{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BUI3D7LI7LCV6QCTOAC4ESASMH","short_pith_number":"pith:BUI3D7LI","schema_version":"1.0","canonical_sha256":"0d11b1fd68fac55f40537005c2481261ee9b184855e55b780a29ec69ba88c3e1","source":{"kind":"arxiv","id":"2503.17069","version":4},"attestation_state":"computed","paper":{"title":"PVChat: Personalized Video Chat with One-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fei Richard Yu, Gang Xu, Ming Li, Si Yong Yeo, Weilong Yan, Yucheng Chen, Yufei Shi, Yumeng Li, Zhenxi Li","submitted_at":"2025-03-21T11:50:06Z","abstract_excerpt":"Video large language models (ViLLMs) excel in general video understanding, e.g., recognizing activities like talking and eating, but struggle with identity-aware comprehension, such as \"Wilson is receiving chemotherapy\" or \"Tom is discussing with Sarah\", limiting their applicability in smart healthcare and smart home environments. To address this limitation, we propose a one-shot learning framework PVChat, the first personalized ViLLM that enables subject-aware question answering (QA) from a single video for each subject. Our approach optimizes a Mixture-of-Heads (MoH) enhanced ViLLM on a synt"},"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":"2503.17069","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-21T11:50:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0880e49562b8f7ce6a988a2d9b04866e63b3f8eb50ecf56f362572ce75b35291","abstract_canon_sha256":"41332310078f1f3a01f2f4f07f80a52e29da603f7858ba5824509e3b9dc31ad9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:45.587812Z","signature_b64":"kpQMeyJqOGhliy/9hHsljeDfeGlNNBH4vh47+xbq2Bpuqxn4SDVOvi3Irv2U2FMcoscgkUYILc32oXm0hjy8Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d11b1fd68fac55f40537005c2481261ee9b184855e55b780a29ec69ba88c3e1","last_reissued_at":"2026-07-05T11:54:45.587270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:45.587270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PVChat: Personalized Video Chat with One-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fei Richard Yu, Gang Xu, Ming Li, Si Yong Yeo, Weilong Yan, Yucheng Chen, Yufei Shi, Yumeng Li, Zhenxi Li","submitted_at":"2025-03-21T11:50:06Z","abstract_excerpt":"Video large language models (ViLLMs) excel in general video understanding, e.g., recognizing activities like talking and eating, but struggle with identity-aware comprehension, such as \"Wilson is receiving chemotherapy\" or \"Tom is discussing with Sarah\", limiting their applicability in smart healthcare and smart home environments. To address this limitation, we propose a one-shot learning framework PVChat, the first personalized ViLLM that enables subject-aware question answering (QA) from a single video for each subject. Our approach optimizes a Mixture-of-Heads (MoH) enhanced ViLLM on a synt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.17069","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/2503.17069/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":"2503.17069","created_at":"2026-07-05T11:54:45.587346+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.17069v4","created_at":"2026-07-05T11:54:45.587346+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.17069","created_at":"2026-07-05T11:54:45.587346+00:00"},{"alias_kind":"pith_short_12","alias_value":"BUI3D7LI7LCV","created_at":"2026-07-05T11:54:45.587346+00:00"},{"alias_kind":"pith_short_16","alias_value":"BUI3D7LI7LCV6QCT","created_at":"2026-07-05T11:54:45.587346+00:00"},{"alias_kind":"pith_short_8","alias_value":"BUI3D7LI","created_at":"2026-07-05T11:54:45.587346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10936","citing_title":"Personal Visual Context Learning in Large Multimodal Models","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BUI3D7LI7LCV6QCTOAC4ESASMH","json":"https://pith.science/pith/BUI3D7LI7LCV6QCTOAC4ESASMH.json","graph_json":"https://pith.science/api/pith-number/BUI3D7LI7LCV6QCTOAC4ESASMH/graph.json","events_json":"https://pith.science/api/pith-number/BUI3D7LI7LCV6QCTOAC4ESASMH/events.json","paper":"https://pith.science/paper/BUI3D7LI"},"agent_actions":{"view_html":"https://pith.science/pith/BUI3D7LI7LCV6QCTOAC4ESASMH","download_json":"https://pith.science/pith/BUI3D7LI7LCV6QCTOAC4ESASMH.json","view_paper":"https://pith.science/paper/BUI3D7LI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.17069&json=true","fetch_graph":"https://pith.science/api/pith-number/BUI3D7LI7LCV6QCTOAC4ESASMH/graph.json","fetch_events":"https://pith.science/api/pith-number/BUI3D7LI7LCV6QCTOAC4ESASMH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BUI3D7LI7LCV6QCTOAC4ESASMH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BUI3D7LI7LCV6QCTOAC4ESASMH/action/storage_attestation","attest_author":"https://pith.science/pith/BUI3D7LI7LCV6QCTOAC4ESASMH/action/author_attestation","sign_citation":"https://pith.science/pith/BUI3D7LI7LCV6QCTOAC4ESASMH/action/citation_signature","submit_replication":"https://pith.science/pith/BUI3D7LI7LCV6QCTOAC4ESASMH/action/replication_record"}},"created_at":"2026-07-05T11:54:45.587346+00:00","updated_at":"2026-07-05T11:54:45.587346+00:00"}