{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L53PKWF2HY7DDQYGTILT3W5XBE","short_pith_number":"pith:L53PKWF2","schema_version":"1.0","canonical_sha256":"5f76f558ba3e3e31c3069a173ddbb7090540fac664fea5075ec2b0904ad41001","source":{"kind":"arxiv","id":"2504.10174","version":3},"attestation_state":"computed","paper":{"title":"LLaVA-ReID: Selective Multi-image Questioner for Interactive Person Re-Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dezhong Peng, Mouxing Yang, Peng Hu, Xi Peng, Yiding Lu, Yijie Lin","submitted_at":"2025-04-14T12:26:31Z","abstract_excerpt":"Traditional text-based person ReID assumes that person descriptions from witnesses are complete and provided at once. However, in real-world scenarios, such descriptions are often partial or vague. To address this limitation, we introduce a new task called interactive person re-identification (Inter-ReID). Inter-ReID is a dialogue-based retrieval task that iteratively refines initial descriptions through ongoing interactions with the witnesses. To facilitate the study of this new task, we construct a dialogue dataset that incorporates multiple types of questions by decomposing fine-grained att"},"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":"2504.10174","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-14T12:26:31Z","cross_cats_sorted":[],"title_canon_sha256":"045aae3be7ab74298ad5061658e5d72eb9502badb780f8f3376ad5c200c6a3cc","abstract_canon_sha256":"c4bc685cc1dabaa11b27cc3f47c07f37543e46f2179c2e6ab9042f2490080dc2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:40.934601Z","signature_b64":"4IPDCgwZSdSATvofDJpL46Yb+vz2nvGNi1PCMaRNXfNvdyHGPgjslqStQw8tQzKqkenpjwB7xKADgGtYcDGTCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f76f558ba3e3e31c3069a173ddbb7090540fac664fea5075ec2b0904ad41001","last_reissued_at":"2026-07-05T11:08:40.934141Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:40.934141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLaVA-ReID: Selective Multi-image Questioner for Interactive Person Re-Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dezhong Peng, Mouxing Yang, Peng Hu, Xi Peng, Yiding Lu, Yijie Lin","submitted_at":"2025-04-14T12:26:31Z","abstract_excerpt":"Traditional text-based person ReID assumes that person descriptions from witnesses are complete and provided at once. However, in real-world scenarios, such descriptions are often partial or vague. To address this limitation, we introduce a new task called interactive person re-identification (Inter-ReID). Inter-ReID is a dialogue-based retrieval task that iteratively refines initial descriptions through ongoing interactions with the witnesses. To facilitate the study of this new task, we construct a dialogue dataset that incorporates multiple types of questions by decomposing fine-grained att"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.10174","kind":"arxiv","version":3},"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/2504.10174/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":"2504.10174","created_at":"2026-07-05T11:08:40.934198+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.10174v3","created_at":"2026-07-05T11:08:40.934198+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.10174","created_at":"2026-07-05T11:08:40.934198+00:00"},{"alias_kind":"pith_short_12","alias_value":"L53PKWF2HY7D","created_at":"2026-07-05T11:08:40.934198+00:00"},{"alias_kind":"pith_short_16","alias_value":"L53PKWF2HY7DDQYG","created_at":"2026-07-05T11:08:40.934198+00:00"},{"alias_kind":"pith_short_8","alias_value":"L53PKWF2","created_at":"2026-07-05T11:08:40.934198+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20044","citing_title":"FUSE: Frequency-domain Unification and Spectral Energy Alignment for Multi-modal Object Re-Identification","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02724","citing_title":"AVTrack: Audio-Visual Tracking in Human-centric Complex Scenes","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09836","citing_title":"ReCoVR: Closing the Loop in Interactive Composed Video Retrieval","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12762","citing_title":"ARGOS: Who, Where, and When in Agentic Multi-Camera Person Search","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L53PKWF2HY7DDQYGTILT3W5XBE","json":"https://pith.science/pith/L53PKWF2HY7DDQYGTILT3W5XBE.json","graph_json":"https://pith.science/api/pith-number/L53PKWF2HY7DDQYGTILT3W5XBE/graph.json","events_json":"https://pith.science/api/pith-number/L53PKWF2HY7DDQYGTILT3W5XBE/events.json","paper":"https://pith.science/paper/L53PKWF2"},"agent_actions":{"view_html":"https://pith.science/pith/L53PKWF2HY7DDQYGTILT3W5XBE","download_json":"https://pith.science/pith/L53PKWF2HY7DDQYGTILT3W5XBE.json","view_paper":"https://pith.science/paper/L53PKWF2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.10174&json=true","fetch_graph":"https://pith.science/api/pith-number/L53PKWF2HY7DDQYGTILT3W5XBE/graph.json","fetch_events":"https://pith.science/api/pith-number/L53PKWF2HY7DDQYGTILT3W5XBE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L53PKWF2HY7DDQYGTILT3W5XBE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L53PKWF2HY7DDQYGTILT3W5XBE/action/storage_attestation","attest_author":"https://pith.science/pith/L53PKWF2HY7DDQYGTILT3W5XBE/action/author_attestation","sign_citation":"https://pith.science/pith/L53PKWF2HY7DDQYGTILT3W5XBE/action/citation_signature","submit_replication":"https://pith.science/pith/L53PKWF2HY7DDQYGTILT3W5XBE/action/replication_record"}},"created_at":"2026-07-05T11:08:40.934198+00:00","updated_at":"2026-07-05T11:08:40.934198+00:00"}