{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:65HYLHET5JGKLCVZZXJQM7XTLE","short_pith_number":"pith:65HYLHET","schema_version":"1.0","canonical_sha256":"f74f859c93ea4ca58ab9cdd3067ef359139c9d57707c788ebf29c27fcc51897c","source":{"kind":"arxiv","id":"2007.03626","version":1},"attestation_state":"computed","paper":{"title":"What Gives the Answer Away? Question Answering Bias Analysis on Video QA Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Amir Zadeh, Jianing Yang, Louis-Philippe Morency, Ruitao Yi, Yongxin Wang, Yuying Zhu","submitted_at":"2020-07-07T17:00:11Z","abstract_excerpt":"Question answering biases in video QA datasets can mislead multimodal model to overfit to QA artifacts and jeopardize the model's ability to generalize. Understanding how strong these QA biases are and where they come from helps the community measure progress more accurately and provide researchers insights to debug their models. In this paper, we analyze QA biases in popular video question answering datasets and discover pretrained language models can answer 37-48% questions correctly without using any multimodal context information, far exceeding the 20% random guess baseline for 5-choose-1 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2007.03626","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-07T17:00:11Z","cross_cats_sorted":["cs.CV","cs.LG","stat.ML"],"title_canon_sha256":"c283d1e01c22f731ee527d0805779a42f44604cc78c804211ccc3817fc1eed0f","abstract_canon_sha256":"612255deb7a6cacaa98c755255395131bcdea5e68d68fa04bcf137e38d1d3164"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:17:04.916630Z","signature_b64":"POR3LC3KcUf6jyv2oba/bsmdIVklXDHCMqd1wmOxbR1kEF2ejhpE7pfvmnpWFUKNPpvlpx+ZG9nWI+UCSlDFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f74f859c93ea4ca58ab9cdd3067ef359139c9d57707c788ebf29c27fcc51897c","last_reissued_at":"2026-07-05T01:17:04.916216Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:17:04.916216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What Gives the Answer Away? Question Answering Bias Analysis on Video QA Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Amir Zadeh, Jianing Yang, Louis-Philippe Morency, Ruitao Yi, Yongxin Wang, Yuying Zhu","submitted_at":"2020-07-07T17:00:11Z","abstract_excerpt":"Question answering biases in video QA datasets can mislead multimodal model to overfit to QA artifacts and jeopardize the model's ability to generalize. Understanding how strong these QA biases are and where they come from helps the community measure progress more accurately and provide researchers insights to debug their models. In this paper, we analyze QA biases in popular video question answering datasets and discover pretrained language models can answer 37-48% questions correctly without using any multimodal context information, far exceeding the 20% random guess baseline for 5-choose-1 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.03626","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/2007.03626/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2007.03626","created_at":"2026-07-05T01:17:04.916276+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.03626v1","created_at":"2026-07-05T01:17:04.916276+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.03626","created_at":"2026-07-05T01:17:04.916276+00:00"},{"alias_kind":"pith_short_12","alias_value":"65HYLHET5JGK","created_at":"2026-07-05T01:17:04.916276+00:00"},{"alias_kind":"pith_short_16","alias_value":"65HYLHET5JGKLCVZ","created_at":"2026-07-05T01:17:04.916276+00:00"},{"alias_kind":"pith_short_8","alias_value":"65HYLHET","created_at":"2026-07-05T01:17:04.916276+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.13428","citing_title":"Mitigating Easy Option Bias in Multiple-Choice Question Answering","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/65HYLHET5JGKLCVZZXJQM7XTLE","json":"https://pith.science/pith/65HYLHET5JGKLCVZZXJQM7XTLE.json","graph_json":"https://pith.science/api/pith-number/65HYLHET5JGKLCVZZXJQM7XTLE/graph.json","events_json":"https://pith.science/api/pith-number/65HYLHET5JGKLCVZZXJQM7XTLE/events.json","paper":"https://pith.science/paper/65HYLHET"},"agent_actions":{"view_html":"https://pith.science/pith/65HYLHET5JGKLCVZZXJQM7XTLE","download_json":"https://pith.science/pith/65HYLHET5JGKLCVZZXJQM7XTLE.json","view_paper":"https://pith.science/paper/65HYLHET","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.03626&json=true","fetch_graph":"https://pith.science/api/pith-number/65HYLHET5JGKLCVZZXJQM7XTLE/graph.json","fetch_events":"https://pith.science/api/pith-number/65HYLHET5JGKLCVZZXJQM7XTLE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/65HYLHET5JGKLCVZZXJQM7XTLE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/65HYLHET5JGKLCVZZXJQM7XTLE/action/storage_attestation","attest_author":"https://pith.science/pith/65HYLHET5JGKLCVZZXJQM7XTLE/action/author_attestation","sign_citation":"https://pith.science/pith/65HYLHET5JGKLCVZZXJQM7XTLE/action/citation_signature","submit_replication":"https://pith.science/pith/65HYLHET5JGKLCVZZXJQM7XTLE/action/replication_record"}},"created_at":"2026-07-05T01:17:04.916276+00:00","updated_at":"2026-07-05T01:17:04.916276+00:00"}