{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:W4N3MTT7LCWSIG3SMTPXCRYVMS","short_pith_number":"pith:W4N3MTT7","schema_version":"1.0","canonical_sha256":"b71bb64e7f58ad241b7264df71471564bfec3cdd8b9ea1490cfb3eb42fc71095","source":{"kind":"arxiv","id":"1511.08411","version":1},"attestation_state":"computed","paper":{"title":"OntoSeg: a Novel Approach to Text Segmentation using Ontological Similarity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Killian Levacher, Mostafa Bayomi, M. Rami Ghorab, S\\'eamus Lawless","submitted_at":"2015-11-26T15:10:18Z","abstract_excerpt":"Text segmentation (TS) aims at dividing long text into coherent segments which reflect the subtopic structure of the text. It is beneficial to many natural language processing tasks, such as Information Retrieval (IR) and document summarisation. Current approaches to text segmentation are similar in that they all use word-frequency metrics to measure the similarity between two regions of text, so that a document is segmented based on the lexical cohesion between its words. Various NLP tasks are now moving towards the semantic web and ontologies, such as ontology-based IR systems, to capture th"},"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":"1511.08411","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-11-26T15:10:18Z","cross_cats_sorted":[],"title_canon_sha256":"21efe8f90b75b2b3b48006f8fcca2bfc79705acfadba3c64386315453b05c2d8","abstract_canon_sha256":"aab08eccd3e7bb716a04e12db40719c39b383a1a2e41d81607eb1f31efada710"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:25:54.139499Z","signature_b64":"hyPs2ozuuBMgCwUnlGyJ0mfg2Lr2llZxiDaqS68Usg4FO7s9vMG1g2DYTK/nS2yT2Wst+C5uFDpP9O3sAKPoAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b71bb64e7f58ad241b7264df71471564bfec3cdd8b9ea1490cfb3eb42fc71095","last_reissued_at":"2026-05-18T01:25:54.138577Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:25:54.138577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OntoSeg: a Novel Approach to Text Segmentation using Ontological Similarity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Killian Levacher, Mostafa Bayomi, M. Rami Ghorab, S\\'eamus Lawless","submitted_at":"2015-11-26T15:10:18Z","abstract_excerpt":"Text segmentation (TS) aims at dividing long text into coherent segments which reflect the subtopic structure of the text. It is beneficial to many natural language processing tasks, such as Information Retrieval (IR) and document summarisation. Current approaches to text segmentation are similar in that they all use word-frequency metrics to measure the similarity between two regions of text, so that a document is segmented based on the lexical cohesion between its words. Various NLP tasks are now moving towards the semantic web and ontologies, such as ontology-based IR systems, to capture th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.08411","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":"1511.08411","created_at":"2026-05-18T01:25:54.138729+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.08411v1","created_at":"2026-05-18T01:25:54.138729+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.08411","created_at":"2026-05-18T01:25:54.138729+00:00"},{"alias_kind":"pith_short_12","alias_value":"W4N3MTT7LCWS","created_at":"2026-05-18T12:29:47.479230+00:00"},{"alias_kind":"pith_short_16","alias_value":"W4N3MTT7LCWSIG3S","created_at":"2026-05-18T12:29:47.479230+00:00"},{"alias_kind":"pith_short_8","alias_value":"W4N3MTT7","created_at":"2026-05-18T12:29:47.479230+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/W4N3MTT7LCWSIG3SMTPXCRYVMS","json":"https://pith.science/pith/W4N3MTT7LCWSIG3SMTPXCRYVMS.json","graph_json":"https://pith.science/api/pith-number/W4N3MTT7LCWSIG3SMTPXCRYVMS/graph.json","events_json":"https://pith.science/api/pith-number/W4N3MTT7LCWSIG3SMTPXCRYVMS/events.json","paper":"https://pith.science/paper/W4N3MTT7"},"agent_actions":{"view_html":"https://pith.science/pith/W4N3MTT7LCWSIG3SMTPXCRYVMS","download_json":"https://pith.science/pith/W4N3MTT7LCWSIG3SMTPXCRYVMS.json","view_paper":"https://pith.science/paper/W4N3MTT7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.08411&json=true","fetch_graph":"https://pith.science/api/pith-number/W4N3MTT7LCWSIG3SMTPXCRYVMS/graph.json","fetch_events":"https://pith.science/api/pith-number/W4N3MTT7LCWSIG3SMTPXCRYVMS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W4N3MTT7LCWSIG3SMTPXCRYVMS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W4N3MTT7LCWSIG3SMTPXCRYVMS/action/storage_attestation","attest_author":"https://pith.science/pith/W4N3MTT7LCWSIG3SMTPXCRYVMS/action/author_attestation","sign_citation":"https://pith.science/pith/W4N3MTT7LCWSIG3SMTPXCRYVMS/action/citation_signature","submit_replication":"https://pith.science/pith/W4N3MTT7LCWSIG3SMTPXCRYVMS/action/replication_record"}},"created_at":"2026-05-18T01:25:54.138729+00:00","updated_at":"2026-05-18T01:25:54.138729+00:00"}