{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MYGKMJKI4QHD77FH6PYJ7PMMHX","short_pith_number":"pith:MYGKMJKI","schema_version":"1.0","canonical_sha256":"660ca62548e40e3ffca7f3f09fbd8c3df1c6634011d28dcfa11a6f4b0df0a12d","source":{"kind":"arxiv","id":"1907.10500","version":1},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1907.10500","created_at":"2026-05-17T23:39:37.740860+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.10500v1","created_at":"2026-05-17T23:39:37.740860+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.10500","created_at":"2026-05-17T23:39:37.740860+00:00"},{"alias_kind":"pith_short_12","alias_value":"MYGKMJKI4QHD","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"MYGKMJKI4QHD77FH","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"MYGKMJKI","created_at":"2026-05-18T12:33:24.271573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.10500","citing_title":"Learning Goal-Oriented Visual Dialog Agents: Imitating and Surpassing Analytic Experts","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MYGKMJKI4QHD77FH6PYJ7PMMHX","json":"https://pith.science/pith/MYGKMJKI4QHD77FH6PYJ7PMMHX.json","graph_json":"https://pith.science/api/pith-number/MYGKMJKI4QHD77FH6PYJ7PMMHX/graph.json","events_json":"https://pith.science/api/pith-number/MYGKMJKI4QHD77FH6PYJ7PMMHX/events.json","paper":"https://pith.science/paper/MYGKMJKI"},"agent_actions":{"view_html":"https://pith.science/pith/MYGKMJKI4QHD77FH6PYJ7PMMHX","download_json":"https://pith.science/pith/MYGKMJKI4QHD77FH6PYJ7PMMHX.json","view_paper":"https://pith.science/paper/MYGKMJKI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.10500&json=true","fetch_graph":"https://pith.science/api/pith-number/MYGKMJKI4QHD77FH6PYJ7PMMHX/graph.json","fetch_events":"https://pith.science/api/pith-number/MYGKMJKI4QHD77FH6PYJ7PMMHX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MYGKMJKI4QHD77FH6PYJ7PMMHX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MYGKMJKI4QHD77FH6PYJ7PMMHX/action/storage_attestation","attest_author":"https://pith.science/pith/MYGKMJKI4QHD77FH6PYJ7PMMHX/action/author_attestation","sign_citation":"https://pith.science/pith/MYGKMJKI4QHD77FH6PYJ7PMMHX/action/citation_signature","submit_replication":"https://pith.science/pith/MYGKMJKI4QHD77FH6PYJ7PMMHX/action/replication_record"}},"created_at":"2026-05-17T23:39:37.740860+00:00","updated_at":"2026-05-17T23:39:37.740860+00:00"}