{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7MI7NGIMYMXO62WEQIWD2KQQRU","short_pith_number":"pith:7MI7NGIM","schema_version":"1.0","canonical_sha256":"fb11f6990cc32eef6ac4822c3d2a108d0d9457e30e4dc0c497bda64ce693e0e8","source":{"kind":"arxiv","id":"2501.07723","version":1},"attestation_state":"computed","paper":{"title":"ESURF: Simple and Effective EDU Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Mohammadreza Sediqin, Shlomo Engelson Argamon","submitted_at":"2025-01-13T22:18:52Z","abstract_excerpt":"Segmenting text into Elemental Discourse Units (EDUs) is a fundamental task in discourse parsing. We present a new simple method for identifying EDU boundaries, and hence segmenting them, based on lexical and character n-gram features, using random forest classification. We show that the method, despite its simplicity, outperforms other methods both for segmentation and within a state of the art discourse parser. This indicates the importance of such features for identifying basic discourse elements, pointing towards potentially more training-efficient methods for discourse analysis."},"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":"2501.07723","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-13T22:18:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ddf8d2048bc841f67233e690d7a4028464224eecd8008bdca5715f85c23c12c7","abstract_canon_sha256":"51e2e9bf3ecaabc5d5a05c6439238520564c9de6c99a62cec10bc249f994d4b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:49.109911Z","signature_b64":"4z1N7VMYV/ha+xFCRkTRsGEbjVj0uJuE0g2hiH1p4EK9MZGT/g4AgF31lTwD3MAAxHmSsR/UMiKRNAv6unvcDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb11f6990cc32eef6ac4822c3d2a108d0d9457e30e4dc0c497bda64ce693e0e8","last_reissued_at":"2026-07-05T10:00:49.109522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:49.109522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ESURF: Simple and Effective EDU Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Mohammadreza Sediqin, Shlomo Engelson Argamon","submitted_at":"2025-01-13T22:18:52Z","abstract_excerpt":"Segmenting text into Elemental Discourse Units (EDUs) is a fundamental task in discourse parsing. We present a new simple method for identifying EDU boundaries, and hence segmenting them, based on lexical and character n-gram features, using random forest classification. We show that the method, despite its simplicity, outperforms other methods both for segmentation and within a state of the art discourse parser. This indicates the importance of such features for identifying basic discourse elements, pointing towards potentially more training-efficient methods for discourse analysis."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07723","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/2501.07723/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":"2501.07723","created_at":"2026-07-05T10:00:49.109567+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.07723v1","created_at":"2026-07-05T10:00:49.109567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07723","created_at":"2026-07-05T10:00:49.109567+00:00"},{"alias_kind":"pith_short_12","alias_value":"7MI7NGIMYMXO","created_at":"2026-07-05T10:00:49.109567+00:00"},{"alias_kind":"pith_short_16","alias_value":"7MI7NGIMYMXO62WE","created_at":"2026-07-05T10:00:49.109567+00:00"},{"alias_kind":"pith_short_8","alias_value":"7MI7NGIM","created_at":"2026-07-05T10:00:49.109567+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/7MI7NGIMYMXO62WEQIWD2KQQRU","json":"https://pith.science/pith/7MI7NGIMYMXO62WEQIWD2KQQRU.json","graph_json":"https://pith.science/api/pith-number/7MI7NGIMYMXO62WEQIWD2KQQRU/graph.json","events_json":"https://pith.science/api/pith-number/7MI7NGIMYMXO62WEQIWD2KQQRU/events.json","paper":"https://pith.science/paper/7MI7NGIM"},"agent_actions":{"view_html":"https://pith.science/pith/7MI7NGIMYMXO62WEQIWD2KQQRU","download_json":"https://pith.science/pith/7MI7NGIMYMXO62WEQIWD2KQQRU.json","view_paper":"https://pith.science/paper/7MI7NGIM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.07723&json=true","fetch_graph":"https://pith.science/api/pith-number/7MI7NGIMYMXO62WEQIWD2KQQRU/graph.json","fetch_events":"https://pith.science/api/pith-number/7MI7NGIMYMXO62WEQIWD2KQQRU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7MI7NGIMYMXO62WEQIWD2KQQRU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7MI7NGIMYMXO62WEQIWD2KQQRU/action/storage_attestation","attest_author":"https://pith.science/pith/7MI7NGIMYMXO62WEQIWD2KQQRU/action/author_attestation","sign_citation":"https://pith.science/pith/7MI7NGIMYMXO62WEQIWD2KQQRU/action/citation_signature","submit_replication":"https://pith.science/pith/7MI7NGIMYMXO62WEQIWD2KQQRU/action/replication_record"}},"created_at":"2026-07-05T10:00:49.109567+00:00","updated_at":"2026-07-05T10:00:49.109567+00:00"}