{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:2O4E4Y2EIGJSOO63IYKAN6PBEX","short_pith_number":"pith:2O4E4Y2E","schema_version":"1.0","canonical_sha256":"d3b84e63444193273bdb461406f9e125e5feb628a00f90a2b4e784c59596eac3","source":{"kind":"arxiv","id":"1805.01252","version":2},"attestation_state":"computed","paper":{"title":"Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Carolin Lawrence, Stefan Riezler","submitted_at":"2018-05-03T12:24:39Z","abstract_excerpt":"Counterfactual learning from human bandit feedback describes a scenario where user feedback on the quality of outputs of a historic system is logged and used to improve a target system. We show how to apply this learning framework to neural semantic parsing. From a machine learning perspective, the key challenge lies in a proper reweighting of the estimator so as to avoid known degeneracies in counterfactual learning, while still being applicable to stochastic gradient optimization. To conduct experiments with human users, we devise an easy-to-use interface to collect human feedback on semanti"},"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":"1805.01252","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-03T12:24:39Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"1e4f902ce09320df3ac93c3528eb2715f852863b354e6eeffda9f8977ab97ac5","abstract_canon_sha256":"898b6fb56ddad59c85cd1e4788e70dfe242338e9f79901c5f6160b60db8e1669"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:32.730581Z","signature_b64":"E72DNwAUQO04mmthhhWh+oqbkMqZMFHMCXDQPvzRU6YWfQMkws9pIxiINDTdr+5V2Khv/20fi6SKE46ZkZZGCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3b84e63444193273bdb461406f9e125e5feb628a00f90a2b4e784c59596eac3","last_reissued_at":"2026-05-17T23:59:32.729956Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:32.729956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Carolin Lawrence, Stefan Riezler","submitted_at":"2018-05-03T12:24:39Z","abstract_excerpt":"Counterfactual learning from human bandit feedback describes a scenario where user feedback on the quality of outputs of a historic system is logged and used to improve a target system. We show how to apply this learning framework to neural semantic parsing. From a machine learning perspective, the key challenge lies in a proper reweighting of the estimator so as to avoid known degeneracies in counterfactual learning, while still being applicable to stochastic gradient optimization. To conduct experiments with human users, we devise an easy-to-use interface to collect human feedback on semanti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.01252","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":""},"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":"1805.01252","created_at":"2026-05-17T23:59:32.730080+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.01252v2","created_at":"2026-05-17T23:59:32.730080+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.01252","created_at":"2026-05-17T23:59:32.730080+00:00"},{"alias_kind":"pith_short_12","alias_value":"2O4E4Y2EIGJS","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"2O4E4Y2EIGJSOO63","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"2O4E4Y2E","created_at":"2026-05-18T12:32:02.567920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2009.01325","citing_title":"Learning to summarize from human feedback","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2O4E4Y2EIGJSOO63IYKAN6PBEX","json":"https://pith.science/pith/2O4E4Y2EIGJSOO63IYKAN6PBEX.json","graph_json":"https://pith.science/api/pith-number/2O4E4Y2EIGJSOO63IYKAN6PBEX/graph.json","events_json":"https://pith.science/api/pith-number/2O4E4Y2EIGJSOO63IYKAN6PBEX/events.json","paper":"https://pith.science/paper/2O4E4Y2E"},"agent_actions":{"view_html":"https://pith.science/pith/2O4E4Y2EIGJSOO63IYKAN6PBEX","download_json":"https://pith.science/pith/2O4E4Y2EIGJSOO63IYKAN6PBEX.json","view_paper":"https://pith.science/paper/2O4E4Y2E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.01252&json=true","fetch_graph":"https://pith.science/api/pith-number/2O4E4Y2EIGJSOO63IYKAN6PBEX/graph.json","fetch_events":"https://pith.science/api/pith-number/2O4E4Y2EIGJSOO63IYKAN6PBEX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2O4E4Y2EIGJSOO63IYKAN6PBEX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2O4E4Y2EIGJSOO63IYKAN6PBEX/action/storage_attestation","attest_author":"https://pith.science/pith/2O4E4Y2EIGJSOO63IYKAN6PBEX/action/author_attestation","sign_citation":"https://pith.science/pith/2O4E4Y2EIGJSOO63IYKAN6PBEX/action/citation_signature","submit_replication":"https://pith.science/pith/2O4E4Y2EIGJSOO63IYKAN6PBEX/action/replication_record"}},"created_at":"2026-05-17T23:59:32.730080+00:00","updated_at":"2026-05-17T23:59:32.730080+00:00"}