{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:MYGKMJKI4QHD77FH6PYJ7PMMHX","short_pith_number":"pith:MYGKMJKI","canonical_record":{"source":{"id":"1907.10500","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-07-24T15:08:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"22a8b07705d6c765bc3705a7502d03842d691c3754ed4828dd1514f6eb8c77f9","abstract_canon_sha256":"91a2d2982ab3ad6a5b3d0f2270d2445716d3b6f5d5054b8f65328e546bae119c"},"schema_version":"1.0"},"canonical_sha256":"660ca62548e40e3ffca7f3f09fbd8c3df1c6634011d28dcfa11a6f4b0df0a12d","source":{"kind":"arxiv","id":"1907.10500","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.10500","created_at":"2026-05-17T23:39:37Z"},{"alias_kind":"arxiv_version","alias_value":"1907.10500v1","created_at":"2026-05-17T23:39:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.10500","created_at":"2026-05-17T23:39:37Z"},{"alias_kind":"pith_short_12","alias_value":"MYGKMJKI4QHD","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"MYGKMJKI4QHD77FH","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"MYGKMJKI","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:MYGKMJKI4QHD77FH6PYJ7PMMHX","target":"record","payload":{"canonical_record":{"source":{"id":"1907.10500","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-07-24T15:08:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"22a8b07705d6c765bc3705a7502d03842d691c3754ed4828dd1514f6eb8c77f9","abstract_canon_sha256":"91a2d2982ab3ad6a5b3d0f2270d2445716d3b6f5d5054b8f65328e546bae119c"},"schema_version":"1.0"},"canonical_sha256":"660ca62548e40e3ffca7f3f09fbd8c3df1c6634011d28dcfa11a6f4b0df0a12d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:37.741396Z","signature_b64":"VVnLvFq5un0X/s6d9xCLXunHosQXkj6iEe3rCdz2O4kviE1sSKZPKsOFBNW9dp4I9gQwbOO4sgDrQvszZxAyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"660ca62548e40e3ffca7f3f09fbd8c3df1c6634011d28dcfa11a6f4b0df0a12d","last_reissued_at":"2026-05-17T23:39:37.740757Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:37.740757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.10500","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K6hvgPkglgmHAyqXoafv7vwkzaa+lWisADUylf/10y/RxIGd2/9dzWoKMlTaVVTMq3T33WswoMo8hEWDiS4JDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T16:51:23.969492Z"},"content_sha256":"4a09d7312badb2261f2f694e0c7cfb2c1fbe9e0730c31ddf394d1fa1633a76b9","schema_version":"1.0","event_id":"sha256:4a09d7312badb2261f2f694e0c7cfb2c1fbe9e0730c31ddf394d1fa1633a76b9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:MYGKMJKI4QHD77FH6PYJ7PMMHX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Goal-Oriented Visual Dialog Agents: Imitating and Surpassing Analytic Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Wen-Hsiao Peng, Yen-Wei Chang","submitted_at":"2019-07-24T15:08:38Z","abstract_excerpt":"This paper tackles the problem of learning a questioner in the goal-oriented visual dialog task. Several previous works adopt model-free reinforcement learning. Most pretrain the model from a finite set of human-generated data. We argue that using limited demonstrations to kick-start the questioner is insufficient due to the large policy search space. Inspired by a recently proposed information theoretic approach, we develop two analytic experts to serve as a source of high-quality demonstrations for imitation learning. We then take advantage of reinforcement learning to refine the model towar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.10500","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EG8VX57ijIwTCGkK61izFotvTYvWy8PMfRPFLZzm+WiY0Eel+C9bKCWXk+0zjhpVE+3SYG8tk0j6F///GBMGAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T16:51:23.970177Z"},"content_sha256":"35778db853f13850b0b559357bc7abaf58e111a75a793bdcab8555341a92f6d1","schema_version":"1.0","event_id":"sha256:35778db853f13850b0b559357bc7abaf58e111a75a793bdcab8555341a92f6d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MYGKMJKI4QHD77FH6PYJ7PMMHX/bundle.json","state_url":"https://pith.science/pith/MYGKMJKI4QHD77FH6PYJ7PMMHX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