{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BHXCS3YLF4HBKDOWM5IGYQL6RH","short_pith_number":"pith:BHXCS3YL","canonical_record":{"source":{"id":"2504.00487","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-04-01T07:23:50Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"c0a5c220d1ddf3fab0d2198f0d720b4572ec09c8569cc02d03845382fce9f208","abstract_canon_sha256":"f820306b9656abb85edd0291ba92244c0f87645f08a06ed85582d282c2680def"},"schema_version":"1.0"},"canonical_sha256":"09ee296f0b2f0e150dd667506c417e89e76b944e26715851483442e1dfd15fd4","source":{"kind":"arxiv","id":"2504.00487","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.00487","created_at":"2026-07-05T10:43:07Z"},{"alias_kind":"arxiv_version","alias_value":"2504.00487v2","created_at":"2026-07-05T10:43:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00487","created_at":"2026-07-05T10:43:07Z"},{"alias_kind":"pith_short_12","alias_value":"BHXCS3YLF4HB","created_at":"2026-07-05T10:43:07Z"},{"alias_kind":"pith_short_16","alias_value":"BHXCS3YLF4HBKDOW","created_at":"2026-07-05T10:43:07Z"},{"alias_kind":"pith_short_8","alias_value":"BHXCS3YL","created_at":"2026-07-05T10:43:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BHXCS3YLF4HBKDOWM5IGYQL6RH","target":"record","payload":{"canonical_record":{"source":{"id":"2504.00487","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-04-01T07:23:50Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"c0a5c220d1ddf3fab0d2198f0d720b4572ec09c8569cc02d03845382fce9f208","abstract_canon_sha256":"f820306b9656abb85edd0291ba92244c0f87645f08a06ed85582d282c2680def"},"schema_version":"1.0"},"canonical_sha256":"09ee296f0b2f0e150dd667506c417e89e76b944e26715851483442e1dfd15fd4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:07.737992Z","signature_b64":"e1m3ukq7BpnsUR0Z85zdhUqkN6dIP9MGg8Jc9ynTILgGffYRzRVKk4eARlq+zsATYtHZaAdeXl/Pvjvsjb1eDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09ee296f0b2f0e150dd667506c417e89e76b944e26715851483442e1dfd15fd4","last_reissued_at":"2026-07-05T10:43:07.737501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:07.737501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.00487","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:43:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KfDGTyhP8SBJ8LzrKlzoY+bPdC6J0x2RpDE0jkjamq90E22JGO53q/IxvmMIfBIYo9DhZug0pPfrhcxB8K0MBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T05:13:28.293201Z"},"content_sha256":"deab14cc18c5c8c4bb9f12e2968c12dad1b0bb37073f724f30251793bed4dddd","schema_version":"1.0","event_id":"sha256:deab14cc18c5c8c4bb9f12e2968c12dad1b0bb37073f724f30251793bed4dddd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BHXCS3YLF4HBKDOWM5IGYQL6RH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FortisAVQA and MAVEN: a Benchmark Dataset and Debiasing Framework for Robust Multimodal Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.MM","authors_text":"Jie Ma, Jing Tao, Jun Liu, Pinghui Wang, Qi Chai, Zhitao Gao, Zhou Su","submitted_at":"2025-04-01T07:23:50Z","abstract_excerpt":"Audio-Visual Question Answering (AVQA) is a challenging multimodal reasoning task requiring intelligent systems to answer natural language queries based on paired audio-video inputs accurately. However, existing AVQA approaches often suffer from overfitting to dataset biases, leading to poor robustness. Moreover, current datasets may not effectively diagnose these methods. To address these challenges, we first introduce a novel dataset, FortisAVQA, constructed in two stages: (1) rephrasing questions in the test split of the public MUSIC-AVQA dataset and (2) introducing distribution shifts acro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00487","kind":"arxiv","version":2},"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/2504.00487/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":"2026-07-05T10:43:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xvcg48R/9fFTB+YQrxDVE2fptfEbpbsRbupRoqoHqbBJn3VAuJ0lKrrKirodmofIOYzd+nEy2BVSWvO5YtzDDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T05:13:28.293641Z"},"content_sha256":"08498a41207f5e909ac2853b7de3c024c9a6e3c19fa55a7928b012552604be40","schema_version":"1.0","event_id":"sha256:08498a41207f5e909ac2853b7de3c024c9a6e3c19fa55a7928b012552604be40"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BHXCS3YLF4HBKDOWM5IGYQL6RH/bundle.json","state_url":"https