{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CMHD3Z6DE2KVATSNVLLPFIXFMU","short_pith_number":"pith:CMHD3Z6D","schema_version":"1.0","canonical_sha256":"130e3de7c32695504e4daad6f2a2e5651cb27cfaae5ea1e8f2f1efe814faebcf","source":{"kind":"arxiv","id":"2411.16613","version":1},"attestation_state":"computed","paper":{"title":"Recent Trends in Linear Text Segmentation: a Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Newell, Iacopo Ghinassi, Lin Wang, Matthew Purver","submitted_at":"2024-11-25T17:48:59Z","abstract_excerpt":"Linear Text Segmentation is the task of automatically tagging text documents with topic shifts, i.e. the places in the text where the topics change. A well-established area of research in Natural Language Processing, drawing from well-understood concepts in linguistic and computational linguistic research, the field has recently seen a lot of interest as a result of the surge of text, video, and audio available on the web, which in turn require ways of summarising and categorizing the mole of content for which linear text segmentation is a fundamental step. In this survey, we provide an extens"},"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":"2411.16613","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-25T17:48:59Z","cross_cats_sorted":[],"title_canon_sha256":"2cda975aef00d64fb90e03215951e3f69885d8cf8d47dc954da7bbbaacded149","abstract_canon_sha256":"76123d7698c6e8fdf872683fae699b62de3d05c184d6946223d566f0171b908d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:11.852333Z","signature_b64":"BVqWpTaUoOjNUPew8GS2MYWrIeW9GQEorq1C7fesztEJTmzKLgY3zQNa3iv53XH/hgl7BuKYc83j4VaOgQFOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"130e3de7c32695504e4daad6f2a2e5651cb27cfaae5ea1e8f2f1efe814faebcf","last_reissued_at":"2026-07-05T09:40:11.851894Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:11.851894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recent Trends in Linear Text Segmentation: a Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Newell, Iacopo Ghinassi, Lin Wang, Matthew Purver","submitted_at":"2024-11-25T17:48:59Z","abstract_excerpt":"Linear Text Segmentation is the task of automatically tagging text documents with topic shifts, i.e. the places in the text where the topics change. A well-established area of research in Natural Language Processing, drawing from well-understood concepts in linguistic and computational linguistic research, the field has recently seen a lot of interest as a result of the surge of text, video, and audio available on the web, which in turn require ways of summarising and categorizing the mole of content for which linear text segmentation is a fundamental step. In this survey, we provide an extens"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16613","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/2411.16613/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":"2411.16613","created_at":"2026-07-05T09:40:11.851956+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16613v1","created_at":"2026-07-05T09:40:11.851956+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16613","created_at":"2026-07-05T09:40:11.851956+00:00"},{"alias_kind":"pith_short_12","alias_value":"CMHD3Z6DE2KV","created_at":"2026-07-05T09:40:11.851956+00:00"},{"alias_kind":"pith_short_16","alias_value":"CMHD3Z6DE2KVATSN","created_at":"2026-07-05T09:40:11.851956+00:00"},{"alias_kind":"pith_short_8","alias_value":"CMHD3Z6D","created_at":"2026-07-05T09:40:11.851956+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.17277","citing_title":"Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation","ref_index":105,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CMHD3Z6DE2KVATSNVLLPFIXFMU","json":"https://pith.science/pith/CMHD3Z6DE2KVATSNVLLPFIXFMU.json","graph_json":"https://pith.science/api/pith-number/CMHD3Z6DE2KVATSNVLLPFIXFMU/graph.json","events_json":"https://pith.science/api/pith-number/CMHD3Z6DE2KVATSNVLLPFIXFMU/events.json","paper":"https://pith.science/paper/CMHD3Z6D"},"agent_actions":{"view_html":"https://pith.science/pith/CMHD3Z6DE2KVATSNVLLPFIXFMU","download_json":"https://pith.science/pith/CMHD3Z6DE2KVATSNVLLPFIXFMU.json","view_paper":"https://pith.science/paper/CMHD3Z6D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16613&json=true","fetch_graph":"https://pith.science/api/pith-number/CMHD3Z6DE2KVATSNVLLPFIXFMU/graph.json","fetch_events":"https://pith.science/api/pith-number/CMHD3Z6DE2KVATSNVLLPFIXFMU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CMHD3Z6DE2KVATSNVLLPFIXFMU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CMHD3Z6DE2KVATSNVLLPFIXFMU/action/storage_attestation","attest_author":"https://pith.science/pith/CMHD3Z6DE2KVATSNVLLPFIXFMU/action/author_attestation","sign_citation":"https://pith.science/pith/CMHD3Z6DE2KVATSNVLLPFIXFMU/action/citation_signature","submit_replication":"https://pith.science/pith/CMHD3Z6DE2KVATSNVLLPFIXFMU/action/replication_record"}},"created_at":"2026-07-05T09:40:11.851956+00:00","updated_at":"2026-07-05T09:40:11.851956+00:00"}