{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6M7N3I5CSFNP42AIF4C6ZHFWNS","short_pith_number":"pith:6M7N3I5C","schema_version":"1.0","canonical_sha256":"f33edda3a2915afe68082f05ec9cb66c98d5e7c7552b5e006ba841baaffd8c48","source":{"kind":"arxiv","id":"2408.01669","version":4},"attestation_state":"computed","paper":{"title":"SynopGround: A Large-Scale Dataset for Multi-Paragraph Video Grounding from TV Dramas and Synopses","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Chaolei Tan, Jian-Fang Hu, Junfu Pu, Wei-Shi Zheng, Wei-Yi Pei, Yexin Wang, Ying Shan, Zhi Qu, Zhongang Qi, Zihang Lin","submitted_at":"2024-08-03T05:35:13Z","abstract_excerpt":"Video grounding is a fundamental problem in multimodal content understanding, aiming to localize specific natural language queries in an untrimmed video. However, current video grounding datasets merely focus on simple events and are either limited to shorter videos or brief sentences, which hinders the model from evolving toward stronger multimodal understanding capabilities. To address these limitations, we present a large-scale video grounding dataset named SynopGround, in which more than 2800 hours of videos are sourced from popular TV dramas and are paired with accurately localized human-"},"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":"2408.01669","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-03T05:35:13Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"01847cfb4a5124a1445e0519da614f99b2df372c57c2187a512c89623c7cdf26","abstract_canon_sha256":"07ae18defb67b3052d5860285f28857c747c3db1e2723eebb7f4fe4931789db5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:23.664966Z","signature_b64":"WoVTCsZGEVuMFD0xZiLBLm5VUrDsSzv1f5MwjWot6I2VCNk7sIXz9gzJe77YOwygztXB5AjnpsKi5MFnqfM1Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f33edda3a2915afe68082f05ec9cb66c98d5e7c7552b5e006ba841baaffd8c48","last_reissued_at":"2026-07-05T08:56:23.664515Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:23.664515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SynopGround: A Large-Scale Dataset for Multi-Paragraph Video Grounding from TV Dramas and Synopses","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Chaolei Tan, Jian-Fang Hu, Junfu Pu, Wei-Shi Zheng, Wei-Yi Pei, Yexin Wang, Ying Shan, Zhi Qu, Zhongang Qi, Zihang Lin","submitted_at":"2024-08-03T05:35:13Z","abstract_excerpt":"Video grounding is a fundamental problem in multimodal content understanding, aiming to localize specific natural language queries in an untrimmed video. However, current video grounding datasets merely focus on simple events and are either limited to shorter videos or brief sentences, which hinders the model from evolving toward stronger multimodal understanding capabilities. To address these limitations, we present a large-scale video grounding dataset named SynopGround, in which more than 2800 hours of videos are sourced from popular TV dramas and are paired with accurately localized human-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.01669","kind":"arxiv","version":4},"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/2408.01669/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":"2408.01669","created_at":"2026-07-05T08:56:23.664584+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.01669v4","created_at":"2026-07-05T08:56:23.664584+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.01669","created_at":"2026-07-05T08:56:23.664584+00:00"},{"alias_kind":"pith_short_12","alias_value":"6M7N3I5CSFNP","created_at":"2026-07-05T08:56:23.664584+00:00"},{"alias_kind":"pith_short_16","alias_value":"6M7N3I5CSFNP42AI","created_at":"2026-07-05T08:56:23.664584+00:00"},{"alias_kind":"pith_short_8","alias_value":"6M7N3I5C","created_at":"2026-07-05T08:56:23.664584+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/6M7N3I5CSFNP42AIF4C6ZHFWNS","json":"https://pith.science/pith/6M7N3I5CSFNP42AIF4C6ZHFWNS.json","graph_json":"https://pith.science/api/pith-number/6M7N3I5CSFNP42AIF4C6ZHFWNS/graph.json","events_json":"https://pith.science/api/pith-number/6M7N3I5CSFNP42AIF4C6ZHFWNS/events.json","paper":"https://pith.science/paper/6M7N3I5C"},"agent_actions":{"view_html":"https://pith.science/pith/6M7N3I5CSFNP42AIF4C6ZHFWNS","download_json":"https://pith.science/pith/6M7N3I5CSFNP42AIF4C6ZHFWNS.json","view_paper":"https://pith.science/paper/6M7N3I5C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.01669&json=true","fetch_graph":"https://pith.science/api/pith-number/6M7N3I5CSFNP42AIF4C6ZHFWNS/graph.json","fetch_events":"https://pith.science/api/pith-number/6M7N3I5CSFNP42AIF4C6ZHFWNS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6M7N3I5CSFNP42AIF4C6ZHFWNS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6M7N3I5CSFNP42AIF4C6ZHFWNS/action/storage_attestation","attest_author":"https://pith.science/pith/6M7N3I5CSFNP42AIF4C6ZHFWNS/action/author_attestation","sign_citation":"https://pith.science/pith/6M7N3I5CSFNP42AIF4C6ZHFWNS/action/citation_signature","submit_replication":"https://pith.science/pith/6M7N3I5CSFNP42AIF4C6ZHFWNS/action/replication_record"}},"created_at":"2026-07-05T08:56:23.664584+00:00","updated_at":"2026-07-05T08:56:23.664584+00:00"}