{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:NJR5PLSN6HQSTG2YC6LT2QIMJU","short_pith_number":"pith:NJR5PLSN","schema_version":"1.0","canonical_sha256":"6a63d7ae4df1e1299b5817973d410c4d320cb094a44c0777cfabd0b126460ee2","source":{"kind":"arxiv","id":"1807.08706","version":1},"attestation_state":"computed","paper":{"title":"Contrastive Explanations for Reinforcement Learning in terms of Expected Consequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jasper van der Waa, Jurriaan van Diggelen, Karel van den Bosch, Mark Neerincx","submitted_at":"2018-07-23T16:32:38Z","abstract_excerpt":"Machine Learning models become increasingly proficient in complex tasks. However, even for experts in the field, it can be difficult to understand what the model learned. This hampers trust and acceptance, and it obstructs the possibility to correct the model. There is therefore a need for transparency of machine learning models. The development of transparent classification models has received much attention, but there are few developments for achieving transparent Reinforcement Learning (RL) models. In this study we propose a method that enables a RL agent to explain its behavior in terms of"},"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":"1807.08706","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-23T16:32:38Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ad5b464de476847284e8e554d3718062bf7f8562469285550995daed3f696bde","abstract_canon_sha256":"35703c72d4c35bb9abf713a2f1ed3eb1f065b4b536a12da2f528e1823b251819"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:04.957632Z","signature_b64":"2PHmsxmTug758gXl32plzKqgBeXVL8rrx0qAss4yPTL+Ghkbr70DvZp8BfA3mdJlEUoUF33baHao15ANxN5ECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a63d7ae4df1e1299b5817973d410c4d320cb094a44c0777cfabd0b126460ee2","last_reissued_at":"2026-05-18T00:10:04.956936Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:04.956936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Explanations for Reinforcement Learning in terms of Expected Consequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jasper van der Waa, Jurriaan van Diggelen, Karel van den Bosch, Mark Neerincx","submitted_at":"2018-07-23T16:32:38Z","abstract_excerpt":"Machine Learning models become increasingly proficient in complex tasks. However, even for experts in the field, it can be difficult to understand what the model learned. This hampers trust and acceptance, and it obstructs the possibility to correct the model. There is therefore a need for transparency of machine learning models. The development of transparent classification models has received much attention, but there are few developments for achieving transparent Reinforcement Learning (RL) models. In this study we propose a method that enables a RL agent to explain its behavior in terms of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.08706","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":"1807.08706","created_at":"2026-05-18T00:10:04.957053+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.08706v1","created_at":"2026-05-18T00:10:04.957053+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.08706","created_at":"2026-05-18T00:10:04.957053+00:00"},{"alias_kind":"pith_short_12","alias_value":"NJR5PLSN6HQS","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"NJR5PLSN6HQSTG2Y","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"NJR5PLSN","created_at":"2026-05-18T12:32:40.477152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.09293","citing_title":"Generating Counterfactual and Contrastive Explanations using SHAP","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02112","citing_title":"An adaptive variance estimator for relative sparsity","ref_index":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NJR5PLSN6HQSTG2YC6LT2QIMJU","json":"https://pith.science/pith/NJR5PLSN6HQSTG2YC6LT2QIMJU.json","graph_json":"https://pith.science/api/pith-number/NJR5PLSN6HQSTG2YC6LT2QIMJU/graph.json","events_json":"https://pith.science/api/pith-number/NJR5PLSN6HQSTG2YC6LT2QIMJU/events.json","paper":"https://pith.science/paper/NJR5PLSN"},"agent_actions":{"view_html":"https://pith.science/pith/NJR5PLSN6HQSTG2YC6LT2QIMJU","download_json":"https://pith.science/pith/NJR5PLSN6HQSTG2YC6LT2QIMJU.json","view_paper":"https://pith.science/paper/NJR5PLSN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.08706&json=true","fetch_graph":"https://pith.science/api/pith-number/NJR5PLSN6HQSTG2YC6LT2QIMJU/graph.json","fetch_events":"https://pith.science/api/pith-number/NJR5PLSN6HQSTG2YC6LT2QIMJU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NJR5PLSN6HQSTG2YC6LT2QIMJU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NJR5PLSN6HQSTG2YC6LT2QIMJU/action/storage_attestation","attest_author":"https://pith.science/pith/NJR5PLSN6HQSTG2YC6LT2QIMJU/action/author_attestation","sign_citation":"https://pith.science/pith/NJR5PLSN6HQSTG2YC6LT2QIMJU/action/citation_signature","submit_replication":"https://pith.science/pith/NJR5PLSN6HQSTG2YC6LT2QIMJU/action/replication_record"}},"created_at":"2026-05-18T00:10:04.957053+00:00","updated_at":"2026-05-18T00:10:04.957053+00:00"}