{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:N7SVOCJFH2LY75DDMEFN5EBJOK","short_pith_number":"pith:N7SVOCJF","schema_version":"1.0","canonical_sha256":"6fe55709253e978ff463610ade90297296eceb971d3fe294d924fa6ebd22f0c9","source":{"kind":"arxiv","id":"2309.09405","version":1},"attestation_state":"computed","paper":{"title":"Does Video Summarization Require Videos? Quantifying the Effectiveness of Language in Video Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Adam Lehavi, Daniel Yang, Digbalay Bose, Shrikanth Narayanan, Swabha Swayamdipta, Yoonsoo Nam","submitted_at":"2023-09-18T00:08:49Z","abstract_excerpt":"Video summarization remains a huge challenge in computer vision due to the size of the input videos to be summarized. We propose an efficient, language-only video summarizer that achieves competitive accuracy with high data efficiency. Using only textual captions obtained via a zero-shot approach, we train a language transformer model and forego image representations. This method allows us to perform filtration amongst the representative text vectors and condense the sequence. With our approach, we gain explainability with natural language that comes easily for human interpretation and textual"},"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":"2309.09405","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-09-18T00:08:49Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"6d71955e96492728d5dd1f59fea4b05e9463448be58f0958297ffc5dcf3a7172","abstract_canon_sha256":"c278f8bd4f961f4a917c822988fdcfcb7ace1ae675a8976f749f523f4935d931"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:38.513155Z","signature_b64":"F+ZEFpPsF/euC3XH4aaUmWv/eae4EcXs0BTZm36XfITd5ZFC9A25B72p8Rlg9QGSLzc+4j4hQZXMEl10F4LbDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fe55709253e978ff463610ade90297296eceb971d3fe294d924fa6ebd22f0c9","last_reissued_at":"2026-07-05T06:51:38.512675Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:38.512675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Does Video Summarization Require Videos? Quantifying the Effectiveness of Language in Video Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Adam Lehavi, Daniel Yang, Digbalay Bose, Shrikanth Narayanan, Swabha Swayamdipta, Yoonsoo Nam","submitted_at":"2023-09-18T00:08:49Z","abstract_excerpt":"Video summarization remains a huge challenge in computer vision due to the size of the input videos to be summarized. We propose an efficient, language-only video summarizer that achieves competitive accuracy with high data efficiency. Using only textual captions obtained via a zero-shot approach, we train a language transformer model and forego image representations. This method allows us to perform filtration amongst the representative text vectors and condense the sequence. With our approach, we gain explainability with natural language that comes easily for human interpretation and textual"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09405","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/2309.09405/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":"2309.09405","created_at":"2026-07-05T06:51:38.512734+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.09405v1","created_at":"2026-07-05T06:51:38.512734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09405","created_at":"2026-07-05T06:51:38.512734+00:00"},{"alias_kind":"pith_short_12","alias_value":"N7SVOCJFH2LY","created_at":"2026-07-05T06:51:38.512734+00:00"},{"alias_kind":"pith_short_16","alias_value":"N7SVOCJFH2LY75DD","created_at":"2026-07-05T06:51:38.512734+00:00"},{"alias_kind":"pith_short_8","alias_value":"N7SVOCJF","created_at":"2026-07-05T06:51:38.512734+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08649","citing_title":"Enhancing Video Memorability Prediction with Text-Motion Cross-modal Contrastive Loss and Its Application in Video Summarization","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N7SVOCJFH2LY75DDMEFN5EBJOK","json":"https://pith.science/pith/N7SVOCJFH2LY75DDMEFN5EBJOK.json","graph_json":"https://pith.science/api/pith-number/N7SVOCJFH2LY75DDMEFN5EBJOK/graph.json","events_json":"https://pith.science/api/pith-number/N7SVOCJFH2LY75DDMEFN5EBJOK/events.json","paper":"https://pith.science/paper/N7SVOCJF"},"agent_actions":{"view_html":"https://pith.science/pith/N7SVOCJFH2LY75DDMEFN5EBJOK","download_json":"https://pith.science/pith/N7SVOCJFH2LY75DDMEFN5EBJOK.json","view_paper":"https://pith.science/paper/N7SVOCJF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.09405&json=true","fetch_graph":"https://pith.science/api/pith-number/N7SVOCJFH2LY75DDMEFN5EBJOK/graph.json","fetch_events":"https://pith.science/api/pith-number/N7SVOCJFH2LY75DDMEFN5EBJOK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N7SVOCJFH2LY75DDMEFN5EBJOK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N7SVOCJFH2LY75DDMEFN5EBJOK/action/storage_attestation","attest_author":"https://pith.science/pith/N7SVOCJFH2LY75DDMEFN5EBJOK/action/author_attestation","sign_citation":"https://pith.science/pith/N7SVOCJFH2LY75DDMEFN5EBJOK/action/citation_signature","submit_replication":"https://pith.science/pith/N7SVOCJFH2LY75DDMEFN5EBJOK/action/replication_record"}},"created_at":"2026-07-05T06:51:38.512734+00:00","updated_at":"2026-07-05T06:51:38.512734+00:00"}