{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DJWVQ6NVU4CQYTRWFDIZLQJCBS","short_pith_number":"pith:DJWVQ6NV","schema_version":"1.0","canonical_sha256":"1a6d5879b5a7050c4e3628d195c1220c89eaf1def53f5f3d12a67dc1e5d1ac63","source":{"kind":"arxiv","id":"2104.13933","version":1},"attestation_state":"computed","paper":{"title":"Learning Syntax from Naturally-Occurring Bracketings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Igor Malioutov, Lillian Lee, Ozan \\.Irsoy, Tianze Shi","submitted_at":"2021-04-28T18:00:02Z","abstract_excerpt":"Naturally-occurring bracketings, such as answer fragments to natural language questions and hyperlinks on webpages, can reflect human syntactic intuition regarding phrasal boundaries. Their availability and approximate correspondence to syntax make them appealing as distant information sources to incorporate into unsupervised constituency parsing. But they are noisy and incomplete; to address this challenge, we develop a partial-brackets-aware structured ramp loss in learning. Experiments demonstrate that our distantly-supervised models trained on naturally-occurring bracketing data are more a"},"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":"2104.13933","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-28T18:00:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c108d4490ebf275c5eaa14ae9ab74076616a0577e404acc43b719b02d60373cf","abstract_canon_sha256":"8315c325bb85edd0adf01cdb7836b215c6c89d9ad0dc1b6308d04cec06700357"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:36:11.351750Z","signature_b64":"mS7OB8pkmTzhpN2LhBQIbW7e39cFwtANCaQ71tvY6yWRAReat/jYZ9Xob5dpDyw230oSsO07Jgyl3FRNFbsGCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a6d5879b5a7050c4e3628d195c1220c89eaf1def53f5f3d12a67dc1e5d1ac63","last_reissued_at":"2026-07-05T02:36:11.351328Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:36:11.351328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Syntax from Naturally-Occurring Bracketings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Igor Malioutov, Lillian Lee, Ozan \\.Irsoy, Tianze Shi","submitted_at":"2021-04-28T18:00:02Z","abstract_excerpt":"Naturally-occurring bracketings, such as answer fragments to natural language questions and hyperlinks on webpages, can reflect human syntactic intuition regarding phrasal boundaries. Their availability and approximate correspondence to syntax make them appealing as distant information sources to incorporate into unsupervised constituency parsing. But they are noisy and incomplete; to address this challenge, we develop a partial-brackets-aware structured ramp loss in learning. Experiments demonstrate that our distantly-supervised models trained on naturally-occurring bracketing data are more a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.13933","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2104.13933/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2104.13933","created_at":"2026-07-05T02:36:11.351389+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.13933v1","created_at":"2026-07-05T02:36:11.351389+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.13933","created_at":"2026-07-05T02:36:11.351389+00:00"},{"alias_kind":"pith_short_12","alias_value":"DJWVQ6NVU4CQ","created_at":"2026-07-05T02:36:11.351389+00:00"},{"alias_kind":"pith_short_16","alias_value":"DJWVQ6NVU4CQYTRW","created_at":"2026-07-05T02:36:11.351389+00:00"},{"alias_kind":"pith_short_8","alias_value":"DJWVQ6NV","created_at":"2026-07-05T02:36:11.351389+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/DJWVQ6NVU4CQYTRWFDIZLQJCBS","json":"https://pith.science/pith/DJWVQ6NVU4CQYTRWFDIZLQJCBS.json","graph_json":"https://pith.science/api/pith-number/DJWVQ6NVU4CQYTRWFDIZLQJCBS/graph.json","events_json":"https://pith.science/api/pith-number/DJWVQ6NVU4CQYTRWFDIZLQJCBS/events.json","paper":"https://pith.science/paper/DJWVQ6NV"},"agent_actions":{"view_html":"https://pith.science/pith/DJWVQ6NVU4CQYTRWFDIZLQJCBS","download_json":"https://pith.science/pith/DJWVQ6NVU4CQYTRWFDIZLQJCBS.json","view_paper":"https://pith.science/paper/DJWVQ6NV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.13933&json=true","fetch_graph":"https://pith.science/api/pith-number/DJWVQ6NVU4CQYTRWFDIZLQJCBS/graph.json","fetch_events":"https://pith.science/api/pith-number/DJWVQ6NVU4CQYTRWFDIZLQJCBS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DJWVQ6NVU4CQYTRWFDIZLQJCBS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DJWVQ6NVU4CQYTRWFDIZLQJCBS/action/storage_attestation","attest_author":"https://pith.science/pith/DJWVQ6NVU4CQYTRWFDIZLQJCBS/action/author_attestation","sign_citation":"https://pith.science/pith/DJWVQ6NVU4CQYTRWFDIZLQJCBS/action/citation_signature","submit_replication":"https://pith.science/pith/DJWVQ6NVU4CQYTRWFDIZLQJCBS/action/replication_record"}},"created_at":"2026-07-05T02:36:11.351389+00:00","updated_at":"2026-07-05T02:36:11.351389+00:00"}