{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:36IJ4FXKHWIBKBUISUVLVVF4BT","short_pith_number":"pith:36IJ4FXK","schema_version":"1.0","canonical_sha256":"df909e16ea3d90150688952abad4bc0ccd4fc059742af77ebf256cb4399720b5","source":{"kind":"arxiv","id":"2608.13239","version":1},"attestation_state":"computed","paper":{"title":"Reasoning for Social Audio-Visual Question Answering: Where Do We Stand?","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Estefan\\'ia Talavera, Koen P. de Vries, St\\'ephane Lathuili\\`ere, Xavier Alameda-Pineda","submitted_at":"2026-08-13T13:44:35Z","abstract_excerpt":"Training Multimodal Large Language Models for audio-visual social understanding is a crucial step toward embodied social intelligence. Chain-of-thought (CoT) reasoning has become the dominant approach, with HumanOmniV2 and its IntentBench benchmark as a prominent reference point. In this context, we report three findings. First, IntentBench is highly noisy: $\\sim$7% of questions are broken and $\\sim$23% are trivially answerable without the video input. We remove the affected questions and release Intentbench-Prime. Second, current reasoning approaches are expensive and surprisingly ineffective"},"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":"2608.13239","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-13T13:44:35Z","cross_cats_sorted":[],"title_canon_sha256":"ad44f1c4e26c44295dcf0bb7f932fc7e90db9d95a331d32f5949290d8b0edcbb","abstract_canon_sha256":"27129fb6df848d7e438aa5cf85e011c4df3726c4860d12ccf86f81fadeca7be9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T01:00:44.639889Z","signature_b64":"fYsJbvcPsF1zf7NlM7a+iCIPfgrUSTuIB+NfAE27T8wD5bOcHyf6QE6uGcoMNCwOTfMqdvCjIEfi0i5GlHGoCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df909e16ea3d90150688952abad4bc0ccd4fc059742af77ebf256cb4399720b5","last_reissued_at":"2026-08-14T01:00:44.637879Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T01:00:44.637879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reasoning for Social Audio-Visual Question Answering: Where Do We Stand?","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Estefan\\'ia Talavera, Koen P. de Vries, St\\'ephane Lathuili\\`ere, Xavier Alameda-Pineda","submitted_at":"2026-08-13T13:44:35Z","abstract_excerpt":"Training Multimodal Large Language Models for audio-visual social understanding is a crucial step toward embodied social intelligence. Chain-of-thought (CoT) reasoning has become the dominant approach, with HumanOmniV2 and its IntentBench benchmark as a prominent reference point. In this context, we report three findings. First, IntentBench is highly noisy: $\\sim$7% of questions are broken and $\\sim$23% are trivially answerable without the video input. We remove the affected questions and release Intentbench-Prime. Second, current reasoning approaches are expensive and surprisingly ineffective"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.13239","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/2608.13239/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":"2608.13239","created_at":"2026-08-14T01:00:44.638900+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.13239v1","created_at":"2026-08-14T01:00:44.638900+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.13239","created_at":"2026-08-14T01:00:44.638900+00:00"},{"alias_kind":"pith_short_12","alias_value":"36IJ4FXKHWIB","created_at":"2026-08-14T01:00:44.638900+00:00"},{"alias_kind":"pith_short_16","alias_value":"36IJ4FXKHWIBKBUI","created_at":"2026-08-14T01:00:44.638900+00:00"},{"alias_kind":"pith_short_8","alias_value":"36IJ4FXK","created_at":"2026-08-14T01:00:44.638900+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/36IJ4FXKHWIBKBUISUVLVVF4BT","json":"https://pith.science/pith/36IJ4FXKHWIBKBUISUVLVVF4BT.json","graph_json":"https://pith.science/api/pith-number/36IJ4FXKHWIBKBUISUVLVVF4BT/graph.json","events_json":"https://pith.science/api/pith-number/36IJ4FXKHWIBKBUISUVLVVF4BT/events.json","paper":"https://pith.science/paper/36IJ4FXK"},"agent_actions":{"view_html":"https://pith.science/pith/36IJ4FXKHWIBKBUISUVLVVF4BT","download_json":"https://pith.science/pith/36IJ4FXKHWIBKBUISUVLVVF4BT.json","view_paper":"https://pith.science/paper/36IJ4FXK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.13239&json=true","fetch_graph":"https://pith.science/api/pith-number/36IJ4FXKHWIBKBUISUVLVVF4BT/graph.json","fetch_events":"https://pith.science/api/pith-number/36IJ4FXKHWIBKBUISUVLVVF4BT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/36IJ4FXKHWIBKBUISUVLVVF4BT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/36IJ4FXKHWIBKBUISUVLVVF4BT/action/storage_attestation","attest_author":"https://pith.science/pith/36IJ4FXKHWIBKBUISUVLVVF4BT/action/author_attestation","sign_citation":"https://pith.science/pith/36IJ4FXKHWIBKBUISUVLVVF4BT/action/citation_signature","submit_replication":"https://pith.science/pith/36IJ4FXKHWIBKBUISUVLVVF4BT/action/replication_record"}},"created_at":"2026-08-14T01:00:44.638900+00:00","updated_at":"2026-08-14T01:00:44.638900+00:00"}