{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:FL5DHMTJXB7XEBRW2KZ3SJ2XK5","short_pith_number":"pith:FL5DHMTJ","schema_version":"1.0","canonical_sha256":"2afa33b269b87f720636d2b3b927575759614f90aae4715c565d2ff603a8eb35","source":{"kind":"arxiv","id":"2009.08018","version":1},"attestation_state":"computed","paper":{"title":"Multi-modal Summarization for Video-containing Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Jun Wang, Xiyan Fu, Zhenglu Yang","submitted_at":"2020-09-17T02:13:14Z","abstract_excerpt":"Summarization of multimedia data becomes increasingly significant as it is the basis for many real-world applications, such as question answering, Web search, and so forth. Most existing multi-modal summarization works however have used visual complementary features extracted from images rather than videos, thereby losing abundant information. Hence, we propose a novel multi-modal summarization task to summarize from a document and its associated video. In this work, we also build a baseline general model with effective strategies, i.e., bi-hop attention and improved late fusion mechanisms to "},"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":"2009.08018","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-17T02:13:14Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"b9bd3855c3e2dcbfe81676259628a4a721cd107a6a759255e2ea7f29544a290f","abstract_canon_sha256":"2647ee121652418cd90a13f4ef2e8a8fa1196ef4470de7d09030fa16960c2cfe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:36:00.478288Z","signature_b64":"+qH5qFR5DrisR8yvM3VTm5XYy2syM01erbMMVCpFTWVQT4pLqDCOMyOUsBwvdjVodxGVy0uAM/ngrvRPv5moBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2afa33b269b87f720636d2b3b927575759614f90aae4715c565d2ff603a8eb35","last_reissued_at":"2026-07-05T01:36:00.477804Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:36:00.477804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-modal Summarization for Video-containing Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Jun Wang, Xiyan Fu, Zhenglu Yang","submitted_at":"2020-09-17T02:13:14Z","abstract_excerpt":"Summarization of multimedia data becomes increasingly significant as it is the basis for many real-world applications, such as question answering, Web search, and so forth. Most existing multi-modal summarization works however have used visual complementary features extracted from images rather than videos, thereby losing abundant information. Hence, we propose a novel multi-modal summarization task to summarize from a document and its associated video. In this work, we also build a baseline general model with effective strategies, i.e., bi-hop attention and improved late fusion mechanisms to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.08018","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/2009.08018/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":"2009.08018","created_at":"2026-07-05T01:36:00.477864+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.08018v1","created_at":"2026-07-05T01:36:00.477864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.08018","created_at":"2026-07-05T01:36:00.477864+00:00"},{"alias_kind":"pith_short_12","alias_value":"FL5DHMTJXB7X","created_at":"2026-07-05T01:36:00.477864+00:00"},{"alias_kind":"pith_short_16","alias_value":"FL5DHMTJXB7XEBRW","created_at":"2026-07-05T01:36:00.477864+00:00"},{"alias_kind":"pith_short_8","alias_value":"FL5DHMTJ","created_at":"2026-07-05T01:36:00.477864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12623","citing_title":"MS4UI: A Dataset for Multi-modal Summarization of User Interface Instructional Videos","ref_index":2020,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FL5DHMTJXB7XEBRW2KZ3SJ2XK5","json":"https://pith.science/pith/FL5DHMTJXB7XEBRW2KZ3SJ2XK5.json","graph_json":"https://pith.science/api/pith-number/FL5DHMTJXB7XEBRW2KZ3SJ2XK5/graph.json","events_json":"https://pith.science/api/pith-number/FL5DHMTJXB7XEBRW2KZ3SJ2XK5/events.json","paper":"https://pith.science/paper/FL5DHMTJ"},"agent_actions":{"view_html":"https://pith.science/pith/FL5DHMTJXB7XEBRW2KZ3SJ2XK5","download_json":"https://pith.science/pith/FL5DHMTJXB7XEBRW2KZ3SJ2XK5.json","view_paper":"https://pith.science/paper/FL5DHMTJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.08018&json=true","fetch_graph":"https://pith.science/api/pith-number/FL5DHMTJXB7XEBRW2KZ3SJ2XK5/graph.json","fetch_events":"https://pith.science/api/pith-number/FL5DHMTJXB7XEBRW2KZ3SJ2XK5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FL5DHMTJXB7XEBRW2KZ3SJ2XK5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FL5DHMTJXB7XEBRW2KZ3SJ2XK5/action/storage_attestation","attest_author":"https://pith.science/pith/FL5DHMTJXB7XEBRW2KZ3SJ2XK5/action/author_attestation","sign_citation":"https://pith.science/pith/FL5DHMTJXB7XEBRW2KZ3SJ2XK5/action/citation_signature","submit_replication":"https://pith.science/pith/FL5DHMTJXB7XEBRW2KZ3SJ2XK5/action/replication_record"}},"created_at":"2026-07-05T01:36:00.477864+00:00","updated_at":"2026-07-05T01:36:00.477864+00:00"}