{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:M6O3COOMPJIKX6R72ZUTM75LBW","short_pith_number":"pith:M6O3COOM","canonical_record":{"source":{"id":"2408.12763","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-22T23:32:42Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"32853075919d419883ffe20b7a9a01788ee56b648b93151080381ac2c7e58317","abstract_canon_sha256":"5cee9a1bf7a873a01476d3a04e1b90214101b7fe773ad9d4300ff7917f94c4d4"},"schema_version":"1.0"},"canonical_sha256":"679db139cc7a50abfa3fd669367fab0db03df712a44e0db63ce0872c50ad6d99","source":{"kind":"arxiv","id":"2408.12763","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.12763","created_at":"2026-07-05T09:52:14Z"},{"alias_kind":"arxiv_version","alias_value":"2408.12763v2","created_at":"2026-07-05T09:52:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12763","created_at":"2026-07-05T09:52:14Z"},{"alias_kind":"pith_short_12","alias_value":"M6O3COOMPJIK","created_at":"2026-07-05T09:52:14Z"},{"alias_kind":"pith_short_16","alias_value":"M6O3COOMPJIKX6R7","created_at":"2026-07-05T09:52:14Z"},{"alias_kind":"pith_short_8","alias_value":"M6O3COOM","created_at":"2026-07-05T09:52:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:M6O3COOMPJIKX6R72ZUTM75LBW","target":"record","payload":{"canonical_record":{"source":{"id":"2408.12763","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-22T23:32:42Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"32853075919d419883ffe20b7a9a01788ee56b648b93151080381ac2c7e58317","abstract_canon_sha256":"5cee9a1bf7a873a01476d3a04e1b90214101b7fe773ad9d4300ff7917f94c4d4"},"schema_version":"1.0"},"canonical_sha256":"679db139cc7a50abfa3fd669367fab0db03df712a44e0db63ce0872c50ad6d99","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:14.890168Z","signature_b64":"mePfClDimDNKvSRjmE/iTCnN6PVkDWE7HzJm3Ybw/i/h8Xp8wxDEA1AKLUtscQI/Ir0Nkxdu3r3oipaGA3b/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"679db139cc7a50abfa3fd669367fab0db03df712a44e0db63ce0872c50ad6d99","last_reissued_at":"2026-07-05T09:52:14.889619Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:14.889619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.12763","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":"2026-07-05T09:52:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r2xlpT5tN9TYZAwumquopsHXU9YJ4eh09XEHqoi29ujRX2WfOSUOVgSAbouo8AL4IoIPeE2zyiEwGxtRBNEyAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:40:38.400252Z"},"content_sha256":"04789c99a5bb768cd2d79169cf4e9813262e4c59be117ef5afc4854512382827","schema_version":"1.0","event_id":"sha256:04789c99a5bb768cd2d79169cf4e9813262e4c59be117ef5afc4854512382827"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:M6O3COOMPJIKX6R72ZUTM75LBW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Assessing Modality Bias in Video Question Answering Benchmarks with Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Andrew Zolensky, Basam Alasaly, Eric Eaton, Insup Lee, Jean Park, Kevin Johnson, Kuk Jin Jang, Sriharsha Mopidevi","submitted_at":"2024-08-22T23:32:42Z","abstract_excerpt":"Multimodal large language models (MLLMs) can simultaneously process visual, textual, and auditory data, capturing insights that complement human analysis. However, existing video question-answering (VidQA) benchmarks and datasets often exhibit a bias toward a single modality, despite the goal of requiring advanced reasoning skills that integrate diverse modalities to answer the queries. In this work, we introduce the modality importance score (MIS) to identify such bias. It is designed to assess which modality embeds the necessary information to answer the question. Additionally, we propose an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12763","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/2408.12763/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":"2026-07-05T09:52:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5mIoWiptBEYovtKUV/ZCPEBA7aMJdMkucbQvuWSGSE0g4fWfqkc0Ie8i5uOk+Jdu5gBnnGsDGNPinaQ1XULPDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:40:38.400859Z"},"content_sha256":"30cacc5a98f4ab28542d5fde9365078baa085d46b9e6e04fe57676c89c93a679","schema_version":"1.0","event_id":"sha256:30cacc5a98f4ab28542d5fde9365078baa085d46b9e6e04fe57676c89c93a679"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M6O3COOMPJIKX6R72ZUTM75LBW/bundle.json","state_