{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:Z5NSCYVQACX3CJR7ZQ7DHS5L4D","short_pith_number":"pith:Z5NSCYVQ","schema_version":"1.0","canonical_sha256":"cf5b2162b000afb1263fcc3e33cbabe0c8013b5a071b266671844750b6ab3592","source":{"kind":"arxiv","id":"1703.06585","version":2},"attestation_state":"computed","paper":{"title":"Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning","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, Dhruv Batra, Jos\\'e M. F. Moura, Satwik Kottur, Stefan Lee","submitted_at":"2017-03-20T03:50:57Z","abstract_excerpt":"We introduce the first goal-driven training for visual question answering and dialog agents. Specifically, we pose a cooperative 'image guessing' game between two agents -- Qbot and Abot -- who communicate in natural language dialog so that Qbot can select an unseen image from a lineup of images. We use deep reinforcement learning (RL) to learn the policies of these agents end-to-end -- from pixels to multi-agent multi-round dialog to game reward.\n  We demonstrate two experimental results.\n  First, as a 'sanity check' demonstration of pure RL (from scratch), we show results on a synthetic worl"},"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":"1703.06585","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-20T03:50:57Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"a6cd357c285594e2fe1e62a8f00a82272eee7d9769d3b449058eb81819599428","abstract_canon_sha256":"2ca34f645961a1b3497b9e1eae0ec97bd764e94d2e79a4d99b77d9de9ef6e571"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:14.048887Z","signature_b64":"FxXGpdR4t1INRCgrzxrMX+V3x/PwLypIT/qeuXjG6VtYCLcUuY12ffqORE20o5ekdVL9tNmOSMixB5qqP7AWAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf5b2162b000afb1263fcc3e33cbabe0c8013b5a071b266671844750b6ab3592","last_reissued_at":"2026-05-18T00:48:14.048143Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:14.048143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning","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, Dhruv Batra, Jos\\'e M. F. Moura, Satwik Kottur, Stefan Lee","submitted_at":"2017-03-20T03:50:57Z","abstract_excerpt":"We introduce the first goal-driven training for visual question answering and dialog agents. Specifically, we pose a cooperative 'image guessing' game between two agents -- Qbot and Abot -- who communicate in natural language dialog so that Qbot can select an unseen image from a lineup of images. We use deep reinforcement learning (RL) to learn the policies of these agents end-to-end -- from pixels to multi-agent multi-round dialog to game reward.\n  We demonstrate two experimental results.\n  First, as a 'sanity check' demonstration of pure RL (from scratch), we show results on a synthetic worl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.06585","kind":"arxiv","version":2},"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":"1703.06585","created_at":"2026-05-18T00:48:14.048279+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.06585v2","created_at":"2026-05-18T00:48:14.048279+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.06585","created_at":"2026-05-18T00:48:14.048279+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z5NSCYVQACX3","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z5NSCYVQACX3CJR7","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z5NSCYVQ","created_at":"2026-05-18T12:31:59.375834+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/Z5NSCYVQACX3CJR7ZQ7DHS5L4D","json":"https://pith.science/pith/Z5NSCYVQACX3CJR7ZQ7DHS5L4D.json","graph_json":"https://pith.science/api/pith-number/Z5NSCYVQACX3CJR7ZQ7DHS5L4D/graph.json","events_json":"https://pith.science/api/pith-number/Z5NSCYVQACX3CJR7ZQ7DHS5L4D/events.json","paper":"https://pith.science/paper/Z5NSCYVQ"},"agent_actions":{"view_html":"https://pith.science/pith/Z5NSCYVQACX3CJR7ZQ7DHS5L4D","download_json":"https://pith.science/pith/Z5NSCYVQACX3CJR7ZQ7DHS5L4D.json","view_paper":"https://pith.science/paper/Z5NSCYVQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.06585&json=true","fetch_graph":"https://pith.science/api/pith-number/Z5NSCYVQACX3CJR7ZQ7DHS5L4D/graph.json","fetch_events":"https://pith.science/api/pith-number/Z5NSCYVQACX3CJR7ZQ7DHS5L4D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z5NSCYVQACX3CJR7ZQ7DHS5L4D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z5NSCYVQACX3CJR7ZQ7DHS5L4D/action/storage_attestation","attest_author":"https://pith.science/pith/Z5NSCYVQACX3CJR7ZQ7DHS5L4D/action/author_attestation","sign_citation":"https://pith.science/pith/Z5NSCYVQACX3CJR7ZQ7DHS5L4D/action/citation_signature","submit_replication":"https://pith.science/pith/Z5NSCYVQACX3CJR7ZQ7DHS5L4D/action/replication_record"}},"created_at":"2026-05-18T00:48:14.048279+00:00","updated_at":"2026-05-18T00:48:14.048279+00:00"}