYT4GQQGB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R76CPQVG33RMVWS5OJYT4GQQGB/action/storage_attestation","attest_author":"https://pith.science/pith/R76CPQVG33RMVWS5OJYT4GQQGB/action/author_attestation","sign_citation":"https://pith.science/pith/R76CPQVG33RMVWS5OJYT4GQQGB/action/citation_signature","submit_replication":"https://pith.science/pith/R76CPQVG33RMVWS5OJYT4GQQGB/action/replication_record"}},"created_at":"2026-05-18T00:19:08.092038+00:00","updated_at":"2026-05-18T00:19:08.092038+00:00"}