{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SO7ITJOV4DWZO7FQJWYYHEV6DC","short_pith_number":"pith:SO7ITJOV","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"},"canonical_sha256":"93be89a5d5e0ed977cb04db18392be18b0c8de3e676e25bdc3537b4be08bfdf9","source":{"kind":"arxiv","id":"2309.00133","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.00133","created_at":"2026-07-05T06:46:52Z"},{"alias_kind":"arxiv_version","alias_value":"2309.00133v1","created_at":"2026-07-05T06:46:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.00133","created_at":"2026-07-05T06:46:52Z"},{"alias_kind":"pith_short_12","alias_value":"SO7ITJOV4DWZ","created_at":"2026-07-05T06:46:52Z"},{"alias_kind":"pith_short_16","alias_value":"SO7ITJOV4DWZO7FQ","created_at":"2026-07-05T06:46:52Z"},{"alias_kind":"pith_short_8","alias_value":"SO7ITJOV","created_at":"2026-07-05T06:46:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SO7ITJOV4DWZO7FQJWYYHEV6DC","target":"record","payload":{"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"},"canonical_sha256":"93be89a5d5e0ed977cb04db18392be18b0c8de3e676e25bdc3537b4be08bfdf9","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"},"source_kind":"arxiv","source_id":"2309.00133","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:46:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T6JKxfE0DNEPlCeYDE5YsVnnSNqZqm92w//uS9WdUfG6JHWkMw+px7oB54jUBOimvOJF3F+O1Fj/X9HYJR5tAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T10:58:52.670154Z"},"content_sha256":"91db6674a3cd7b5193bdee793ab96fa194cc5bf7378323a518c8ed0dd98547bc","schema_version":"1.0","event_id":"sha256:91db6674a3cd7b5193bdee793ab96fa194cc5bf7378323a518c8ed0dd98547bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SO7ITJOV4DWZO7FQJWYYHEV6DC","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:46:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5vL2awBFauVrFFeJcT6htZcTJCzBd5cpiTNTLTW8ZsbwHGgDIvSen1ldZv4MjHqaQAAPE5XqUs3AA2Pg0SLfBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T10:58:52.670547Z"},"content_sha256":"507c8a4992f72fb9ddac93097aa270288cffb4d9a31983c670dc1bffe6ecee85","schema_version":"1.0","event_id":"sha256:507c8a4992f72fb9ddac93097aa270288cffb4d9a31983c670dc1bffe6ecee85"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SO7ITJOV4DWZO7FQJWYYHEV6DC/bundle.json","state_url":"https://pith.science/pith/SO7ITJOV4DWZO7FQJWYYHEV6DC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SO7ITJOV4DWZO7FQJWYYHEV6DC/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":"2026-07-14T10:58:52Z","links":{"resolver":"https://pith.science/pith/SO7ITJOV4DWZO7FQJWYYHEV6DC","bundle":"https://pith.science/pith/SO7ITJOV4DWZO7FQJWYYHEV6DC/bundle.json","state":"https://pith.science/pith/SO7ITJOV4DWZO7FQJWYYHEV6DC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SO7ITJOV4DWZO7FQJWYYHEV6DC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SO7ITJOV4DWZO7FQJWYYHEV6DC","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":"615bb87bb84d262a375ed5f76738fb3ab41f05aead26a09c2ae9b3e0a17e326b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-31T21:02:25Z","title_canon_sha256":"fbac6404facc68af4d2fc955832448021a4c6aeb7c4266337155182d1aee38dc"},"schema_version":"1.0","source":{"id":"2309.00133","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.00133","created_at":"2026-07-05T06:46:52Z"},{"alias_kind":"arxiv_version","alias_value":"2309.00133v1","created_at":"2026-07-05T06:46:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.00133","created_at":"2026-07-05T06:46:52Z"},{"alias_kind":"pith_short_12","alias_value":"SO7ITJOV4DWZ","created_at":"2026-07-05T06:46:52Z"},{"alias_kind":"pith_short_16","alias_value":"SO7ITJOV4DWZO7FQ","created_at":"2026-07-05T06:46:52Z"},{"alias_kind":"pith_short_8","alias_value":"SO7ITJOV","created_at":"2026-07-05T06:46:52Z"}],"graph_snapshots":[{"event_id":"sha256:507c8a4992f72fb9ddac93097aa270288cffb4d9a31983c670dc1bffe6ecee85","target":"graph","created_at":"2026-07-05T06:46:52Z","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/2309.00133/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ameet Deshpande, Ashwin Kalyan, Atharvan Dogra, Deeksha Varshney, Neeraj Kumar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-31T21:02:25Z","title":"Distraction-free Embeddings for Robust VQA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.00133","kind":"arxiv","version":1},"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":"sha256:91db6674a3cd7b5193bdee793ab96fa194cc5bf7378323a518c8ed0dd98547bc","target":"record","created_at":"2026-07-05T06:46:52Z","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":"615bb87bb84d262a375ed5f76738fb3ab41f05aead26a09c2ae9b3e0a17e326b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-31T21:02:25Z","title_canon_sha256":"fbac6404facc68af4d2fc955832448021a4c6aeb7c4266337155182d1aee38dc"},"schema_version":"1.0","source":{"id":"2309.00133","kind":"arxiv","version":1}},"canonical_sha256":"93be89a5d5e0ed977cb04db18392be18b0c8de3e676e25bdc3537b4be08bfdf9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93be89a5d5e0ed977cb04db18392be18b0c8de3e676e25bdc3537b4be08bfdf9","first_computed_at":"2026-07-05T06:46:52.689551Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:46:52.689551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4ghkzCihBDIBRyqAyDBUQ6Ccr45DYJS1oXKu+o78gH0aqIusPyADB+FRF97ardqy3MKGYH+yZ9Q2XzvjouhzBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:46:52.690093Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.00133","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91db6674a3cd7b5193bdee793ab96fa194cc5bf7378323a518c8ed0dd98547bc","sha256:507c8a4992f72fb9ddac93097aa270288cffb4d9a31983c670dc1bffe6ecee85"],"state_sha256":"edef454fcb6a690c735ba8a727136a66c55cf34508b1e9c4cd735ba8c0f28836"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i3EUoZojvZ4cjmz4v9oLpq7nSXbINdHhdc66j5RVi95inhJKzSGi5ZZmHcjdjlZPZZr6MpcKGlMp3EiXDiELCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-14T10:58:52.672772Z","bundle_sha256":"97d7f966bdc9620a4221b031897c5e8f44d4d28dd3a84b776168b834e238dede"}}