{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Q5JCD2FNYFQ444IVOKM2C4HGGJ","short_pith_number":"pith:Q5JCD2FN","canonical_record":{"source":{"id":"2410.14248","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-18T07:52:22Z","cross_cats_sorted":[],"title_canon_sha256":"f2b7686b8c3d6d372283e24287a900a915cc8bc4706767e7aef46100427583cc","abstract_canon_sha256":"ef279a3cc40bb9eb58633566f7d5f3b4e5bb20a1bd79f9e661ae5beaae457867"},"schema_version":"1.0"},"canonical_sha256":"875221e8adc161ce71157299a170e63244471c81c72acbfa6a20e85bdd2c212c","source":{"kind":"arxiv","id":"2410.14248","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.14248","created_at":"2026-07-05T11:12:21Z"},{"alias_kind":"arxiv_version","alias_value":"2410.14248v2","created_at":"2026-07-05T11:12:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14248","created_at":"2026-07-05T11:12:21Z"},{"alias_kind":"pith_short_12","alias_value":"Q5JCD2FNYFQ4","created_at":"2026-07-05T11:12:21Z"},{"alias_kind":"pith_short_16","alias_value":"Q5JCD2FNYFQ444IV","created_at":"2026-07-05T11:12:21Z"},{"alias_kind":"pith_short_8","alias_value":"Q5JCD2FN","created_at":"2026-07-05T11:12:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Q5JCD2FNYFQ444IVOKM2C4HGGJ","target":"record","payload":{"canonical_record":{"source":{"id":"2410.14248","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-18T07:52:22Z","cross_cats_sorted":[],"title_canon_sha256":"f2b7686b8c3d6d372283e24287a900a915cc8bc4706767e7aef46100427583cc","abstract_canon_sha256":"ef279a3cc40bb9eb58633566f7d5f3b4e5bb20a1bd79f9e661ae5beaae457867"},"schema_version":"1.0"},"canonical_sha256":"875221e8adc161ce71157299a170e63244471c81c72acbfa6a20e85bdd2c212c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:21.501131Z","signature_b64":"PdKdwaQrQfNPUMBMbCtVJZvRiv2OKCGl+Ephw8WohThlxiiEsc4E51A0MvlpCwnnVjPhmyLT/6zN6dafEG3aBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"875221e8adc161ce71157299a170e63244471c81c72acbfa6a20e85bdd2c212c","last_reissued_at":"2026-07-05T11:12:21.500628Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:21.500628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.14248","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":"2026-07-05T11:12:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u3U012Rww7rYvT0xAP3N7rZAfdWW2EK2HqqnfmmRGMwWCrQSoC7chzecCKaYHowGMhcyaOUEa6Z2mij6WgVbBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:13:09.760291Z"},"content_sha256":"af41dde6990b0a185af7e87e8eb7b33483ebafdccf2a41ddb2bf1c27120b8cc3","schema_version":"1.0","event_id":"sha256:af41dde6990b0a185af7e87e8eb7b33483ebafdccf2a41ddb2bf1c27120b8cc3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Q5JCD2FNYFQ444IVOKM2C4HGGJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Addressing Blind Guessing: Calibration of Selection Bias in Multiple-Choice Question Answering by Video Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexey Kravets, Oleksandr Bezrukov, Olga Loginova, Ravi Shekhar","submitted_at":"2024-10-18T07:52:22Z","abstract_excerpt":"Evaluating Video Language Models (VLMs) is a challenging task. Due to its transparency, Multiple-Choice Question Answering (MCQA) is widely used to measure the performance of these models through accuracy. However, existing MCQA benchmarks fail to capture the full reasoning capabilities of VLMs due to selection bias, when models disproportionately favor certain answer options based on positional patterns observed during training. In this work, we conduct a comprehensive empirical analysis of several VLM architectures across major datasets designed to assess complex video-focused reasoning. We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14248","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/2410.14248/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":"2026-07-05T11:12:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MDGUnZK4STHONI/KSJdwLyE50ABue7WPV0IFojFOl2OPdHYubbsWi5ijKc0Fmn0QPYRxyy5m9ezM2WMcYI0FBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:13:09.760789Z"},"content_sha256":"e953e4f597641944c44ef487fd3af9b0d894f3b9def9e7185dbac550c356b65d","schema_version":"1.0","event_id":"sha256:e953e4f597641944c44ef487fd3af9b0d894f3b9def9e7185dbac550c356b65d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q5JCD2FNYFQ444IVOKM2C4HGGJ/bundle.json","state_url":"https://pith