{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:KICYMYFJAIDRIYFMOZ53SL2S5Z","short_pith_number":"pith:KICYMYFJ","schema_version":"1.0","canonical_sha256":"52058660a902071460ac767bb92f52ee7e70d5a4cafdfd6413b3976afb5da389","source":{"kind":"arxiv","id":"1611.08669","version":5},"attestation_state":"computed","paper":{"title":"Visual Dialog","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhishek Das, Avi Singh, Deshraj Yadav, Devi Parikh, Dhruv Batra, Jos\\'e M. F. Moura, Khushi Gupta, Satwik Kottur","submitted_at":"2016-11-26T06:39:28Z","abstract_excerpt":"We introduce the task of Visual Dialog, which requires an AI agent to hold a meaningful dialog with humans in natural, conversational language about visual content. Specifically, given an image, a dialog history, and a question about the image, the agent has to ground the question in image, infer context from history, and answer the question accurately. Visual Dialog is disentangled enough from a specific downstream task so as to serve as a general test of machine intelligence, while being grounded in vision enough to allow objective evaluation of individual responses and benchmark progress. W"},"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":"1611.08669","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-26T06:39:28Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"52819b7051bc973cec91a2c98808607f082acc87f9f968adab97c3b11de548df","abstract_canon_sha256":"3938cb39c7d79127aaab5d798ea918c55bc85e52852883a5d6e5d01e7aa5107f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:46.415739Z","signature_b64":"26opXH7Q3PDZ+h/e31V7P9MuPzjnNS67ezizyaej/YwlvAPI0UYZyBu0Q8uZnoWzifwAbxSvuAuL5eJn7KgVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52058660a902071460ac767bb92f52ee7e70d5a4cafdfd6413b3976afb5da389","last_reissued_at":"2026-05-18T00:38:46.415073Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:46.415073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Dialog","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhishek Das, Avi Singh, Deshraj Yadav, Devi Parikh, Dhruv Batra, Jos\\'e M. F. Moura, Khushi Gupta, Satwik Kottur","submitted_at":"2016-11-26T06:39:28Z","abstract_excerpt":"We introduce the task of Visual Dialog, which requires an AI agent to hold a meaningful dialog with humans in natural, conversational language about visual content. Specifically, given an image, a dialog history, and a question about the image, the agent has to ground the question in image, infer context from history, and answer the question accurately. Visual Dialog is disentangled enough from a specific downstream task so as to serve as a general test of machine intelligence, while being grounded in vision enough to allow objective evaluation of individual responses and benchmark progress. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.08669","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1611.08669","created_at":"2026-05-18T00:38:46.415184+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.08669v5","created_at":"2026-05-18T00:38:46.415184+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.08669","created_at":"2026-05-18T00:38:46.415184+00:00"},{"alias_kind":"pith_short_12","alias_value":"KICYMYFJAIDR","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_16","alias_value":"KICYMYFJAIDRIYFM","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_8","alias_value":"KICYMYFJ","created_at":"2026-05-18T12:30:25.849896+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/KICYMYFJAIDRIYFMOZ53SL2S5Z","json":"https://pith.science/pith/KICYMYFJAIDRIYFMOZ53SL2S5Z.json","graph_json":"https://pith.science/api/pith-number/KICYMYFJAIDRIYFMOZ53SL2S5Z/graph.json","events_json":"https://pith.science/api/pith-number/KICYMYFJAIDRIYFMOZ53SL2S5Z/events.json","paper":"https://pith.science/paper/KICYMYFJ"},"agent_actions":{"view_html":"https://pith.science/pith/KICYMYFJAIDRIYFMOZ53SL2S5Z","download_json":"https://pith.science/pith/KICYMYFJAIDRIYFMOZ53SL2S5Z.json","view_paper":"https://pith.science/paper/KICYMYFJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.08669&json=true","fetch_graph":"https://pith.science/api/pith-number/KICYMYFJAIDRIYFMOZ53SL2S5Z/graph.json","fetch_events":"https://pith.science/api/pith-number/KICYMYFJAIDRIYFMOZ53SL2S5Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KICYMYFJAIDRIYFMOZ53SL2S5Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KICYMYFJAIDRIYFMOZ53SL2S5Z/action/storage_attestation","attest_author":"https://pith.science/pith/KICYMYFJAIDRIYFMOZ53SL2S5Z/action/author_attestation","sign_citation":"https://pith.science/pith/KICYMYFJAIDRIYFMOZ53SL2S5Z/action/citation_signature","submit_replication":"https://pith.science/pith/KICYMYFJAIDRIYFMOZ53SL2S5Z/action/replication_record"}},"created_at":"2026-05-18T00:38:46.415184+00:00","updated_at":"2026-05-18T00:38:46.415184+00:00"}