{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:Z5NSCYVQACX3CJR7ZQ7DHS5L4D","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2ca34f645961a1b3497b9e1eae0ec97bd764e94d2e79a4d99b77d9de9ef6e571","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-20T03:50:57Z","title_canon_sha256":"a6cd357c285594e2fe1e62a8f00a82272eee7d9769d3b449058eb81819599428"},"schema_version":"1.0","source":{"id":"1703.06585","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.06585","created_at":"2026-05-18T00:48:14Z"},{"alias_kind":"arxiv_version","alias_value":"1703.06585v2","created_at":"2026-05-18T00:48:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.06585","created_at":"2026-05-18T00:48:14Z"},{"alias_kind":"pith_short_12","alias_value":"Z5NSCYVQACX3","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"Z5NSCYVQACX3CJR7","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"Z5NSCYVQ","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:bfdc256ff3c52a0020dc6656e527ebbb2b2ad1e54c5d40a156b2f0996da69d16","target":"graph","created_at":"2026-05-18T00:48:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Abhishek Das, Dhruv Batra, Jos\\'e M. F. Moura, Satwik Kottur, Stefan Lee","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-20T03:50:57Z","title":"Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.06585","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0fe8845d669004a5ab2f2f4f0cc853855b866acd49b79553bb51ae4b027aea1e","target":"record","created_at":"2026-05-18T00:48:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2ca34f645961a1b3497b9e1eae0ec97bd764e94d2e79a4d99b77d9de9ef6e571","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-20T03:50:57Z","title_canon_sha256":"a6cd357c285594e2fe1e62a8f00a82272eee7d9769d3b449058eb81819599428"},"schema_version":"1.0","source":{"id":"1703.06585","kind":"arxiv","version":2}},"canonical_sha256":"cf5b2162b000afb1263fcc3e33cbabe0c8013b5a071b266671844750b6ab3592","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf5b2162b000afb1263fcc3e33cbabe0c8013b5a071b266671844750b6ab3592","first_computed_at":"2026-05-18T00:48:14.048143Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:48:14.048143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FxXGpdR4t1INRCgrzxrMX+V3x/PwLypIT/qeuXjG6VtYCLcUuY12ffqORE20o5ekdVL9tNmOSMixB5qqP7AWAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:48:14.048887Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.06585","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0fe8845d669004a5ab2f2f4f0cc853855b866acd49b79553bb51ae4b027aea1e","sha256:bfdc256ff3c52a0020dc6656e527ebbb2b2ad1e54c5d40a156b2f0996da69d16"],"state_sha256":"76e0953e8a909d66960d0b4d18e180341bcf7b0f8b4e592e867ddcb3c8b8d449"}