{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:Z44WNKEPQ66GRV6C4AD45XXZYM","short_pith_number":"pith:Z44WNKEP","schema_version":"1.0","canonical_sha256":"cf3966a88f87bc68d7c2e007cedef9c331c139047d877f657a24fc8765eabc02","source":{"kind":"arxiv","id":"1406.5824","version":1},"attestation_state":"computed","paper":{"title":"VideoSET: Video Summary Evaluation through Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.CV","authors_text":"Alireza Fathi, Li Fei-Fei, Serena Yeung","submitted_at":"2014-06-23T07:56:23Z","abstract_excerpt":"In this paper we present VideoSET, a method for Video Summary Evaluation through Text that can evaluate how well a video summary is able to retain the semantic information contained in its original video. We observe that semantics is most easily expressed in words, and develop a text-based approach for the evaluation. Given a video summary, a text representation of the video summary is first generated, and an NLP-based metric is then used to measure its semantic distance to ground-truth text summaries written by humans. We show that our technique has higher agreement with human judgment than p"},"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":"1406.5824","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-06-23T07:56:23Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"22bd8fe091ec81c8308894ed73fd818280163de9419b6f27e690f5c22a7ba0cd","abstract_canon_sha256":"2cd68e05cec77ebdbdf792972497b548d27a551dc4ecf3efc3390275d9aeb423"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:49:10.660696Z","signature_b64":"RJqj1WeomhF7rrcOaGC5xGwPFkikkhdAdpuMbnQLTC7vJzsvQVfgffWp/7QBpMelUlQ3HqpikhMXThTjy1jcBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf3966a88f87bc68d7c2e007cedef9c331c139047d877f657a24fc8765eabc02","last_reissued_at":"2026-05-18T02:49:10.660219Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:49:10.660219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoSET: Video Summary Evaluation through Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.CV","authors_text":"Alireza Fathi, Li Fei-Fei, Serena Yeung","submitted_at":"2014-06-23T07:56:23Z","abstract_excerpt":"In this paper we present VideoSET, a method for Video Summary Evaluation through Text that can evaluate how well a video summary is able to retain the semantic information contained in its original video. We observe that semantics is most easily expressed in words, and develop a text-based approach for the evaluation. Given a video summary, a text representation of the video summary is first generated, and an NLP-based metric is then used to measure its semantic distance to ground-truth text summaries written by humans. We show that our technique has higher agreement with human judgment than p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.5824","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":""},"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":"1406.5824","created_at":"2026-05-18T02:49:10.660287+00:00"},{"alias_kind":"arxiv_version","alias_value":"1406.5824v1","created_at":"2026-05-18T02:49:10.660287+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.5824","created_at":"2026-05-18T02:49:10.660287+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z44WNKEPQ66G","created_at":"2026-05-18T12:28:59.999130+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z44WNKEPQ66GRV6C","created_at":"2026-05-18T12:28:59.999130+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z44WNKEP","created_at":"2026-05-18T12:28:59.999130+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2510.05652","citing_title":"SD-MVSum: Script-Driven Multimodal Video Summarization Method and Datasets","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z44WNKEPQ66GRV6C4AD45XXZYM","json":"https://pith.science/pith/Z44WNKEPQ66GRV6C4AD45XXZYM.json","graph_json":"https://pith.science/api/pith-number/Z44WNKEPQ66GRV6C4AD45XXZYM/graph.json","events_json":"https://pith.science/api/pith-number/Z44WNKEPQ66GRV6C4AD45XXZYM/events.json","paper":"https://pith.science/paper/Z44WNKEP"},"agent_actions":{"view_html":"https://pith.science/pith/Z44WNKEPQ66GRV6C4AD45XXZYM","download_json":"https://pith.science/pith/Z44WNKEPQ66GRV6C4AD45XXZYM.json","view_paper":"https://pith.science/paper/Z44WNKEP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1406.5824&json=true","fetch_graph":"https://pith.science/api/pith-number/Z44WNKEPQ66GRV6C4AD45XXZYM/graph.json","fetch_events":"https://pith.science/api/pith-number/Z44WNKEPQ66GRV6C4AD45XXZYM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z44WNKEPQ66GRV6C4AD45XXZYM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z44WNKEPQ66GRV6C4AD45XXZYM/action/storage_attestation","attest_author":"https://pith.science/pith/Z44WNKEPQ66GRV6C4AD45XXZYM/action/author_attestation","sign_citation":"https://pith.science/pith/Z44WNKEPQ66GRV6C4AD45XXZYM/action/citation_signature","submit_replication":"https://pith.science/pith/Z44WNKEPQ66GRV6C4AD45XXZYM/action/replication_record"}},"created_at":"2026-05-18T02:49:10.660287+00:00","updated_at":"2026-05-18T02:49:10.660287+00:00"}