{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:RDNDAKLSGJJ7I5MMYSMYGILESD","short_pith_number":"pith:RDNDAKLS","schema_version":"1.0","canonical_sha256":"88da3029723253f4758cc49983216490f742884813822420cc69010368a9dbd0","source":{"kind":"arxiv","id":"1511.06350","version":3},"attestation_state":"computed","paper":{"title":"Structured Prediction Energy Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew McCallum, David Belanger","submitted_at":"2015-11-19T20:39:59Z","abstract_excerpt":"We introduce structured prediction energy networks (SPENs), a flexible framework for structured prediction. A deep architecture is used to define an energy function of candidate labels, and then predictions are produced by using back-propagation to iteratively optimize the energy with respect to the labels. This deep architecture captures dependencies between labels that would lead to intractable graphical models, and performs structure learning by automatically learning discriminative features of the structured output. One natural application of our technique is multi-label classification, wh"},"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":"1511.06350","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T20:39:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1549991a47463746dcc67d9a6531c1883071b2960c8ee2ca41f1f5d32d2375ab","abstract_canon_sha256":"3efd2ba9d961ea976ac48c59faf413780e1000bb83e9d4d976532b73d204144e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:05:12.659790Z","signature_b64":"lbdK8rBMMgPFaa7mMvrGdiqHJLaI9lJ+IAW90crs3gtxC7sREPTWIBR7bQ8KzjDf6sV/LEWhYHJU4LNO/H/GBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88da3029723253f4758cc49983216490f742884813822420cc69010368a9dbd0","last_reissued_at":"2026-05-18T01:05:12.659098Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:05:12.659098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structured Prediction Energy Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew McCallum, David Belanger","submitted_at":"2015-11-19T20:39:59Z","abstract_excerpt":"We introduce structured prediction energy networks (SPENs), a flexible framework for structured prediction. A deep architecture is used to define an energy function of candidate labels, and then predictions are produced by using back-propagation to iteratively optimize the energy with respect to the labels. This deep architecture captures dependencies between labels that would lead to intractable graphical models, and performs structure learning by automatically learning discriminative features of the structured output. One natural application of our technique is multi-label classification, wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06350","kind":"arxiv","version":3},"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":"1511.06350","created_at":"2026-05-18T01:05:12.659197+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.06350v3","created_at":"2026-05-18T01:05:12.659197+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06350","created_at":"2026-05-18T01:05:12.659197+00:00"},{"alias_kind":"pith_short_12","alias_value":"RDNDAKLSGJJ7","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_16","alias_value":"RDNDAKLSGJJ7I5MM","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_8","alias_value":"RDNDAKLS","created_at":"2026-05-18T12:29:39.896362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.20713","citing_title":"SAVER: Selective As-Needed Vision Evidence for Multimodal Information Extraction","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RDNDAKLSGJJ7I5MMYSMYGILESD","json":"https://pith.science/pith/RDNDAKLSGJJ7I5MMYSMYGILESD.json","graph_json":"https://pith.science/api/pith-number/RDNDAKLSGJJ7I5MMYSMYGILESD/graph.json","events_json":"https://pith.science/api/pith-number/RDNDAKLSGJJ7I5MMYSMYGILESD/events.json","paper":"https://pith.science/paper/RDNDAKLS"},"agent_actions":{"view_html":"https://pith.science/pith/RDNDAKLSGJJ7I5MMYSMYGILESD","download_json":"https://pith.science/pith/RDNDAKLSGJJ7I5MMYSMYGILESD.json","view_paper":"https://pith.science/paper/RDNDAKLS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.06350&json=true","fetch_graph":"https://pith.science/api/pith-number/RDNDAKLSGJJ7I5MMYSMYGILESD/graph.json","fetch_events":"https://pith.science/api/pith-number/RDNDAKLSGJJ7I5MMYSMYGILESD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RDNDAKLSGJJ7I5MMYSMYGILESD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RDNDAKLSGJJ7I5MMYSMYGILESD/action/storage_attestation","attest_author":"https://pith.science/pith/RDNDAKLSGJJ7I5MMYSMYGILESD/action/author_attestation","sign_citation":"https://pith.science/pith/RDNDAKLSGJJ7I5MMYSMYGILESD/action/citation_signature","submit_replication":"https://pith.science/pith/RDNDAKLSGJJ7I5MMYSMYGILESD/action/replication_record"}},"created_at":"2026-05-18T01:05:12.659197+00:00","updated_at":"2026-05-18T01:05:12.659197+00:00"}