.science/pith/Q5JCD2FNYFQ444IVOKM2C4HGGJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q5JCD2FNYFQ444IVOKM2C4HGGJ/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":"2026-08-08T13:13:09Z","links":{"resolver":"https://pith.science/pith/Q5JCD2FNYFQ444IVOKM2C4HGGJ","bundle":"https://pith.science/pith/Q5JCD2FNYFQ444IVOKM2C4HGGJ/bundle.json","state":"https://pith.science/pith/Q5JCD2FNYFQ444IVOKM2C4HGGJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q5JCD2FNYFQ444IVOKM2C4HGGJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q5JCD2FNYFQ444IVOKM2C4HGGJ","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":"ef279a3cc40bb9eb58633566f7d5f3b4e5bb20a1bd79f9e661ae5beaae457867","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-18T07:52:22Z","title_canon_sha256":"f2b7686b8c3d6d372283e24287a900a915cc8bc4706767e7aef46100427583cc"},"schema_version":"1.0","source":{"id":"2410.14248","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.14248","created_at":"2026-07-05T11:12:21Z"},{"alias_kind":"arxiv_version","alias_value":"2410.14248v2","created_at":"2026-07-05T11:12:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14248","created_at":"2026-07-05T11:12:21Z"},{"alias_kind":"pith_short_12","alias_value":"Q5JCD2FNYFQ4","created_at":"2026-07-05T11:12:21Z"},{"alias_kind":"pith_short_16","alias_value":"Q5JCD2FNYFQ444IV","created_at":"2026-07-05T11:12:21Z"},{"alias_kind":"pith_short_8","alias_value":"Q5JCD2FN","created_at":"2026-07-05T11:12:21Z"}],"graph_snapshots":[{"event_id":"sha256:e953e4f597641944c44ef487fd3af9b0d894f3b9def9e7185dbac550c356b65d","target":"graph","created_at":"2026-07-05T11:12:21Z","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/2410.14248/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating Video Language Models (VLMs) is a challenging task. Due to its transparency, Multiple-Choice Question Answering (MCQA) is widely used to measure the performance of these models through accuracy. However, existing MCQA benchmarks fail to capture the full reasoning capabilities of VLMs due to selection bias, when models disproportionately favor certain answer options based on positional patterns observed during training. In this work, we conduct a comprehensive empirical analysis of several VLM architectures across major datasets designed to assess complex video-focused reasoning. We ","authors_text":"Alexey Kravets, Oleksandr Bezrukov, Olga Loginova, Ravi Shekhar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-18T07:52:22Z","title":"Addressing Blind Guessing: Calibration of Selection Bias in Multiple-Choice Question Answering by Video Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14248","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:af41dde6990b0a185af7e87e8eb7b33483ebafdccf2a41ddb2bf1c27120b8cc3","target":"record","created_at":"2026-07-05T11:12:21Z","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":"ef279a3cc40bb9eb58633566f7d5f3b4e5bb20a1bd79f9e661ae5beaae457867","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-18T07:52:22Z","title_canon_sha256":"f2b7686b8c3d6d372283e24287a900a915cc8bc4706767e7aef46100427583cc"},"schema_version":"1.0","source":{"id":"2410.14248","kind":"arxiv","version":2}},"canonical_sha256":"875221e8adc161ce71157299a170e63244471c81c72acbfa6a20e85bdd2c212c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"875221e8adc161ce71157299a170e63244471c81c72acbfa6a20e85bdd2c212c","first_computed_at":"2026-07-05T11:12:21.500628Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:21.500628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PdKdwaQrQfNPUMBMbCtVJZvRiv2OKCGl+Ephw8WohThlxiiEsc4E51A0MvlpCwnnVjPhmyLT/6zN6dafEG3aBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:21.501131Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.14248","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af41dde6990b0a185af7e87e8eb7b33483ebafdccf2a41ddb2bf1c27120b8cc3","sha256:e953e4f597641944c44ef487fd3af9b0d894f3b9def9e7185dbac550c356b65d"],"state_sha256":"b50d075b52cab2e16f2204477e7219573cfbd30e5e0fc26a412ebfaab84a72b0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AUMEX5hghPIkFUe260leQY7cfCw/mlSFRuXbXehYJ11yN/MH+fPteKvBfU/Dzdyqw9RIVbyygjxMaKpDY4FUAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:13:09.764475Z","bundle_sha256":"fd47a751a7c233924b7d676e78f1043c23a5c5fd5e36b8a68fc07ac30a3ebd53"}}