{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XMPFMOE4QLCDVNOGHSDPSFP37X","short_pith_number":"pith:XMPFMOE4","schema_version":"1.0","canonical_sha256":"bb1e56389c82c43ab5c63c86f915fbfdcda8bb15ef279477ce149095e9999116","source":{"kind":"arxiv","id":"2203.17247","version":3},"attestation_state":"computed","paper":{"title":"VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chenfei Wu, Estelle Aflalo, Meng Du, Nan Duan, Shao-Yen Tseng, Vasudev Lal, Yongfei Liu","submitted_at":"2022-03-30T05:25:35Z","abstract_excerpt":"Breakthroughs in transformer-based models have revolutionized not only the NLP field, but also vision and multimodal systems. However, although visualization and interpretability tools have become available for NLP models, internal mechanisms of vision and multimodal transformers remain largely opaque. With the success of these transformers, it is increasingly critical to understand their inner workings, as unraveling these black-boxes will lead to more capable and trustworthy models. To contribute to this quest, we propose VL-InterpreT, which provides novel interactive visualizations for inte"},"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":"2203.17247","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-30T05:25:35Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"b1de6ebb47024fee0f48cd8501cc78e7676a0e96a83a91e292003926fa49ac5d","abstract_canon_sha256":"7f49b342ac5b2880c46d47d93e82fea187d8a38bf31da4342f5b010fe3089747"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:50:33.945008Z","signature_b64":"/bC/C0UEJLlkH8JsLaM9gQaC70ueudSlA1rYybtfmbN7js7Tgd21MXGawEuYQpKaEgPHsGLHC2QBtAiHOgpkAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb1e56389c82c43ab5c63c86f915fbfdcda8bb15ef279477ce149095e9999116","last_reissued_at":"2026-07-05T04:50:33.944572Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:50:33.944572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chenfei Wu, Estelle Aflalo, Meng Du, Nan Duan, Shao-Yen Tseng, Vasudev Lal, Yongfei Liu","submitted_at":"2022-03-30T05:25:35Z","abstract_excerpt":"Breakthroughs in transformer-based models have revolutionized not only the NLP field, but also vision and multimodal systems. However, although visualization and interpretability tools have become available for NLP models, internal mechanisms of vision and multimodal transformers remain largely opaque. With the success of these transformers, it is increasingly critical to understand their inner workings, as unraveling these black-boxes will lead to more capable and trustworthy models. To contribute to this quest, we propose VL-InterpreT, which provides novel interactive visualizations for inte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.17247","kind":"arxiv","version":3},"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/2203.17247/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":"2203.17247","created_at":"2026-07-05T04:50:33.944625+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.17247v3","created_at":"2026-07-05T04:50:33.944625+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.17247","created_at":"2026-07-05T04:50:33.944625+00:00"},{"alias_kind":"pith_short_12","alias_value":"XMPFMOE4QLCD","created_at":"2026-07-05T04:50:33.944625+00:00"},{"alias_kind":"pith_short_16","alias_value":"XMPFMOE4QLCDVNOG","created_at":"2026-07-05T04:50:33.944625+00:00"},{"alias_kind":"pith_short_8","alias_value":"XMPFMOE4","created_at":"2026-07-05T04:50:33.944625+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.04427","citing_title":"Decoding the Multimodal Maze: A Systematic Review on the Adoption of Explainability in Multimodal Attention-based Models","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XMPFMOE4QLCDVNOGHSDPSFP37X","json":"https://pith.science/pith/XMPFMOE4QLCDVNOGHSDPSFP37X.json","graph_json":"https://pith.science/api/pith-number/XMPFMOE4QLCDVNOGHSDPSFP37X/graph.json","events_json":"https://pith.science/api/pith-number/XMPFMOE4QLCDVNOGHSDPSFP37X/events.json","paper":"https://pith.science/paper/XMPFMOE4"},"agent_actions":{"view_html":"https://pith.science/pith/XMPFMOE4QLCDVNOGHSDPSFP37X","download_json":"https://pith.science/pith/XMPFMOE4QLCDVNOGHSDPSFP37X.json","view_paper":"https://pith.science/paper/XMPFMOE4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.17247&json=true","fetch_graph":"https://pith.science/api/pith-number/XMPFMOE4QLCDVNOGHSDPSFP37X/graph.json","fetch_events":"https://pith.science/api/pith-number/XMPFMOE4QLCDVNOGHSDPSFP37X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XMPFMOE4QLCDVNOGHSDPSFP37X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XMPFMOE4QLCDVNOGHSDPSFP37X/action/storage_attestation","attest_author":"https://pith.science/pith/XMPFMOE4QLCDVNOGHSDPSFP37X/action/author_attestation","sign_citation":"https://pith.science/pith/XMPFMOE4QLCDVNOGHSDPSFP37X/action/citation_signature","submit_replication":"https://pith.science/pith/XMPFMOE4QLCDVNOGHSDPSFP37X/action/replication_record"}},"created_at":"2026-07-05T04:50:33.944625+00:00","updated_at":"2026-07-05T04:50:33.944625+00:00"}