{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:36IJ4FXKHWIBKBUISUVLVVF4BT","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"27129fb6df848d7e438aa5cf85e011c4df3726c4860d12ccf86f81fadeca7be9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-13T13:44:35Z","title_canon_sha256":"ad44f1c4e26c44295dcf0bb7f932fc7e90db9d95a331d32f5949290d8b0edcbb"},"schema_version":"1.0","source":{"id":"2608.13239","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.13239","created_at":"2026-08-14T01:00:44Z"},{"alias_kind":"arxiv_version","alias_value":"2608.13239v1","created_at":"2026-08-14T01:00:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.13239","created_at":"2026-08-14T01:00:44Z"},{"alias_kind":"pith_short_12","alias_value":"36IJ4FXKHWIB","created_at":"2026-08-14T01:00:44Z"},{"alias_kind":"pith_short_16","alias_value":"36IJ4FXKHWIBKBUI","created_at":"2026-08-14T01:00:44Z"},{"alias_kind":"pith_short_8","alias_value":"36IJ4FXK","created_at":"2026-08-14T01:00:44Z"}],"graph_snapshots":[{"event_id":"sha256:154a0ccedc06ab2b6817aa5e0cd86b72560e57ef16266c4bae1599b91d78652f","target":"graph","created_at":"2026-08-14T01:00:44Z","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/2608.13239/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Estefan\\'ia Talavera, Koen P. de Vries, St\\'ephane Lathuili\\`ere, Xavier Alameda-Pineda","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-13T13:44:35Z","title":"Reasoning for Social Audio-Visual Question Answering: Where Do We Stand?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.13239","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:a840a296997278adf6c7620cd14349a7122f06b3025d9504198e76403b87e042","target":"record","created_at":"2026-08-14T01:00:44Z","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":"27129fb6df848d7e438aa5cf85e011c4df3726c4860d12ccf86f81fadeca7be9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-13T13:44:35Z","title_canon_sha256":"ad44f1c4e26c44295dcf0bb7f932fc7e90db9d95a331d32f5949290d8b0edcbb"},"schema_version":"1.0","source":{"id":"2608.13239","kind":"arxiv","version":1}},"canonical_sha256":"df909e16ea3d90150688952abad4bc0ccd4fc059742af77ebf256cb4399720b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df909e16ea3d90150688952abad4bc0ccd4fc059742af77ebf256cb4399720b5","first_computed_at":"2026-08-14T01:00:44.637879Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-14T01:00:44.637879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fYsJbvcPsF1zf7NlM7a+iCIPfgrUSTuIB+NfAE27T8wD5bOcHyf6QE6uGcoMNCwOTfMqdvCjIEfi0i5GlHGoCg==","signature_status":"signed_v1","signed_at":"2026-08-14T01:00:44.639889Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.13239","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a840a296997278adf6c7620cd14349a7122f06b3025d9504198e76403b87e042","sha256:154a0ccedc06ab2b6817aa5e0cd86b72560e57ef16266c4bae1599b91d78652f","sha256:42beeaf0a596053125bee5ca6df4ac6a0800a682c191a7f3e8237682c41ef3ce"],"state_sha256":"8942bf2a0cd82b941a38ffd90a859304a9afeef950fd2cc5f2fc8dbf0ca460c4"}