{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:RYS2UIXOGBEBGKJ4GWBJ6IIYJN","short_pith_number":"pith:RYS2UIXO","schema_version":"1.0","canonical_sha256":"8e25aa22ee304813293c35829f21184b6738dcce133edbdec66a5e3035e435ff","source":{"kind":"arxiv","id":"1707.08608","version":3},"attestation_state":"computed","paper":{"title":"Gradient-based Inference for Networks with Output Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jaime Carbonell, Jay Yoon Lee, Jean-Baptiste Tristan, Michael Wick, Sanket Vaibhav Mehta","submitted_at":"2017-07-26T19:00:10Z","abstract_excerpt":"Practitioners apply neural networks to increasingly complex problems in natural language processing, such as syntactic parsing and semantic role labeling that have rich output structures. Many such structured-prediction problems require deterministic constraints on the output values; for example, in sequence-to-sequence syntactic parsing, we require that the sequential outputs encode valid trees. While hidden units might capture such properties, the network is not always able to learn such constraints from the training data alone, and practitioners must then resort to post-processing. 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":"1707.08608","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-26T19:00:10Z","cross_cats_sorted":[],"title_canon_sha256":"2ea0b05df66190a62a37cf04326e8d2d81a81c5ee493cfa1e7f589fdddab85b4","abstract_canon_sha256":"503c04c5317331544819bc1d0caef0a03d59fd50c064152fe4c7b7f2968801b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:06.905211Z","signature_b64":"1CsmGlI0+TxnM5Yz8QDFhDotW63ok4kQeELzINNU/ANhS6XHxqryKCBsnQ2lvO8SALui2sB9jrxLjdDh8EylDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e25aa22ee304813293c35829f21184b6738dcce133edbdec66a5e3035e435ff","last_reissued_at":"2026-05-17T23:48:06.904801Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:06.904801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient-based Inference for Networks with Output Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jaime Carbonell, Jay Yoon Lee, Jean-Baptiste Tristan, Michael Wick, Sanket Vaibhav Mehta","submitted_at":"2017-07-26T19:00:10Z","abstract_excerpt":"Practitioners apply neural networks to increasingly complex problems in natural language processing, such as syntactic parsing and semantic role labeling that have rich output structures. Many such structured-prediction problems require deterministic constraints on the output values; for example, in sequence-to-sequence syntactic parsing, we require that the sequential outputs encode valid trees. While hidden units might capture such properties, the network is not always able to learn such constraints from the training data alone, and practitioners must then resort to post-processing. In this "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.08608","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":"1707.08608","created_at":"2026-05-17T23:48:06.904862+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.08608v3","created_at":"2026-05-17T23:48:06.904862+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.08608","created_at":"2026-05-17T23:48:06.904862+00:00"},{"alias_kind":"pith_short_12","alias_value":"RYS2UIXOGBEB","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_16","alias_value":"RYS2UIXOGBEBGKJ4","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_8","alias_value":"RYS2UIXO","created_at":"2026-05-18T12:31:43.269735+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/RYS2UIXOGBEBGKJ4GWBJ6IIYJN","json":"https://pith.science/pith/RYS2UIXOGBEBGKJ4GWBJ6IIYJN.json","graph_json":"https://pith.science/api/pith-number/RYS2UIXOGBEBGKJ4GWBJ6IIYJN/graph.json","events_json":"https://pith.science/api/pith-number/RYS2UIXOGBEBGKJ4GWBJ6IIYJN/events.json","paper":"https://pith.science/paper/RYS2UIXO"},"agent_actions":{"view_html":"https://pith.science/pith/RYS2UIXOGBEBGKJ4GWBJ6IIYJN","download_json":"https://pith.science/pith/RYS2UIXOGBEBGKJ4GWBJ6IIYJN.json","view_paper":"https://pith.science/paper/RYS2UIXO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.08608&json=true","fetch_graph":"https://pith.science/api/pith-number/RYS2UIXOGBEBGKJ4GWBJ6IIYJN/graph.json","fetch_events":"https://pith.science/api/pith-number/RYS2UIXOGBEBGKJ4GWBJ6IIYJN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RYS2UIXOGBEBGKJ4GWBJ6IIYJN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RYS2UIXOGBEBGKJ4GWBJ6IIYJN/action/storage_attestation","attest_author":"https://pith.science/pith/RYS2UIXOGBEBGKJ4GWBJ6IIYJN/action/author_attestation","sign_citation":"https://pith.science/pith/RYS2UIXOGBEBGKJ4GWBJ6IIYJN/action/citation_signature","submit_replication":"https://pith.science/pith/RYS2UIXOGBEBGKJ4GWBJ6IIYJN/action/replication_record"}},"created_at":"2026-05-17T23:48:06.904862+00:00","updated_at":"2026-05-17T23:48:06.904862+00:00"}