{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VQZCG5ECMBH7YYVTQO6ULQ64DB","short_pith_number":"pith:VQZCG5EC","schema_version":"1.0","canonical_sha256":"ac32237482604ffc62b383bd45c3dc18754847ac8fa598efc53c98438608f1b1","source":{"kind":"arxiv","id":"2103.15679","version":1},"attestation_state":"computed","paper":{"title":"Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hila Chefer, Lior Wolf, Shir Gur","submitted_at":"2021-03-29T15:03:11Z","abstract_excerpt":"Transformers are increasingly dominating multi-modal reasoning tasks, such as visual question answering, achieving state-of-the-art results thanks to their ability to contextualize information using the self-attention and co-attention mechanisms. These attention modules also play a role in other computer vision tasks including object detection and image segmentation. Unlike Transformers that only use self-attention, Transformers with co-attention require to consider multiple attention maps in parallel in order to highlight the information that is relevant to the prediction in the model's input"},"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":"2103.15679","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-29T15:03:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0a5ea810b011f80a2355e04ea619078d860cc701175487aeb0fe9ce97e48bf8b","abstract_canon_sha256":"58d92685b4d5cbf44da50eae8fba15f83ccb8b2c4bc2a3de6158335662158bfe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:27:08.763816Z","signature_b64":"PQa5z5YUYD8M3Z9vFxAeOZxZ2//63Wd/zbdAcE4hYTJIaNAbJbC5ha/0jPh8lII7uSWW7Yz0RBGzsA/ygv8sAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac32237482604ffc62b383bd45c3dc18754847ac8fa598efc53c98438608f1b1","last_reissued_at":"2026-07-05T02:27:08.763282Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:27:08.763282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hila Chefer, Lior Wolf, Shir Gur","submitted_at":"2021-03-29T15:03:11Z","abstract_excerpt":"Transformers are increasingly dominating multi-modal reasoning tasks, such as visual question answering, achieving state-of-the-art results thanks to their ability to contextualize information using the self-attention and co-attention mechanisms. These attention modules also play a role in other computer vision tasks including object detection and image segmentation. Unlike Transformers that only use self-attention, Transformers with co-attention require to consider multiple attention maps in parallel in order to highlight the information that is relevant to the prediction in the model's input"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.15679","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/2103.15679/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":"2103.15679","created_at":"2026-07-05T02:27:08.763341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.15679v1","created_at":"2026-07-05T02:27:08.763341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.15679","created_at":"2026-07-05T02:27:08.763341+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQZCG5ECMBH7","created_at":"2026-07-05T02:27:08.763341+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQZCG5ECMBH7YYVT","created_at":"2026-07-05T02:27:08.763341+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQZCG5EC","created_at":"2026-07-05T02:27:08.763341+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/VQZCG5ECMBH7YYVTQO6ULQ64DB","json":"https://pith.science/pith/VQZCG5ECMBH7YYVTQO6ULQ64DB.json","graph_json":"https://pith.science/api/pith-number/VQZCG5ECMBH7YYVTQO6ULQ64DB/graph.json","events_json":"https://pith.science/api/pith-number/VQZCG5ECMBH7YYVTQO6ULQ64DB/events.json","paper":"https://pith.science/paper/VQZCG5EC"},"agent_actions":{"view_html":"https://pith.science/pith/VQZCG5ECMBH7YYVTQO6ULQ64DB","download_json":"https://pith.science/pith/VQZCG5ECMBH7YYVTQO6ULQ64DB.json","view_paper":"https://pith.science/paper/VQZCG5EC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.15679&json=true","fetch_graph":"https://pith.science/api/pith-number/VQZCG5ECMBH7YYVTQO6ULQ64DB/graph.json","fetch_events":"https://pith.science/api/pith-number/VQZCG5ECMBH7YYVTQO6ULQ64DB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQZCG5ECMBH7YYVTQO6ULQ64DB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQZCG5ECMBH7YYVTQO6ULQ64DB/action/storage_attestation","attest_author":"https://pith.science/pith/VQZCG5ECMBH7YYVTQO6ULQ64DB/action/author_attestation","sign_citation":"https://pith.science/pith/VQZCG5ECMBH7YYVTQO6ULQ64DB/action/citation_signature","submit_replication":"https://pith.science/pith/VQZCG5ECMBH7YYVTQO6ULQ64DB/action/replication_record"}},"created_at":"2026-07-05T02:27:08.763341+00:00","updated_at":"2026-07-05T02:27:08.763341+00:00"}