{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ICYFH7AL2AC4DXB24PURJNFIUN","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":"e926a9a1c4dfc3e63739136948f9bc6ae45fa1ef444210af2c49871c69a76fb5","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-23T10:22:16Z","title_canon_sha256":"e24b6a6bd566787c762553e54001fb29057d55f38fc8cdadd72883139f1a1d68"},"schema_version":"1.0","source":{"id":"2004.11054","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.11054","created_at":"2026-07-05T01:26:51Z"},{"alias_kind":"arxiv_version","alias_value":"2004.11054v2","created_at":"2026-07-05T01:26:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.11054","created_at":"2026-07-05T01:26:51Z"},{"alias_kind":"pith_short_12","alias_value":"ICYFH7AL2AC4","created_at":"2026-07-05T01:26:51Z"},{"alias_kind":"pith_short_16","alias_value":"ICYFH7AL2AC4DXB2","created_at":"2026-07-05T01:26:51Z"},{"alias_kind":"pith_short_8","alias_value":"ICYFH7AL","created_at":"2026-07-05T01:26:51Z"}],"graph_snapshots":[{"event_id":"sha256:9e88771326f5281c2e1d92cafd1a6f1162c2a46690f6d34c8c958a8ba8775a43","target":"graph","created_at":"2026-07-05T01:26:51Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2004.11054/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning is a promising approach to training a dialog manager, but current methods struggle with the large state and action spaces of multi-domain dialog systems. Building upon Deep Q-learning from Demonstrations (DQfD), an algorithm that scores highly in difficult Atari games, we leverage dialog data to guide the agent to successfully respond to a user's requests. We make progressively fewer assumptions about the data needed, using labeled, reduced-labeled, and even unlabeled data to train expert demonstrators. We introduce Reinforced Fine-tune Learning, an extension to DQf","authors_text":"Gabriel Gordon-Hall, Philip John Gorinski, Shay B. Cohen","cross_cats":["cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-23T10:22:16Z","title":"Learning Dialog Policies from Weak Demonstrations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.11054","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:a633e93790eab3fe21dacd5f8755cd456fb0b2e61703c5078375ea7c7b3334b2","target":"record","created_at":"2026-07-05T01:26:51Z","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":"e926a9a1c4dfc3e63739136948f9bc6ae45fa1ef444210af2c49871c69a76fb5","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-23T10:22:16Z","title_canon_sha256":"e24b6a6bd566787c762553e54001fb29057d55f38fc8cdadd72883139f1a1d68"},"schema_version":"1.0","source":{"id":"2004.11054","kind":"arxiv","version":2}},"canonical_sha256":"40b053fc0bd005c1dc3ae3e914b4a8a35fdda659280837067dab709c76c3edc2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40b053fc0bd005c1dc3ae3e914b4a8a35fdda659280837067dab709c76c3edc2","first_computed_at":"2026-07-05T01:26:51.716834Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:26:51.716834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EuRx+DVHs8HASANLd5fIUI6tYTMZNdEfa3MKUfhWIB33SYj9t2fmBQD3yvwhtHznpH2M8PohGGTRbIBnBIHqDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:26:51.717373Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.11054","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a633e93790eab3fe21dacd5f8755cd456fb0b2e61703c5078375ea7c7b3334b2","sha256:9e88771326f5281c2e1d92cafd1a6f1162c2a46690f6d34c8c958a8ba8775a43"],"state_sha256":"c141abca05944e6f15404b9debd1df02096be8ba2076c529a6d233593b04ae96"}