{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:T2RC2JXOLL2U2MVHF5D2WPWGYD","short_pith_number":"pith:T2RC2JXO","schema_version":"1.0","canonical_sha256":"9ea22d26ee5af54d32a72f47ab3ec6c0cccd6bf3ad9314cb0fa45551f41a46cf","source":{"kind":"arxiv","id":"2607.02504","version":1},"attestation_state":"computed","paper":{"title":"Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Jiacheng Shao, Jiannan Ge, Jihao Qiu, Kaiwen Duan, Lingxi Xie, Pengfei Chen, Qi Tian, Xinyue Huo, Yuxuan Li","submitted_at":"2026-07-02T17:58:52Z","abstract_excerpt":"Long-form TV dramas present a formidable challenge for comprehensive video understanding, where deciphering complex storyline often relies on \\textbf{speaker recognition}, the task of accurately attributing each spoken utterance to its respective character. In this paper, we advance this field through two primary contributions. (1) We introduce \\textbf{DramaSR-532K}, a large-scale benchmark comprising 532K annotated dialogue lines across more than 900 unique characters, necessitating the integration of auditory, linguistic, and visual cues for speaker recognition. (2) We propose \\textbf{DramaS"},"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":"2607.02504","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-02T17:58:52Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"400639d90ac2611f85fb3729499b5da93021d818a33013fbdff413f15f20943f","abstract_canon_sha256":"9962695ce94415870e139befa0be299d03523b065dc9e73d4c4b7cf07a6edb8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:18:01.335681Z","signature_b64":"zz7xmJeYtu+tSOG6OmH8R+C/aUZSXRq9PYgkKbVwj4bjWupELTlp7UomQUujb+xndrKcKDPltr5zXApsUTpsAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ea22d26ee5af54d32a72f47ab3ec6c0cccd6bf3ad9314cb0fa45551f41a46cf","last_reissued_at":"2026-07-03T01:18:01.335296Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:18:01.335296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Jiacheng Shao, Jiannan Ge, Jihao Qiu, Kaiwen Duan, Lingxi Xie, Pengfei Chen, Qi Tian, Xinyue Huo, Yuxuan Li","submitted_at":"2026-07-02T17:58:52Z","abstract_excerpt":"Long-form TV dramas present a formidable challenge for comprehensive video understanding, where deciphering complex storyline often relies on \\textbf{speaker recognition}, the task of accurately attributing each spoken utterance to its respective character. In this paper, we advance this field through two primary contributions. (1) We introduce \\textbf{DramaSR-532K}, a large-scale benchmark comprising 532K annotated dialogue lines across more than 900 unique characters, necessitating the integration of auditory, linguistic, and visual cues for speaker recognition. (2) We propose \\textbf{DramaS"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02504","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/2607.02504/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":"2607.02504","created_at":"2026-07-03T01:18:01.335361+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.02504v1","created_at":"2026-07-03T01:18:01.335361+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02504","created_at":"2026-07-03T01:18:01.335361+00:00"},{"alias_kind":"pith_short_12","alias_value":"T2RC2JXOLL2U","created_at":"2026-07-03T01:18:01.335361+00:00"},{"alias_kind":"pith_short_16","alias_value":"T2RC2JXOLL2U2MVH","created_at":"2026-07-03T01:18:01.335361+00:00"},{"alias_kind":"pith_short_8","alias_value":"T2RC2JXO","created_at":"2026-07-03T01:18:01.335361+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/T2RC2JXOLL2U2MVHF5D2WPWGYD","json":"https://pith.science/pith/T2RC2JXOLL2U2MVHF5D2WPWGYD.json","graph_json":"https://pith.science/api/pith-number/T2RC2JXOLL2U2MVHF5D2WPWGYD/graph.json","events_json":"https://pith.science/api/pith-number/T2RC2JXOLL2U2MVHF5D2WPWGYD/events.json","paper":"https://pith.science/paper/T2RC2JXO"},"agent_actions":{"view_html":"https://pith.science/pith/T2RC2JXOLL2U2MVHF5D2WPWGYD","download_json":"https://pith.science/pith/T2RC2JXOLL2U2MVHF5D2WPWGYD.json","view_paper":"https://pith.science/paper/T2RC2JXO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.02504&json=true","fetch_graph":"https://pith.science/api/pith-number/T2RC2JXOLL2U2MVHF5D2WPWGYD/graph.json","fetch_events":"https://pith.science/api/pith-number/T2RC2JXOLL2U2MVHF5D2WPWGYD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T2RC2JXOLL2U2MVHF5D2WPWGYD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T2RC2JXOLL2U2MVHF5D2WPWGYD/action/storage_attestation","attest_author":"https://pith.science/pith/T2RC2JXOLL2U2MVHF5D2WPWGYD/action/author_attestation","sign_citation":"https://pith.science/pith/T2RC2JXOLL2U2MVHF5D2WPWGYD/action/citation_signature","submit_replication":"https://pith.science/pith/T2RC2JXOLL2U2MVHF5D2WPWGYD/action/replication_record"}},"created_at":"2026-07-03T01:18:01.335361+00:00","updated_at":"2026-07-03T01:18:01.335361+00:00"}