{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5TVJWQ7RDBP4TZQRU4B3BLXHEP","short_pith_number":"pith:5TVJWQ7R","schema_version":"1.0","canonical_sha256":"ecea9b43f1185fc9e611a703b0aee723c672ab5c12cc2451346bcbeed5060895","source":{"kind":"arxiv","id":"2207.05703","version":1},"attestation_state":"computed","paper":{"title":"Tell Me the Evidence? Dual Visual-Linguistic Interaction for Answer Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Bian, Guanlin Chen, Jiexiang Wang, Junwen Pan, Pengfei Zhu, Yi Liu, Zhicheng Zhang","submitted_at":"2022-06-21T03:15:27Z","abstract_excerpt":"Answer grounding aims to reveal the visual evidence for visual question answering (VQA), which entails highlighting relevant positions in the image when answering questions about images. Previous attempts typically tackle this problem using pretrained object detectors, but without the flexibility for objects not in the predefined vocabulary. However, these black-box methods solely concentrate on the linguistic generation, ignoring the visual interpretability. In this paper, we propose Dual Visual-Linguistic Interaction (DaVI), a novel unified end-to-end framework with the capability for both l"},"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":"2207.05703","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-21T03:15:27Z","cross_cats_sorted":[],"title_canon_sha256":"b1db50e6e3ce68b26921b9b26a577cb3584b5fea188f404a83fdf590e81ceffe","abstract_canon_sha256":"939b02f21c650440ab82a2f54b44226fc371454c7ecb98c36edb5851b2793947"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:39:45.752875Z","signature_b64":"JQQ75MbClozj9TtLoK3n3+2jl7s5DUANHKK0F/0F1lswTXGaOfqu0oTfZj7DcCXMG2uzqtTd1El8Xx47NXSfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecea9b43f1185fc9e611a703b0aee723c672ab5c12cc2451346bcbeed5060895","last_reissued_at":"2026-07-05T04:39:45.752545Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:39:45.752545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tell Me the Evidence? Dual Visual-Linguistic Interaction for Answer Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Bian, Guanlin Chen, Jiexiang Wang, Junwen Pan, Pengfei Zhu, Yi Liu, Zhicheng Zhang","submitted_at":"2022-06-21T03:15:27Z","abstract_excerpt":"Answer grounding aims to reveal the visual evidence for visual question answering (VQA), which entails highlighting relevant positions in the image when answering questions about images. Previous attempts typically tackle this problem using pretrained object detectors, but without the flexibility for objects not in the predefined vocabulary. However, these black-box methods solely concentrate on the linguistic generation, ignoring the visual interpretability. In this paper, we propose Dual Visual-Linguistic Interaction (DaVI), a novel unified end-to-end framework with the capability for both l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.05703","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/2207.05703/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":"2207.05703","created_at":"2026-07-05T04:39:45.752599+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.05703v1","created_at":"2026-07-05T04:39:45.752599+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.05703","created_at":"2026-07-05T04:39:45.752599+00:00"},{"alias_kind":"pith_short_12","alias_value":"5TVJWQ7RDBP4","created_at":"2026-07-05T04:39:45.752599+00:00"},{"alias_kind":"pith_short_16","alias_value":"5TVJWQ7RDBP4TZQR","created_at":"2026-07-05T04:39:45.752599+00:00"},{"alias_kind":"pith_short_8","alias_value":"5TVJWQ7R","created_at":"2026-07-05T04:39:45.752599+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/5TVJWQ7RDBP4TZQRU4B3BLXHEP","json":"https://pith.science/pith/5TVJWQ7RDBP4TZQRU4B3BLXHEP.json","graph_json":"https://pith.science/api/pith-number/5TVJWQ7RDBP4TZQRU4B3BLXHEP/graph.json","events_json":"https://pith.science/api/pith-number/5TVJWQ7RDBP4TZQRU4B3BLXHEP/events.json","paper":"https://pith.science/paper/5TVJWQ7R"},"agent_actions":{"view_html":"https://pith.science/pith/5TVJWQ7RDBP4TZQRU4B3BLXHEP","download_json":"https://pith.science/pith/5TVJWQ7RDBP4TZQRU4B3BLXHEP.json","view_paper":"https://pith.science/paper/5TVJWQ7R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.05703&json=true","fetch_graph":"https://pith.science/api/pith-number/5TVJWQ7RDBP4TZQRU4B3BLXHEP/graph.json","fetch_events":"https://pith.science/api/pith-number/5TVJWQ7RDBP4TZQRU4B3BLXHEP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5TVJWQ7RDBP4TZQRU4B3BLXHEP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5TVJWQ7RDBP4TZQRU4B3BLXHEP/action/storage_attestation","attest_author":"https://pith.science/pith/5TVJWQ7RDBP4TZQRU4B3BLXHEP/action/author_attestation","sign_citation":"https://pith.science/pith/5TVJWQ7RDBP4TZQRU4B3BLXHEP/action/citation_signature","submit_replication":"https://pith.science/pith/5TVJWQ7RDBP4TZQRU4B3BLXHEP/action/replication_record"}},"created_at":"2026-07-05T04:39:45.752599+00:00","updated_at":"2026-07-05T04:39:45.752599+00:00"}