{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EA5JAV7JGSMUMG5XGEF27ED3C5","short_pith_number":"pith:EA5JAV7J","schema_version":"1.0","canonical_sha256":"203a9057e93499461bb7310baf907b174f9df9c2aa9ed0ac2e74259b04e9f172","source":{"kind":"arxiv","id":"2606.20970","version":1},"attestation_state":"computed","paper":{"title":"CogniRoute: Learning to Route Social Evidence in Omni-Modal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ana Jojic, Bingxuan Li, Bowen Fang, Ismini Lourentzou, James Matthew Rehg, Pei Tian, Shujun Xia, Wenming Ye, Xinzhuo Li, Xu Cao, Yifan Shen","submitted_at":"2026-06-18T22:17:18Z","abstract_excerpt":"Omni-modal models can ingest video, audio, and text, but unified access to multiple modalities does not guarantee that a model uses the right evidence. This gap is especially pronounced in social video question answering, where the answer may hinge on a gesture, vocal tone, temporal cue, or mismatch between what is said and what is visually expressed. We introduce CogniRoute, a schema-guided Mixture-of-Experts framework for social omni reasoning. CogniRoute uses a training-only cognitive schema that factorizes each example by cross-modal relation, reasoning demand, and temporal scope, and alig"},"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":"2606.20970","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-18T22:17:18Z","cross_cats_sorted":[],"title_canon_sha256":"d367b78d1b5c7e56e758d26588082e8f682044c6fed53970f2df157d1e1704f0","abstract_canon_sha256":"623d92028952148aebc829912d7a748b06d6251b6407501443e743d62dace247"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:23.671547Z","signature_b64":"J34tIyWO8mFVukiyajhRwetl9OJ+PTPg5+FAwFEd7sthKfC1FdCK5hThfqwvdDBXsrE+a9eO4MTm1jvOzSdIBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"203a9057e93499461bb7310baf907b174f9df9c2aa9ed0ac2e74259b04e9f172","last_reissued_at":"2026-06-23T01:12:23.671040Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:23.671040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CogniRoute: Learning to Route Social Evidence in Omni-Modal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ana Jojic, Bingxuan Li, Bowen Fang, Ismini Lourentzou, James Matthew Rehg, Pei Tian, Shujun Xia, Wenming Ye, Xinzhuo Li, Xu Cao, Yifan Shen","submitted_at":"2026-06-18T22:17:18Z","abstract_excerpt":"Omni-modal models can ingest video, audio, and text, but unified access to multiple modalities does not guarantee that a model uses the right evidence. This gap is especially pronounced in social video question answering, where the answer may hinge on a gesture, vocal tone, temporal cue, or mismatch between what is said and what is visually expressed. We introduce CogniRoute, a schema-guided Mixture-of-Experts framework for social omni reasoning. CogniRoute uses a training-only cognitive schema that factorizes each example by cross-modal relation, reasoning demand, and temporal scope, and alig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20970","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/2606.20970/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":"2606.20970","created_at":"2026-06-23T01:12:23.671132+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20970v1","created_at":"2026-06-23T01:12:23.671132+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20970","created_at":"2026-06-23T01:12:23.671132+00:00"},{"alias_kind":"pith_short_12","alias_value":"EA5JAV7JGSMU","created_at":"2026-06-23T01:12:23.671132+00:00"},{"alias_kind":"pith_short_16","alias_value":"EA5JAV7JGSMUMG5X","created_at":"2026-06-23T01:12:23.671132+00:00"},{"alias_kind":"pith_short_8","alias_value":"EA5JAV7J","created_at":"2026-06-23T01:12:23.671132+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/EA5JAV7JGSMUMG5XGEF27ED3C5","json":"https://pith.science/pith/EA5JAV7JGSMUMG5XGEF27ED3C5.json","graph_json":"https://pith.science/api/pith-number/EA5JAV7JGSMUMG5XGEF27ED3C5/graph.json","events_json":"https://pith.science/api/pith-number/EA5JAV7JGSMUMG5XGEF27ED3C5/events.json","paper":"https://pith.science/paper/EA5JAV7J"},"agent_actions":{"view_html":"https://pith.science/pith/EA5JAV7JGSMUMG5XGEF27ED3C5","download_json":"https://pith.science/pith/EA5JAV7JGSMUMG5XGEF27ED3C5.json","view_paper":"https://pith.science/paper/EA5JAV7J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20970&json=true","fetch_graph":"https://pith.science/api/pith-number/EA5JAV7JGSMUMG5XGEF27ED3C5/graph.json","fetch_events":"https://pith.science/api/pith-number/EA5JAV7JGSMUMG5XGEF27ED3C5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EA5JAV7JGSMUMG5XGEF27ED3C5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EA5JAV7JGSMUMG5XGEF27ED3C5/action/storage_attestation","attest_author":"https://pith.science/pith/EA5JAV7JGSMUMG5XGEF27ED3C5/action/author_attestation","sign_citation":"https://pith.science/pith/EA5JAV7JGSMUMG5XGEF27ED3C5/action/citation_signature","submit_replication":"https://pith.science/pith/EA5JAV7JGSMUMG5XGEF27ED3C5/action/replication_record"}},"created_at":"2026-06-23T01:12:23.671132+00:00","updated_at":"2026-06-23T01:12:23.671132+00:00"}