://pith.science/pith/BHXCS3YLF4HBKDOWM5IGYQL6RH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BHXCS3YLF4HBKDOWM5IGYQL6RH/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":"2026-07-10T05:13:28Z","links":{"resolver":"https://pith.science/pith/BHXCS3YLF4HBKDOWM5IGYQL6RH","bundle":"https://pith.science/pith/BHXCS3YLF4HBKDOWM5IGYQL6RH/bundle.json","state":"https://pith.science/pith/BHXCS3YLF4HBKDOWM5IGYQL6RH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BHXCS3YLF4HBKDOWM5IGYQL6RH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BHXCS3YLF4HBKDOWM5IGYQL6RH","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":"f820306b9656abb85edd0291ba92244c0f87645f08a06ed85582d282c2680def","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-04-01T07:23:50Z","title_canon_sha256":"c0a5c220d1ddf3fab0d2198f0d720b4572ec09c8569cc02d03845382fce9f208"},"schema_version":"1.0","source":{"id":"2504.00487","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.00487","created_at":"2026-07-05T10:43:07Z"},{"alias_kind":"arxiv_version","alias_value":"2504.00487v2","created_at":"2026-07-05T10:43:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00487","created_at":"2026-07-05T10:43:07Z"},{"alias_kind":"pith_short_12","alias_value":"BHXCS3YLF4HB","created_at":"2026-07-05T10:43:07Z"},{"alias_kind":"pith_short_16","alias_value":"BHXCS3YLF4HBKDOW","created_at":"2026-07-05T10:43:07Z"},{"alias_kind":"pith_short_8","alias_value":"BHXCS3YL","created_at":"2026-07-05T10:43:07Z"}],"graph_snapshots":[{"event_id":"sha256:08498a41207f5e909ac2853b7de3c024c9a6e3c19fa55a7928b012552604be40","target":"graph","created_at":"2026-07-05T10:43:07Z","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/2504.00487/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-Visual Question Answering (AVQA) is a challenging multimodal reasoning task requiring intelligent systems to answer natural language queries based on paired audio-video inputs accurately. However, existing AVQA approaches often suffer from overfitting to dataset biases, leading to poor robustness. Moreover, current datasets may not effectively diagnose these methods. To address these challenges, we first introduce a novel dataset, FortisAVQA, constructed in two stages: (1) rephrasing questions in the test split of the public MUSIC-AVQA dataset and (2) introducing distribution shifts acro","authors_text":"Jie Ma, Jing Tao, Jun Liu, Pinghui Wang, Qi Chai, Zhitao Gao, Zhou Su","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-04-01T07:23:50Z","title":"FortisAVQA and MAVEN: a Benchmark Dataset and Debiasing Framework for Robust Multimodal Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00487","kind":"arxiv","version":2},"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:deab14cc18c5c8c4bb9f12e2968c12dad1b0bb37073f724f30251793bed4dddd","target":"record","created_at":"2026-07-05T10:43:07Z","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":"f820306b9656abb85edd0291ba92244c0f87645f08a06ed85582d282c2680def","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-04-01T07:23:50Z","title_canon_sha256":"c0a5c220d1ddf3fab0d2198f0d720b4572ec09c8569cc02d03845382fce9f208"},"schema_version":"1.0","source":{"id":"2504.00487","kind":"arxiv","version":2}},"canonical_sha256":"09ee296f0b2f0e150dd667506c417e89e76b944e26715851483442e1dfd15fd4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09ee296f0b2f0e150dd667506c417e89e76b944e26715851483442e1dfd15fd4","first_computed_at":"2026-07-05T10:43:07.737501Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:07.737501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e1m3ukq7BpnsUR0Z85zdhUqkN6dIP9MGg8Jc9ynTILgGffYRzRVKk4eARlq+zsATYtHZaAdeXl/Pvjvsjb1eDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:07.737992Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.00487","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:deab14cc18c5c8c4bb9f12e2968c12dad1b0bb37073f724f30251793bed4dddd","sha256:08498a41207f5e909ac2853b7de3c024c9a6e3c19fa55a7928b012552604be40"],"state_sha256":"888a73067d4520804aafa3a11e78c1680157995ff50f0a841989bd8eaeb3d905"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bmhH9vA5nm+SLpbGD8DXksfXeydY929HRbOPxlb4k2w4ZHrmTYI3Iwnv6LmyxIepYR8J/DxjTI+m5HuwPnCuDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T05:13:28.295579Z","bundle_sha256":"2038be53ebf611142ef7a59ba9265d7bee2a15ce1296c037a0e3a1c9c86901c9"}}