{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DA2NFOWIXT3AUSSEXD5L4JVRE5","short_pith_number":"pith:DA2NFOWI","schema_version":"1.0","canonical_sha256":"1834d2bac8bcf60a4a44b8fabe26b12762faf26b098c41922705177b478e2589","source":{"kind":"arxiv","id":"1908.07795","version":2},"attestation_state":"computed","paper":{"title":"Dialog State Tracking with Reinforced Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Lifeng Shang, Qun Liu, Xiao Chen, Xin Jiang, Yichun Yin","submitted_at":"2019-08-21T11:07:14Z","abstract_excerpt":"Neural dialog state trackers are generally limited due to the lack of quantity and diversity of annotated training data. In this paper, we address this difficulty by proposing a reinforcement learning (RL) based framework for data augmentation that can generate high-quality data to improve the neural state tracker. Specifically, we introduce a novel contextual bandit generator to learn fine-grained augmentation policies that can generate new effective instances by choosing suitable replacements for the specific context. Moreover, by alternately learning between the generator and the state trac"},"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":"1908.07795","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-21T11:07:14Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c2a8cb3425ff2262a9249735012a6bdca5870080806f17bea9f47cf0c00c0c5d","abstract_canon_sha256":"ed4e50ba2e540915dfa151768a8e48727caa837ea7692e5ae5db3f0bc888f1ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:19:37.578058Z","signature_b64":"HGaFHVnThmwNg3/IlAJL6PSaHLPXjjak2gvGR7nfgR8+w7ov7F12XYQdGKFnWFHRS25ti8WpE3LboG7FwhefCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1834d2bac8bcf60a4a44b8fabe26b12762faf26b098c41922705177b478e2589","last_reissued_at":"2026-07-05T00:19:37.577574Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:19:37.577574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dialog State Tracking with Reinforced Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Lifeng Shang, Qun Liu, Xiao Chen, Xin Jiang, Yichun Yin","submitted_at":"2019-08-21T11:07:14Z","abstract_excerpt":"Neural dialog state trackers are generally limited due to the lack of quantity and diversity of annotated training data. In this paper, we address this difficulty by proposing a reinforcement learning (RL) based framework for data augmentation that can generate high-quality data to improve the neural state tracker. Specifically, we introduce a novel contextual bandit generator to learn fine-grained augmentation policies that can generate new effective instances by choosing suitable replacements for the specific context. Moreover, by alternately learning between the generator and the state trac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.07795","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.07795/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1908.07795","created_at":"2026-07-05T00:19:37.577635+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.07795v2","created_at":"2026-07-05T00:19:37.577635+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.07795","created_at":"2026-07-05T00:19:37.577635+00:00"},{"alias_kind":"pith_short_12","alias_value":"DA2NFOWIXT3A","created_at":"2026-07-05T00:19:37.577635+00:00"},{"alias_kind":"pith_short_16","alias_value":"DA2NFOWIXT3AUSSE","created_at":"2026-07-05T00:19:37.577635+00:00"},{"alias_kind":"pith_short_8","alias_value":"DA2NFOWI","created_at":"2026-07-05T00:19:37.577635+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/DA2NFOWIXT3AUSSEXD5L4JVRE5","json":"https://pith.science/pith/DA2NFOWIXT3AUSSEXD5L4JVRE5.json","graph_json":"https://pith.science/api/pith-number/DA2NFOWIXT3AUSSEXD5L4JVRE5/graph.json","events_json":"https://pith.science/api/pith-number/DA2NFOWIXT3AUSSEXD5L4JVRE5/events.json","paper":"https://pith.science/paper/DA2NFOWI"},"agent_actions":{"view_html":"https://pith.science/pith/DA2NFOWIXT3AUSSEXD5L4JVRE5","download_json":"https://pith.science/pith/DA2NFOWIXT3AUSSEXD5L4JVRE5.json","view_paper":"https://pith.science/paper/DA2NFOWI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.07795&json=true","fetch_graph":"https://pith.science/api/pith-number/DA2NFOWIXT3AUSSEXD5L4JVRE5/graph.json","fetch_events":"https://pith.science/api/pith-number/DA2NFOWIXT3AUSSEXD5L4JVRE5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DA2NFOWIXT3AUSSEXD5L4JVRE5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DA2NFOWIXT3AUSSEXD5L4JVRE5/action/storage_attestation","attest_author":"https://pith.science/pith/DA2NFOWIXT3AUSSEXD5L4JVRE5/action/author_attestation","sign_citation":"https://pith.science/pith/DA2NFOWIXT3AUSSEXD5L4JVRE5/action/citation_signature","submit_replication":"https://pith.science/pith/DA2NFOWIXT3AUSSEXD5L4JVRE5/action/replication_record"}},"created_at":"2026-07-05T00:19:37.577635+00:00","updated_at":"2026-07-05T00:19:37.577635+00:00"}