{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AADOPCU5YGBI7WGOEXSYJK5OW6","short_pith_number":"pith:AADOPCU5","schema_version":"1.0","canonical_sha256":"0006e78a9dc1828fd8ce25e584abaeb780b0fb26a34ce20e4480dcf0a8fe8191","source":{"kind":"arxiv","id":"2608.07417","version":1},"attestation_state":"computed","paper":{"title":"I Seek You in Videos: Identity-Conditioned Queries for Person-Centric Video Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenglong Huang, Chongxiao Wang, Fei Ding, Haolin Shi, Jie Ma, Jing Li, Jun Liu, Linlin Huang, Peipei Yang, Qiang Lyu, Shibo Gao, Yang Liu, Yangyang Liu","submitted_at":"2026-08-07T17:02:02Z","abstract_excerpt":"Real-world video reasoning often involves multimodal, multi-source inputs, whereas existing video reasoning tasks typically assume a simplified video-text setting, limiting identity matching and person-centric reasoning. To bridge this gap, we introduce the Identity-conditioned Queries (ICQ) task, in which models are required to jointly associate and interpret an input video and a reference image of a person, and leverage this conditioning to address identity grounding, behavior understanding, and temporal reasoning, among other challenges. Building on ICQ, we present ISYV (I Seek You in Video"},"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":"2608.07417","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-07T17:02:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b5d6a0427852f8abc1c89540f622024fa13837a86621a2c7e42c7d4660ef7339","abstract_canon_sha256":"ef733a0cd43d3444499949354fb2ec129b8900432acf7badf1dc6a6853931fd0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:15:19.201800Z","signature_b64":"9yNDgADbcKpe7utTpbDWqZDAQmdpERk4n15v+DfKHI34Hkhv42vochQLSiRUPqm4lJx5bLM+4dkxw5P0Ty4fCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0006e78a9dc1828fd8ce25e584abaeb780b0fb26a34ce20e4480dcf0a8fe8191","last_reissued_at":"2026-08-10T01:15:19.198853Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:15:19.198853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"I Seek You in Videos: Identity-Conditioned Queries for Person-Centric Video Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenglong Huang, Chongxiao Wang, Fei Ding, Haolin Shi, Jie Ma, Jing Li, Jun Liu, Linlin Huang, Peipei Yang, Qiang Lyu, Shibo Gao, Yang Liu, Yangyang Liu","submitted_at":"2026-08-07T17:02:02Z","abstract_excerpt":"Real-world video reasoning often involves multimodal, multi-source inputs, whereas existing video reasoning tasks typically assume a simplified video-text setting, limiting identity matching and person-centric reasoning. To bridge this gap, we introduce the Identity-conditioned Queries (ICQ) task, in which models are required to jointly associate and interpret an input video and a reference image of a person, and leverage this conditioning to address identity grounding, behavior understanding, and temporal reasoning, among other challenges. Building on ICQ, we present ISYV (I Seek You in Video"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07417","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/2608.07417/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":"2608.07417","created_at":"2026-08-10T01:15:19.200286+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.07417v1","created_at":"2026-08-10T01:15:19.200286+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07417","created_at":"2026-08-10T01:15:19.200286+00:00"},{"alias_kind":"pith_short_12","alias_value":"AADOPCU5YGBI","created_at":"2026-08-10T01:15:19.200286+00:00"},{"alias_kind":"pith_short_16","alias_value":"AADOPCU5YGBI7WGO","created_at":"2026-08-10T01:15:19.200286+00:00"},{"alias_kind":"pith_short_8","alias_value":"AADOPCU5","created_at":"2026-08-10T01:15:19.200286+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/AADOPCU5YGBI7WGOEXSYJK5OW6","json":"https://pith.science/pith/AADOPCU5YGBI7WGOEXSYJK5OW6.json","graph_json":"https://pith.science/api/pith-number/AADOPCU5YGBI7WGOEXSYJK5OW6/graph.json","events_json":"https://pith.science/api/pith-number/AADOPCU5YGBI7WGOEXSYJK5OW6/events.json","paper":"https://pith.science/paper/AADOPCU5"},"agent_actions":{"view_html":"https://pith.science/pith/AADOPCU5YGBI7WGOEXSYJK5OW6","download_json":"https://pith.science/pith/AADOPCU5YGBI7WGOEXSYJK5OW6.json","view_paper":"https://pith.science/paper/AADOPCU5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.07417&json=true","fetch_graph":"https://pith.science/api/pith-number/AADOPCU5YGBI7WGOEXSYJK5OW6/graph.json","fetch_events":"https://pith.science/api/pith-number/AADOPCU5YGBI7WGOEXSYJK5OW6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AADOPCU5YGBI7WGOEXSYJK5OW6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AADOPCU5YGBI7WGOEXSYJK5OW6/action/storage_attestation","attest_author":"https://pith.science/pith/AADOPCU5YGBI7WGOEXSYJK5OW6/action/author_attestation","sign_citation":"https://pith.science/pith/AADOPCU5YGBI7WGOEXSYJK5OW6/action/citation_signature","submit_replication":"https://pith.science/pith/AADOPCU5YGBI7WGOEXSYJK5OW6/action/replication_record"}},"created_at":"2026-08-10T01:15:19.200286+00:00","updated_at":"2026-08-10T01:15:19.200286+00:00"}