{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:36IJ4FXKHWIBKBUISUVLVVF4BT","short_pith_number":"pith:36IJ4FXK","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"},"canonical_sha256":"df909e16ea3d90150688952abad4bc0ccd4fc059742af77ebf256cb4399720b5","source":{"kind":"arxiv","id":"2608.13239","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:36IJ4FXKHWIBKBUISUVLVVF4BT","target":"record","payload":{"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"},"canonical_sha256":"df909e16ea3d90150688952abad4bc0ccd4fc059742af77ebf256cb4399720b5","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"},"source_kind":"arxiv","source_id":"2608.13239","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-14T01:00:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oUQtiJVMDKUyMxnUK3kQau/wzO4rR0AKfe63oPRp4ns9PEeu8pvzuSSIOiDx+5Q0ckOc8GPRXFmtrlmHCpj3Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:46:01.275084Z"},"content_sha256":"a840a296997278adf6c7620cd14349a7122f06b3025d9504198e76403b87e042","schema_version":"1.0","event_id":"sha256:a840a296997278adf6c7620cd14349a7122f06b3025d9504198e76403b87e042"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:36IJ4FXKHWIBKBUISUVLVVF4BT","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-14T01:00:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2Eivw6xoqpoUwya9MRs/YPbL0riQR4oFXlcjjPP9nz2vDeeYlzDVVellpjbxpkH3DGBGNzbEjhYOCpHDAkSWDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:46:01.275630Z"},"content_sha256":"154a0ccedc06ab2b6817aa5e0cd86b72560e57ef16266c4bae1599b91d78652f","schema_version":"1.0","event_id":"sha256:154a0ccedc06ab2b6817aa5e0cd86b72560e57ef16266c4bae1599b91d78652f"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:36IJ4FXKHWIBKBUISUVLVVF4BT","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1609/aaai.v40i3.37184) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Rha, H., Yeo, J.H., Kim, Y., Ro, Y.M.: Emotion-coherent reasoning for multimodal llms via emotional rationale verifier. Proceedings of the AAAI Conference on Arti- ficial Intelligence40(3), 2029–2037 (Mar 2026).https://doi.org/10.1609/aaai.","arxiv_id":"2608.13239","detector":"doi_compliance","evidence":{"ref_index":23,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.1609/aaai","reconstructed_doi":"10.1609/aaai.v40i3.37184"},"severity":"advisory","ref_index":23,"audited_at":"2026-08-14T15:48:27.249764Z","event_type":"pith.integrity.v1","detected_doi":"10.1609/aaai.v40i3.37184","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"153c92a996339a34302c55b00f71aa7af0f0540ae6c67ca5faa15ec363e76417","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":19741,"payload_sha256":"45631fdf2aec7ff406738ff029d2c36c6a315d0466d5fc7316001d62f6f93122","signature_b64":"8su5RD/KXHy0mb1AFtapwxx6AE99P/Uqj9IYMaWn64Lrp5OeZPKfs87LUk5zzpnCph0p5z+TcxtcceibrxwFBQ==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-14T15:48:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C0fFjSz0tdpbAk5pDch7h62kqo2H549S953IaA3s77BgImvGeljIszXRBC7bc/Jz7KYS0EvWYLeukW5ypL+FDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:46:01.284544Z"},"content_sha256":"42beeaf0a596053125bee5ca6df4ac6a0800a682c191a7f3e8237682c41ef3ce","schema_version":"1.0","event_id":"sha256:42beeaf0a596053125bee5ca6df4ac6a0800a682c191a7f3e8237682c41ef3ce"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/36IJ4FXKHWIBKBUISUVLVVF4BT/bundle.json","state_url":"https://pith.science/pith/36IJ4FXKHWIBKBUISUVLVVF4BT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/36IJ4FXKHWIBKBUISUVLVVF4BT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-17T20:46:01Z","links":{"resolver":"https://pith.science/pith/36IJ4FXKHWIBKBUISUVLVVF4BT","bundle":"https://pith.science/pith/36IJ4FXKHWIBKBUISUVLVVF4BT/bundle.json","state":"https://pith.science/pith/36IJ4FXKHWIBKBUISUVLVVF4BT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/36IJ4FXKHWIBKBUISUVLVVF4BT/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5NRn7IxB3XdRwQ9JhREeP523bDlZ4V7AYsr15zRi5Jur2BSHitSqgFUzR/IUPmR5yX/LaKzA27giwvxNRfprBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T20:46:01.287819Z","bundle_sha256":"0d014e7007ab7f68d8be57a365698613b8a4bc9f289dcdb235cc9ce2aedf33de"}}