{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:M4R5HCMMP7E5RVHL3NLQS3B6X6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bdca416b9796c68d3c90aa025460790169b5de49f66cf28c30ff262f0bc56cb1","cross_cats_sorted":["cs.AI","cs.CV","cs.IR","cs.LG","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T09:33:58Z","title_canon_sha256":"b02f29d49f1fb03bf3084a3ee7ed763c35c762f810d4f2991a7af995023ef4e4"},"schema_version":"1.0","source":{"id":"2606.05931","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05931","created_at":"2026-06-05T01:15:28Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05931v1","created_at":"2026-06-05T01:15:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05931","created_at":"2026-06-05T01:15:28Z"},{"alias_kind":"pith_short_12","alias_value":"M4R5HCMMP7E5","created_at":"2026-06-05T01:15:28Z"},{"alias_kind":"pith_short_16","alias_value":"M4R5HCMMP7E5RVHL","created_at":"2026-06-05T01:15:28Z"},{"alias_kind":"pith_short_8","alias_value":"M4R5HCMM","created_at":"2026-06-05T01:15:28Z"}],"graph_snapshots":[{"event_id":"sha256:c0d7c89c26fd590a474a9d0d93a8887cd7e7371bce8f7b9193d298379c9720b1","target":"graph","created_at":"2026-06-05T01:15:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.05931/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When retrieving a person from a video archive by voice and face, should the system be multimodal or not? In real-world broadcast archives, unlike curated benchmarks, a target may be heard but unseen, seen but unheard, or both. Fusing scores from an absent modality injects noise, degrading precision below the best unimodal system. We propose a query-adaptive framework that detects active modalities via cross-modal score consistency: when both modalities are active, files retrieved by one also score highly on the other; this agreement breaks down when a modality is absent. Classifiers driven by ","authors_text":"Abbas Haider, Chi-Ho Chan, Erfan Loweimi, Guanfeng Wu, Hui Wang, Josef Kittler, Kate Knill, Mark Gales, Mengjie Qian, Muhammad Awan","cross_cats":["cs.AI","cs.CV","cs.IR","cs.LG","cs.MM","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T09:33:58Z","title":"To Be Multimodal or Not to Be: Query-Adaptive Audio-Visual Person Retrieval via Active Modality Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05931","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:75a6f75d07fa3ae91e612b99b3be8ec0d9b5c46a6116c77e7482ed0892db23f4","target":"record","created_at":"2026-06-05T01:15:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bdca416b9796c68d3c90aa025460790169b5de49f66cf28c30ff262f0bc56cb1","cross_cats_sorted":["cs.AI","cs.CV","cs.IR","cs.LG","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T09:33:58Z","title_canon_sha256":"b02f29d49f1fb03bf3084a3ee7ed763c35c762f810d4f2991a7af995023ef4e4"},"schema_version":"1.0","source":{"id":"2606.05931","kind":"arxiv","version":1}},"canonical_sha256":"6723d3898c7fc9d8d4ebdb57096c3ebf83a3eb6844e215b916f3f6c9098a3184","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6723d3898c7fc9d8d4ebdb57096c3ebf83a3eb6844e215b916f3f6c9098a3184","first_computed_at":"2026-06-05T01:15:28.078073Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:28.078073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s2bgig11jZMYoOuAfTswfPHpnpvhjVAVzpMK+umczJrqEesD3Lwdjli6ll3fESkKlDiyzExFpPplAjC127Q/Dw==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:28.078484Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05931","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75a6f75d07fa3ae91e612b99b3be8ec0d9b5c46a6116c77e7482ed0892db23f4","sha256:c0d7c89c26fd590a474a9d0d93a8887cd7e7371bce8f7b9193d298379c9720b1"],"state_sha256":"630178924b495381b749991b4aab5d9766ca0cdc2048c92dadacb52e011eb5e6"}