MYGKMJKI4QHD77FH6PYJ7PMMHX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T16:51:23Z","links":{"resolver":"https://pith.science/pith/MYGKMJKI4QHD77FH6PYJ7PMMHX","bundle":"https://pith.science/pith/MYGKMJKI4QHD77FH6PYJ7PMMHX/bundle.json","state":"https://pith.science/pith/MYGKMJKI4QHD77FH6PYJ7PMMHX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MYGKMJKI4QHD77FH6PYJ7PMMHX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:MYGKMJKI4QHD77FH6PYJ7PMMHX","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":"91a2d2982ab3ad6a5b3d0f2270d2445716d3b6f5d5054b8f65328e546bae119c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-07-24T15:08:38Z","title_canon_sha256":"22a8b07705d6c765bc3705a7502d03842d691c3754ed4828dd1514f6eb8c77f9"},"schema_version":"1.0","source":{"id":"1907.10500","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.10500","created_at":"2026-05-17T23:39:37Z"},{"alias_kind":"arxiv_version","alias_value":"1907.10500v1","created_at":"2026-05-17T23:39:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.10500","created_at":"2026-05-17T23:39:37Z"},{"alias_kind":"pith_short_12","alias_value":"MYGKMJKI4QHD","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"MYGKMJKI4QHD77FH","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"MYGKMJKI","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:35778db853f13850b0b559357bc7abaf58e111a75a793bdcab8555341a92f6d1","target":"graph","created_at":"2026-05-17T23:39:37Z","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":"This paper tackles the problem of learning a questioner in the goal-oriented visual dialog task. Several previous works adopt model-free reinforcement learning. Most pretrain the model from a finite set of human-generated data. We argue that using limited demonstrations to kick-start the questioner is insufficient due to the large policy search space. Inspired by a recently proposed information theoretic approach, we develop two analytic experts to serve as a source of high-quality demonstrations for imitation learning. We then take advantage of reinforcement learning to refine the model towar","authors_text":"Wen-Hsiao Peng, Yen-Wei Chang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-07-24T15:08:38Z","title":"Learning Goal-Oriented Visual Dialog Agents: Imitating and Surpassing Analytic Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.10500","kind":"arxiv","version":1},"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":"sha256:4a09d7312badb2261f2f694e0c7cfb2c1fbe9e0730c31ddf394d1fa1633a76b9","target":"record","created_at":"2026-05-17T23:39:37Z","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":"91a2d2982ab3ad6a5b3d0f2270d2445716d3b6f5d5054b8f65328e546bae119c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-07-24T15:08:38Z","title_canon_sha256":"22a8b07705d6c765bc3705a7502d03842d691c3754ed4828dd1514f6eb8c77f9"},"schema_version":"1.0","source":{"id":"1907.10500","kind":"arxiv","version":1}},"canonical_sha256":"660ca62548e40e3ffca7f3f09fbd8c3df1c6634011d28dcfa11a6f4b0df0a12d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"660ca62548e40e3ffca7f3f09fbd8c3df1c6634011d28dcfa11a6f4b0df0a12d","first_computed_at":"2026-05-17T23:39:37.740757Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:37.740757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VVnLvFq5un0X/s6d9xCLXunHosQXkj6iEe3rCdz2O4kviE1sSKZPKsOFBNW9dp4I9gQwbOO4sgDrQvszZxAyBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:37.741396Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.10500","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a09d7312badb2261f2f694e0c7cfb2c1fbe9e0730c31ddf394d1fa1633a76b9","sha256:35778db853f13850b0b559357bc7abaf58e111a75a793bdcab8555341a92f6d1"],"state_sha256":"07a48c978e6424075bfed75b0bb84f05d867705dc9cf29ce6f8bf675cf2198c3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AF2MCR0pxsqIJpmQYOiP5tZIRvvXh7mxxp5ipZw2tEOn0LuHeqUAFI3z6G3y8ChpGwBHYDZB4j5cQ11/JpO5CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T16:51:23.973806Z","bundle_sha256":"3f9c2331850f29abc6fbb6c9c3edd34c89e40011ccc303cf90dafaee0e9d73bd"}}