{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:TWNMIZM6MDE2AHEXI3OZA3RJRA","short_pith_number":"pith:TWNMIZM6","schema_version":"1.0","canonical_sha256":"9d9ac4659e60c9a01c9746dd906e29883b39fd591519c87229f16112ca160b44","source":{"kind":"arxiv","id":"1403.1349","version":2},"attestation_state":"computed","paper":{"title":"Learning Soft Linear Constraints with Application to Citation Field Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DL","cs.IR"],"primary_cat":"cs.CL","authors_text":"Alexandre Passos, Andrew McCallum, David Belanger, Sam Anzaroot","submitted_at":"2014-03-06T05:24:02Z","abstract_excerpt":"Accurately segmenting a citation string into fields for authors, titles, etc. is a challenging task because the output typically obeys various global constraints. Previous work has shown that modeling soft constraints, where the model is encouraged, but not require to obey the constraints, can substantially improve segmentation performance. On the other hand, for imposing hard constraints, dual decomposition is a popular technique for efficient prediction given existing algorithms for unconstrained inference. We extend the technique to perform prediction subject to soft constraints. Moreover, "},"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":"1403.1349","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-03-06T05:24:02Z","cross_cats_sorted":["cs.DL","cs.IR"],"title_canon_sha256":"ca827ee163d076cb1dbe6540134f19cd1c3fb4c9a0d88b3ec7648b08edb81d5e","abstract_canon_sha256":"842130cb89a6fce68baaa521bdb7d3704d0de0f1186538f58d643802ac1fe989"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:39:55.610310Z","signature_b64":"KLsuvM5/j/9rlX9LmozfKQ9ttT75r3jCsw7TriArBg7SsJfK5PGs3QhtCcObuWHBYKBo9HTAS0+wRyuZFpoCCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d9ac4659e60c9a01c9746dd906e29883b39fd591519c87229f16112ca160b44","last_reissued_at":"2026-05-18T02:39:55.609869Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:39:55.609869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Soft Linear Constraints with Application to Citation Field Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DL","cs.IR"],"primary_cat":"cs.CL","authors_text":"Alexandre Passos, Andrew McCallum, David Belanger, Sam Anzaroot","submitted_at":"2014-03-06T05:24:02Z","abstract_excerpt":"Accurately segmenting a citation string into fields for authors, titles, etc. is a challenging task because the output typically obeys various global constraints. Previous work has shown that modeling soft constraints, where the model is encouraged, but not require to obey the constraints, can substantially improve segmentation performance. On the other hand, for imposing hard constraints, dual decomposition is a popular technique for efficient prediction given existing algorithms for unconstrained inference. We extend the technique to perform prediction subject to soft constraints. Moreover, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1403.1349","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":"1403.1349","created_at":"2026-05-18T02:39:55.609941+00:00"},{"alias_kind":"arxiv_version","alias_value":"1403.1349v2","created_at":"2026-05-18T02:39:55.609941+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1403.1349","created_at":"2026-05-18T02:39:55.609941+00:00"},{"alias_kind":"pith_short_12","alias_value":"TWNMIZM6MDE2","created_at":"2026-05-18T12:28:52.271510+00:00"},{"alias_kind":"pith_short_16","alias_value":"TWNMIZM6MDE2AHEX","created_at":"2026-05-18T12:28:52.271510+00:00"},{"alias_kind":"pith_short_8","alias_value":"TWNMIZM6","created_at":"2026-05-18T12:28:52.271510+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2605.23192","citing_title":"Occlusion-Aware Physics-Semantic Keyframe Selection for Robust Video Editing","ref_index":91,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21479","citing_title":"WikiVQABench: A Knowledge-Grounded Visual Question Answering Benchmark from Wikipedia and Wikidata","ref_index":91,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20646","citing_title":"DisImpact: Quantifying the Physi-Social Impact of Natural Disasters Through Social Media","ref_index":93,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16294","citing_title":"Are Researchers Being Replaced by Artificial Intelligence?","ref_index":99,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16813","citing_title":"QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning","ref_index":97,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08583","citing_title":"Source or It Didn't Happen: A Multi-Agent Framework for Citation Hallucination Detection","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04524","citing_title":"High-Fidelity Single-Image Head Modeling with Industry-Grade Topology","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00658","citing_title":"UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors","ref_index":243,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17325","citing_title":"Align Documents to Questions: Question-Oriented Document Rewriting for Retrieval-Augmented Generation","ref_index":91,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TWNMIZM6MDE2AHEXI3OZA3RJRA","json":"https://pith.science/pith/TWNMIZM6MDE2AHEXI3OZA3RJRA.json","graph_json":"https://pith.science/api/pith-number/TWNMIZM6MDE2AHEXI3OZA3RJRA/graph.json","events_json":"https://pith.science/api/pith-number/TWNMIZM6MDE2AHEXI3OZA3RJRA/events.json","paper":"https://pith.science/paper/TWNMIZM6"},"agent_actions":{"view_html":"https://pith.science/pith/TWNMIZM6MDE2AHEXI3OZA3RJRA","download_json":"https://pith.science/pith/TWNMIZM6MDE2AHEXI3OZA3RJRA.json","view_paper":"https://pith.science/paper/TWNMIZM6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1403.1349&json=true","fetch_graph":"https://pith.science/api/pith-number/TWNMIZM6MDE2AHEXI3OZA3RJRA/graph.json","fetch_events":"https://pith.science/api/pith-number/TWNMIZM6MDE2AHEXI3OZA3RJRA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TWNMIZM6MDE2AHEXI3OZA3RJRA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TWNMIZM6MDE2AHEXI3OZA3RJRA/action/storage_attestation","attest_author":"https://pith.science/pith/TWNMIZM6MDE2AHEXI3OZA3RJRA/action/author_attestation","sign_citation":"https://pith.science/pith/TWNMIZM6MDE2AHEXI3OZA3RJRA/action/citation_signature","submit_replication":"https://pith.science/pith/TWNMIZM6MDE2AHEXI3OZA3RJRA/action/replication_record"}},"created_at":"2026-05-18T02:39:55.609941+00:00","updated_at":"2026-05-18T02:39:55.609941+00:00"}