{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:HVGZP4WJII6W5CBZ7FA2U4DRTU","short_pith_number":"pith:HVGZP4WJ","schema_version":"1.0","canonical_sha256":"3d4d97f2c9423d6e8839f941aa70719d1f0b13ef8148ef80aeddfb350e7ba85a","source":{"kind":"arxiv","id":"1407.8215","version":1},"attestation_state":"computed","paper":{"title":"Two-pass Discourse Segmentation with Pairing and Global Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Graeme Hirst, Vanessa Wei Feng","submitted_at":"2014-07-30T21:00:25Z","abstract_excerpt":"Previous attempts at RST-style discourse segmentation typically adopt features centered on a single token to predict whether to insert a boundary before that token. In contrast, we develop a discourse segmenter utilizing a set of pairing features, which are centered on a pair of adjacent tokens in the sentence, by equally taking into account the information from both tokens. Moreover, we propose a novel set of global features, which encode characteristics of the segmentation as a whole, once we have an initial segmentation. We show that both the pairing and global features are useful on their "},"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":"1407.8215","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-07-30T21:00:25Z","cross_cats_sorted":[],"title_canon_sha256":"62d2d20311c9df0dc1920bdadf87a5d67c2d1c1a72f56c1fc25ba8d937af21d4","abstract_canon_sha256":"0678962f9d0ae038b92f20df444421e08c0bc326fc9b527fe7dc593594931807"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:46:05.623736Z","signature_b64":"n45bo3XtkOvXSuloSW8Rg87pmb2M7IlJBCqW3LMYKXZyf0QRxK0oHJeKAZaoNOSkglWGofVBQzbL7KIiTmLxBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d4d97f2c9423d6e8839f941aa70719d1f0b13ef8148ef80aeddfb350e7ba85a","last_reissued_at":"2026-05-18T02:46:05.623293Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:46:05.623293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Two-pass Discourse Segmentation with Pairing and Global Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Graeme Hirst, Vanessa Wei Feng","submitted_at":"2014-07-30T21:00:25Z","abstract_excerpt":"Previous attempts at RST-style discourse segmentation typically adopt features centered on a single token to predict whether to insert a boundary before that token. In contrast, we develop a discourse segmenter utilizing a set of pairing features, which are centered on a pair of adjacent tokens in the sentence, by equally taking into account the information from both tokens. Moreover, we propose a novel set of global features, which encode characteristics of the segmentation as a whole, once we have an initial segmentation. We show that both the pairing and global features are useful on their "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1407.8215","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":"1407.8215","created_at":"2026-05-18T02:46:05.623366+00:00"},{"alias_kind":"arxiv_version","alias_value":"1407.8215v1","created_at":"2026-05-18T02:46:05.623366+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1407.8215","created_at":"2026-05-18T02:46:05.623366+00:00"},{"alias_kind":"pith_short_12","alias_value":"HVGZP4WJII6W","created_at":"2026-05-18T12:28:30.664211+00:00"},{"alias_kind":"pith_short_16","alias_value":"HVGZP4WJII6W5CBZ","created_at":"2026-05-18T12:28:30.664211+00:00"},{"alias_kind":"pith_short_8","alias_value":"HVGZP4WJ","created_at":"2026-05-18T12:28:30.664211+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.07723","citing_title":"ESURF: Simple and Effective EDU Segmentation","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HVGZP4WJII6W5CBZ7FA2U4DRTU","json":"https://pith.science/pith/HVGZP4WJII6W5CBZ7FA2U4DRTU.json","graph_json":"https://pith.science/api/pith-number/HVGZP4WJII6W5CBZ7FA2U4DRTU/graph.json","events_json":"https://pith.science/api/pith-number/HVGZP4WJII6W5CBZ7FA2U4DRTU/events.json","paper":"https://pith.science/paper/HVGZP4WJ"},"agent_actions":{"view_html":"https://pith.science/pith/HVGZP4WJII6W5CBZ7FA2U4DRTU","download_json":"https://pith.science/pith/HVGZP4WJII6W5CBZ7FA2U4DRTU.json","view_paper":"https://pith.science/paper/HVGZP4WJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1407.8215&json=true","fetch_graph":"https://pith.science/api/pith-number/HVGZP4WJII6W5CBZ7FA2U4DRTU/graph.json","fetch_events":"https://pith.science/api/pith-number/HVGZP4WJII6W5CBZ7FA2U4DRTU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HVGZP4WJII6W5CBZ7FA2U4DRTU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HVGZP4WJII6W5CBZ7FA2U4DRTU/action/storage_attestation","attest_author":"https://pith.science/pith/HVGZP4WJII6W5CBZ7FA2U4DRTU/action/author_attestation","sign_citation":"https://pith.science/pith/HVGZP4WJII6W5CBZ7FA2U4DRTU/action/citation_signature","submit_replication":"https://pith.science/pith/HVGZP4WJII6W5CBZ7FA2U4DRTU/action/replication_record"}},"created_at":"2026-05-18T02:46:05.623366+00:00","updated_at":"2026-05-18T02:46:05.623366+00:00"}