{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:HSQJ7PTK4VSSQT3PB37PHQXCRJ","short_pith_number":"pith:HSQJ7PTK","schema_version":"1.0","canonical_sha256":"3ca09fbe6ae565284f6f0efef3c2e28a41caa512779cde6c320eea74bc4ef8b4","source":{"kind":"arxiv","id":"1906.01351","version":2},"attestation_state":"computed","paper":{"title":"TalkSumm: A Dataset and Scalable Annotation Method for Scientific Paper Summarization Based on Conference Talks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Achiya Jerbi, David Konopnicki, Guy Lev, Jonathan Herzig, Michal Shmueli-Scheuer","submitted_at":"2019-06-04T11:25:14Z","abstract_excerpt":"Currently, no large-scale training data is available for the task of scientific paper summarization. In this paper, we propose a novel method that automatically generates summaries for scientific papers, by utilizing videos of talks at scientific conferences. We hypothesize that such talks constitute a coherent and concise description of the papers' content, and can form the basis for good summaries. We collected 1716 papers and their corresponding videos, and created a dataset of paper summaries. A model trained on this dataset achieves similar performance as models trained on a dataset of su"},"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":"1906.01351","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-04T11:25:14Z","cross_cats_sorted":[],"title_canon_sha256":"a17727b32980fdb16011c38c6c54b7363197c1d4441222105c3726f71b813278","abstract_canon_sha256":"c3d18de8228c579f10e55a21877c6e7bfbb0fff271af4530b4fe4ae011d29573"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:27.520006Z","signature_b64":"IUnFD7j49n0npuDFbfzN9Xd9BwGDVsnSL1Cu5DiRbGxJtYBMDwGhWhewskDABC5uAEP0df++jeQ2OmyBpn+DDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ca09fbe6ae565284f6f0efef3c2e28a41caa512779cde6c320eea74bc4ef8b4","last_reissued_at":"2026-05-17T23:43:27.519498Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:27.519498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TalkSumm: A Dataset and Scalable Annotation Method for Scientific Paper Summarization Based on Conference Talks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Achiya Jerbi, David Konopnicki, Guy Lev, Jonathan Herzig, Michal Shmueli-Scheuer","submitted_at":"2019-06-04T11:25:14Z","abstract_excerpt":"Currently, no large-scale training data is available for the task of scientific paper summarization. In this paper, we propose a novel method that automatically generates summaries for scientific papers, by utilizing videos of talks at scientific conferences. We hypothesize that such talks constitute a coherent and concise description of the papers' content, and can form the basis for good summaries. We collected 1716 papers and their corresponding videos, and created a dataset of paper summaries. A model trained on this dataset achieves similar performance as models trained on a dataset of su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01351","kind":"arxiv","version":2},"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":"1906.01351","created_at":"2026-05-17T23:43:27.519577+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.01351v2","created_at":"2026-05-17T23:43:27.519577+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01351","created_at":"2026-05-17T23:43:27.519577+00:00"},{"alias_kind":"pith_short_12","alias_value":"HSQJ7PTK4VSS","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"HSQJ7PTK4VSSQT3P","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"HSQJ7PTK","created_at":"2026-05-18T12:33:18.533446+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/HSQJ7PTK4VSSQT3PB37PHQXCRJ","json":"https://pith.science/pith/HSQJ7PTK4VSSQT3PB37PHQXCRJ.json","graph_json":"https://pith.science/api/pith-number/HSQJ7PTK4VSSQT3PB37PHQXCRJ/graph.json","events_json":"https://pith.science/api/pith-number/HSQJ7PTK4VSSQT3PB37PHQXCRJ/events.json","paper":"https://pith.science/paper/HSQJ7PTK"},"agent_actions":{"view_html":"https://pith.science/pith/HSQJ7PTK4VSSQT3PB37PHQXCRJ","download_json":"https://pith.science/pith/HSQJ7PTK4VSSQT3PB37PHQXCRJ.json","view_paper":"https://pith.science/paper/HSQJ7PTK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.01351&json=true","fetch_graph":"https://pith.science/api/pith-number/HSQJ7PTK4VSSQT3PB37PHQXCRJ/graph.json","fetch_events":"https://pith.science/api/pith-number/HSQJ7PTK4VSSQT3PB37PHQXCRJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HSQJ7PTK4VSSQT3PB37PHQXCRJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HSQJ7PTK4VSSQT3PB37PHQXCRJ/action/storage_attestation","attest_author":"https://pith.science/pith/HSQJ7PTK4VSSQT3PB37PHQXCRJ/action/author_attestation","sign_citation":"https://pith.science/pith/HSQJ7PTK4VSSQT3PB37PHQXCRJ/action/citation_signature","submit_replication":"https://pith.science/pith/HSQJ7PTK4VSSQT3PB37PHQXCRJ/action/replication_record"}},"created_at":"2026-05-17T23:43:27.519577+00:00","updated_at":"2026-05-17T23:43:27.519577+00:00"}