url":"https://pith.science/pith/M6O3COOMPJIKX6R72ZUTM75LBW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M6O3COOMPJIKX6R72ZUTM75LBW/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":"2026-08-05T10:40:38Z","links":{"resolver":"https://pith.science/pith/M6O3COOMPJIKX6R72ZUTM75LBW","bundle":"https://pith.science/pith/M6O3COOMPJIKX6R72ZUTM75LBW/bundle.json","state":"https://pith.science/pith/M6O3COOMPJIKX6R72ZUTM75LBW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M6O3COOMPJIKX6R72ZUTM75LBW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:M6O3COOMPJIKX6R72ZUTM75LBW","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":"5cee9a1bf7a873a01476d3a04e1b90214101b7fe773ad9d4300ff7917f94c4d4","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-22T23:32:42Z","title_canon_sha256":"32853075919d419883ffe20b7a9a01788ee56b648b93151080381ac2c7e58317"},"schema_version":"1.0","source":{"id":"2408.12763","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.12763","created_at":"2026-07-05T09:52:14Z"},{"alias_kind":"arxiv_version","alias_value":"2408.12763v2","created_at":"2026-07-05T09:52:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12763","created_at":"2026-07-05T09:52:14Z"},{"alias_kind":"pith_short_12","alias_value":"M6O3COOMPJIK","created_at":"2026-07-05T09:52:14Z"},{"alias_kind":"pith_short_16","alias_value":"M6O3COOMPJIKX6R7","created_at":"2026-07-05T09:52:14Z"},{"alias_kind":"pith_short_8","alias_value":"M6O3COOM","created_at":"2026-07-05T09:52:14Z"}],"graph_snapshots":[{"event_id":"sha256:30cacc5a98f4ab28542d5fde9365078baa085d46b9e6e04fe57676c89c93a679","target":"graph","created_at":"2026-07-05T09:52:14Z","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/2408.12763/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) can simultaneously process visual, textual, and auditory data, capturing insights that complement human analysis. However, existing video question-answering (VidQA) benchmarks and datasets often exhibit a bias toward a single modality, despite the goal of requiring advanced reasoning skills that integrate diverse modalities to answer the queries. In this work, we introduce the modality importance score (MIS) to identify such bias. It is designed to assess which modality embeds the necessary information to answer the question. Additionally, we propose an","authors_text":"Andrew Zolensky, Basam Alasaly, Eric Eaton, Insup Lee, Jean Park, Kevin Johnson, Kuk Jin Jang, Sriharsha Mopidevi","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-22T23:32:42Z","title":"Assessing Modality Bias in Video Question Answering Benchmarks with Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12763","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":"sha256:04789c99a5bb768cd2d79169cf4e9813262e4c59be117ef5afc4854512382827","target":"record","created_at":"2026-07-05T09:52:14Z","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":"5cee9a1bf7a873a01476d3a04e1b90214101b7fe773ad9d4300ff7917f94c4d4","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-22T23:32:42Z","title_canon_sha256":"32853075919d419883ffe20b7a9a01788ee56b648b93151080381ac2c7e58317"},"schema_version":"1.0","source":{"id":"2408.12763","kind":"arxiv","version":2}},"canonical_sha256":"679db139cc7a50abfa3fd669367fab0db03df712a44e0db63ce0872c50ad6d99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"679db139cc7a50abfa3fd669367fab0db03df712a44e0db63ce0872c50ad6d99","first_computed_at":"2026-07-05T09:52:14.889619Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:52:14.889619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mePfClDimDNKvSRjmE/iTCnN6PVkDWE7HzJm3Ybw/i/h8Xp8wxDEA1AKLUtscQI/Ir0Nkxdu3r3oipaGA3b/Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:52:14.890168Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.12763","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:04789c99a5bb768cd2d79169cf4e9813262e4c59be117ef5afc4854512382827","sha256:30cacc5a98f4ab28542d5fde9365078baa085d46b9e6e04fe57676c89c93a679"],"state_sha256":"80c55a4955095278ac02da18831273ef7ad9d863bc06b56782d30cc6f2396f64"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ASSXxVhC0CTTH0eURkjoYZPqFUDpZfB5p6g3aUI4jnSSrOv3HlaSBRfpSDFLEItVWIxKt8NbXzeBXiKOtbC3Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T10:40:38.406862Z","bundle_sha256":"4960020ea669e56432f66bde7b1379a901fdeefb993e5679538c2a2e2faec2e9"}}