{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:QOB6OEMENFHG3B7CLE4CGUNVWO","short_pith_number":"pith:QOB6OEME","schema_version":"1.0","canonical_sha256":"8383e71184694e6d87e259382351b5b3b8971c51797fdefb68bebc6e0afbb81b","source":{"kind":"arxiv","id":"1901.03729","version":1},"attestation_state":"computed","paper":{"title":"Automated Rationale Generation: A Technique for Explainable AI and its Effects on Human Perceptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.AI","authors_text":"Brent Harrison, Larry Chan, Mark Riedl, Pradyumna Tambwekar, Upol Ehsan","submitted_at":"2019-01-11T19:55:48Z","abstract_excerpt":"Automated rationale generation is an approach for real-time explanation generation whereby a computational model learns to translate an autonomous agent's internal state and action data representations into natural language. Training on human explanation data can enable agents to learn to generate human-like explanations for their behavior. In this paper, using the context of an agent that plays Frogger, we describe (a) how to collect a corpus of explanations, (b) how to train a neural rationale generator to produce different styles of rationales, and (c) how people perceive these rationales. "},"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":"1901.03729","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-01-11T19:55:48Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"20b3d14c057b365a0acccf0da2d685f2f7fabc4bf45fd45948dc55e6d89da94a","abstract_canon_sha256":"99b98fac395fd62ec21d3d21bba1a3e80e2effcf2c9315c590c974c9f7421bc4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:27.153995Z","signature_b64":"xTfCpU+SB+RxoM7XxBwPJrLpy4nTkTK87qexFUTuwiVgNcficPGvbqtZSjUDjVJd7YdCnKPK2ZbwIEsMn9EYDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8383e71184694e6d87e259382351b5b3b8971c51797fdefb68bebc6e0afbb81b","last_reissued_at":"2026-05-17T23:56:27.153601Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:27.153601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automated Rationale Generation: A Technique for Explainable AI and its Effects on Human Perceptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.AI","authors_text":"Brent Harrison, Larry Chan, Mark Riedl, Pradyumna Tambwekar, Upol Ehsan","submitted_at":"2019-01-11T19:55:48Z","abstract_excerpt":"Automated rationale generation is an approach for real-time explanation generation whereby a computational model learns to translate an autonomous agent's internal state and action data representations into natural language. Training on human explanation data can enable agents to learn to generate human-like explanations for their behavior. In this paper, using the context of an agent that plays Frogger, we describe (a) how to collect a corpus of explanations, (b) how to train a neural rationale generator to produce different styles of rationales, and (c) how people perceive these rationales. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.03729","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":"1901.03729","created_at":"2026-05-17T23:56:27.153671+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.03729v1","created_at":"2026-05-17T23:56:27.153671+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.03729","created_at":"2026-05-17T23:56:27.153671+00:00"},{"alias_kind":"pith_short_12","alias_value":"QOB6OEMENFHG","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"QOB6OEMENFHG3B7C","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"QOB6OEME","created_at":"2026-05-18T12:33:27.125529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.03869","citing_title":"Unexplainability and Incomprehensibility of Artificial Intelligence","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QOB6OEMENFHG3B7CLE4CGUNVWO","json":"https://pith.science/pith/QOB6OEMENFHG3B7CLE4CGUNVWO.json","graph_json":"https://pith.science/api/pith-number/QOB6OEMENFHG3B7CLE4CGUNVWO/graph.json","events_json":"https://pith.science/api/pith-number/QOB6OEMENFHG3B7CLE4CGUNVWO/events.json","paper":"https://pith.science/paper/QOB6OEME"},"agent_actions":{"view_html":"https://pith.science/pith/QOB6OEMENFHG3B7CLE4CGUNVWO","download_json":"https://pith.science/pith/QOB6OEMENFHG3B7CLE4CGUNVWO.json","view_paper":"https://pith.science/paper/QOB6OEME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.03729&json=true","fetch_graph":"https://pith.science/api/pith-number/QOB6OEMENFHG3B7CLE4CGUNVWO/graph.json","fetch_events":"https://pith.science/api/pith-number/QOB6OEMENFHG3B7CLE4CGUNVWO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QOB6OEMENFHG3B7CLE4CGUNVWO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QOB6OEMENFHG3B7CLE4CGUNVWO/action/storage_attestation","attest_author":"https://pith.science/pith/QOB6OEMENFHG3B7CLE4CGUNVWO/action/author_attestation","sign_citation":"https://pith.science/pith/QOB6OEMENFHG3B7CLE4CGUNVWO/action/citation_signature","submit_replication":"https://pith.science/pith/QOB6OEMENFHG3B7CLE4CGUNVWO/action/replication_record"}},"created_at":"2026-05-17T23:56:27.153671+00:00","updated_at":"2026-05-17T23:56:27.153671+00:00"}