{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SO7ITJOV4DWZO7FQJWYYHEV6DC","short_pith_number":"pith:SO7ITJOV","schema_version":"1.0","canonical_sha256":"93be89a5d5e0ed977cb04db18392be18b0c8de3e676e25bdc3537b4be08bfdf9","source":{"kind":"arxiv","id":"2309.00133","version":1},"attestation_state":"computed","paper":{"title":"Distraction-free Embeddings for Robust VQA","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ameet Deshpande, Ashwin Kalyan, Atharvan Dogra, Deeksha Varshney, Neeraj Kumar","submitted_at":"2023-08-31T21:02:25Z","abstract_excerpt":"The generation of effective latent representations and their subsequent refinement to incorporate precise information is an essential prerequisite for Vision-Language Understanding (VLU) tasks such as Video Question Answering (VQA). However, most existing methods for VLU focus on sparsely sampling or fine-graining the input information (e.g., sampling a sparse set of frames or text tokens), or adding external knowledge. We present a novel \"DRAX: Distraction Removal and Attended Cross-Alignment\" method to rid our cross-modal representations of distractors in the latent space. We do not exclusiv"},"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":"2309.00133","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-31T21:02:25Z","cross_cats_sorted":[],"title_canon_sha256":"fbac6404facc68af4d2fc955832448021a4c6aeb7c4266337155182d1aee38dc","abstract_canon_sha256":"615bb87bb84d262a375ed5f76738fb3ab41f05aead26a09c2ae9b3e0a17e326b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:46:52.690093Z","signature_b64":"4ghkzCihBDIBRyqAyDBUQ6Ccr45DYJS1oXKu+o78gH0aqIusPyADB+FRF97ardqy3MKGYH+yZ9Q2XzvjouhzBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93be89a5d5e0ed977cb04db18392be18b0c8de3e676e25bdc3537b4be08bfdf9","last_reissued_at":"2026-07-05T06:46:52.689551Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:46:52.689551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distraction-free Embeddings for Robust VQA","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ameet Deshpande, Ashwin Kalyan, Atharvan Dogra, Deeksha Varshney, Neeraj Kumar","submitted_at":"2023-08-31T21:02:25Z","abstract_excerpt":"The generation of effective latent representations and their subsequent refinement to incorporate precise information is an essential prerequisite for Vision-Language Understanding (VLU) tasks such as Video Question Answering (VQA). However, most existing methods for VLU focus on sparsely sampling or fine-graining the input information (e.g., sampling a sparse set of frames or text tokens), or adding external knowledge. We present a novel \"DRAX: Distraction Removal and Attended Cross-Alignment\" method to rid our cross-modal representations of distractors in the latent space. We do not exclusiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.00133","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/2309.00133/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":"2309.00133","created_at":"2026-07-05T06:46:52.689608+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.00133v1","created_at":"2026-07-05T06:46:52.689608+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.00133","created_at":"2026-07-05T06:46:52.689608+00:00"},{"alias_kind":"pith_short_12","alias_value":"SO7ITJOV4DWZ","created_at":"2026-07-05T06:46:52.689608+00:00"},{"alias_kind":"pith_short_16","alias_value":"SO7ITJOV4DWZO7FQ","created_at":"2026-07-05T06:46:52.689608+00:00"},{"alias_kind":"pith_short_8","alias_value":"SO7ITJOV","created_at":"2026-07-05T06:46:52.689608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SO7ITJOV4DWZO7FQJWYYHEV6DC","json":"https://pith.science/pith/SO7ITJOV4DWZO7FQJWYYHEV6DC.json","graph_json":"https://pith.science/api/pith-number/SO7ITJOV4DWZO7FQJWYYHEV6DC/graph.json","events_json":"https://pith.science/api/pith-number/SO7ITJOV4DWZO7FQJWYYHEV6DC/events.json","paper":"https://pith.science/paper/SO7ITJOV"},"agent_actions":{"view_html":"https://pith.science/pith/SO7ITJOV4DWZO7FQJWYYHEV6DC","download_json":"https://pith.science/pith/SO7ITJOV4DWZO7FQJWYYHEV6DC.json","view_paper":"https://pith.science/paper/SO7ITJOV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.00133&json=true","fetch_graph":"https://pith.science/api/pith-number/SO7ITJOV4DWZO7FQJWYYHEV6DC/graph.json","fetch_events":"https://pith.science/api/pith-number/SO7ITJOV4DWZO7FQJWYYHEV6DC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SO7ITJOV4DWZO7FQJWYYHEV6DC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SO7ITJOV4DWZO7FQJWYYHEV6DC/action/storage_attestation","attest_author":"https://pith.science/pith/SO7ITJOV4DWZO7FQJWYYHEV6DC/action/author_attestation","sign_citation":"https://pith.science/pith/SO7ITJOV4DWZO7FQJWYYHEV6DC/action/citation_signature","submit_replication":"https://pith.science/pith/SO7ITJOV4DWZO7FQJWYYHEV6DC/action/replication_record"}},"created_at":"2026-07-05T06:46:52.689608+00:00","updated_at":"2026-07-05T06:46:52.689608+00:00"}