{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JRM33VWPSFRX7EYX5343WYEDKB","short_pith_number":"pith:JRM33VWP","schema_version":"1.0","canonical_sha256":"4c59bdd6cf91637f9317eef9bb6083507d00e7c4032001bb6d87764d5b804358","source":{"kind":"arxiv","id":"2408.00205","version":1},"attestation_state":"computed","paper":{"title":"Sentence-wise Speech Summarization: Task, Datasets, and End-to-End Modeling with LM Knowledge Distillation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Atsunori Ogawa, Kohei Matsuura, Marc Delcroix, Masato Mimura, Takafumi Moriya, Takanori Ashihara, Takatomo Kano","submitted_at":"2024-08-01T00:18:21Z","abstract_excerpt":"This paper introduces a novel approach called sentence-wise speech summarization (Sen-SSum), which generates text summaries from a spoken document in a sentence-by-sentence manner. Sen-SSum combines the real-time processing of automatic speech recognition (ASR) with the conciseness of speech summarization. To explore this approach, we present two datasets for Sen-SSum: Mega-SSum and CSJ-SSum. Using these datasets, our study evaluates two types of Transformer-based models: 1) cascade models that combine ASR and strong text summarization models, and 2) end-to-end (E2E) models that directly conve"},"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":"2408.00205","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-01T00:18:21Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"3d07660c7fe7352af2cb56978860de708c229fbd04953026dc2bfa9cbbf2269a","abstract_canon_sha256":"61b19d4423117a494a8c86dcd0de639b517eba06757ee8d4944c2d1126f79c5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:51:00.028079Z","signature_b64":"peTBrccJGUrX+raBiV3aRxIQF6CTtSCw5sBkYrl8wDIHAfVTpY+CkjRJ9JNq5HNIswy1zwdfKMLpQcKFSgUhBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c59bdd6cf91637f9317eef9bb6083507d00e7c4032001bb6d87764d5b804358","last_reissued_at":"2026-07-05T08:51:00.027618Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:51:00.027618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sentence-wise Speech Summarization: Task, Datasets, and End-to-End Modeling with LM Knowledge Distillation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Atsunori Ogawa, Kohei Matsuura, Marc Delcroix, Masato Mimura, Takafumi Moriya, Takanori Ashihara, Takatomo Kano","submitted_at":"2024-08-01T00:18:21Z","abstract_excerpt":"This paper introduces a novel approach called sentence-wise speech summarization (Sen-SSum), which generates text summaries from a spoken document in a sentence-by-sentence manner. Sen-SSum combines the real-time processing of automatic speech recognition (ASR) with the conciseness of speech summarization. To explore this approach, we present two datasets for Sen-SSum: Mega-SSum and CSJ-SSum. Using these datasets, our study evaluates two types of Transformer-based models: 1) cascade models that combine ASR and strong text summarization models, and 2) end-to-end (E2E) models that directly conve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.00205","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/2408.00205/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":"2408.00205","created_at":"2026-07-05T08:51:00.027672+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.00205v1","created_at":"2026-07-05T08:51:00.027672+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00205","created_at":"2026-07-05T08:51:00.027672+00:00"},{"alias_kind":"pith_short_12","alias_value":"JRM33VWPSFRX","created_at":"2026-07-05T08:51:00.027672+00:00"},{"alias_kind":"pith_short_16","alias_value":"JRM33VWPSFRX7EYX","created_at":"2026-07-05T08:51:00.027672+00:00"},{"alias_kind":"pith_short_8","alias_value":"JRM33VWP","created_at":"2026-07-05T08:51:00.027672+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.16942","citing_title":"NUTSHELL: A Dataset for Abstract Generation from Scientific Talks","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JRM33VWPSFRX7EYX5343WYEDKB","json":"https://pith.science/pith/JRM33VWPSFRX7EYX5343WYEDKB.json","graph_json":"https://pith.science/api/pith-number/JRM33VWPSFRX7EYX5343WYEDKB/graph.json","events_json":"https://pith.science/api/pith-number/JRM33VWPSFRX7EYX5343WYEDKB/events.json","paper":"https://pith.science/paper/JRM33VWP"},"agent_actions":{"view_html":"https://pith.science/pith/JRM33VWPSFRX7EYX5343WYEDKB","download_json":"https://pith.science/pith/JRM33VWPSFRX7EYX5343WYEDKB.json","view_paper":"https://pith.science/paper/JRM33VWP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.00205&json=true","fetch_graph":"https://pith.science/api/pith-number/JRM33VWPSFRX7EYX5343WYEDKB/graph.json","fetch_events":"https://pith.science/api/pith-number/JRM33VWPSFRX7EYX5343WYEDKB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JRM33VWPSFRX7EYX5343WYEDKB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JRM33VWPSFRX7EYX5343WYEDKB/action/storage_attestation","attest_author":"https://pith.science/pith/JRM33VWPSFRX7EYX5343WYEDKB/action/author_attestation","sign_citation":"https://pith.science/pith/JRM33VWPSFRX7EYX5343WYEDKB/action/citation_signature","submit_replication":"https://pith.science/pith/JRM33VWPSFRX7EYX5343WYEDKB/action/replication_record"}},"created_at":"2026-07-05T08:51:00.027672+00:00","updated_at":"2026-07-05T08:51:00.027672+00:00"}