{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XQ7D7FI3AWFTUQQ74MSHIKDU6V","short_pith_number":"pith:XQ7D7FI3","schema_version":"1.0","canonical_sha256":"bc3e3f951b058b3a421fe324742874f57849c4daca41ad7971417be2ed13afbd","source":{"kind":"arxiv","id":"2312.11118","version":1},"attestation_state":"computed","paper":{"title":"Explaining Reinforcement Learning Agents Through Counterfactual Action Outcomes","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Ofra Amir, Yael Septon, Yotam Amitai","submitted_at":"2023-12-18T11:34:58Z","abstract_excerpt":"Explainable reinforcement learning (XRL) methods aim to help elucidate agent policies and decision-making processes. The majority of XRL approaches focus on local explanations, seeking to shed light on the reasons an agent acts the way it does at a specific world state. While such explanations are both useful and necessary, they typically do not portray the outcomes of the agent's selected choice of action. In this work, we propose ``COViz'', a new local explanation method that visually compares the outcome of an agent's chosen action to a counterfactual one. In contrast to most local explanat"},"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":"2312.11118","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-18T11:34:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"84dfabc916017812c429eceffb40feac849bc226462924299c6a467a13883753","abstract_canon_sha256":"58ea47596807a8c6e6843376af6039fd1964fa5a68fd4ec74573fb559353dde6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:25:28.472600Z","signature_b64":"UOsrifoIxG73zOUrFD0iXT6g0cok0aTGmOutiYI5q3jVo2MCDyAmifWpWHkqNgyqhky35n1H0fywjSYK4GbODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc3e3f951b058b3a421fe324742874f57849c4daca41ad7971417be2ed13afbd","last_reissued_at":"2026-07-05T07:25:28.472111Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:25:28.472111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explaining Reinforcement Learning Agents Through Counterfactual Action Outcomes","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Ofra Amir, Yael Septon, Yotam Amitai","submitted_at":"2023-12-18T11:34:58Z","abstract_excerpt":"Explainable reinforcement learning (XRL) methods aim to help elucidate agent policies and decision-making processes. The majority of XRL approaches focus on local explanations, seeking to shed light on the reasons an agent acts the way it does at a specific world state. While such explanations are both useful and necessary, they typically do not portray the outcomes of the agent's selected choice of action. In this work, we propose ``COViz'', a new local explanation method that visually compares the outcome of an agent's chosen action to a counterfactual one. In contrast to most local explanat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11118","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2312.11118/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":"2312.11118","created_at":"2026-07-05T07:25:28.472167+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.11118v1","created_at":"2026-07-05T07:25:28.472167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11118","created_at":"2026-07-05T07:25:28.472167+00:00"},{"alias_kind":"pith_short_12","alias_value":"XQ7D7FI3AWFT","created_at":"2026-07-05T07:25:28.472167+00:00"},{"alias_kind":"pith_short_16","alias_value":"XQ7D7FI3AWFTUQQ7","created_at":"2026-07-05T07:25:28.472167+00:00"},{"alias_kind":"pith_short_8","alias_value":"XQ7D7FI3","created_at":"2026-07-05T07:25:28.472167+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12366","citing_title":"Ghost Policies: A New Paradigm for Understanding and Learning from Failure in Deep Reinforcement Learning","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XQ7D7FI3AWFTUQQ74MSHIKDU6V","json":"https://pith.science/pith/XQ7D7FI3AWFTUQQ74MSHIKDU6V.json","graph_json":"https://pith.science/api/pith-number/XQ7D7FI3AWFTUQQ74MSHIKDU6V/graph.json","events_json":"https://pith.science/api/pith-number/XQ7D7FI3AWFTUQQ74MSHIKDU6V/events.json","paper":"https://pith.science/paper/XQ7D7FI3"},"agent_actions":{"view_html":"https://pith.science/pith/XQ7D7FI3AWFTUQQ74MSHIKDU6V","download_json":"https://pith.science/pith/XQ7D7FI3AWFTUQQ74MSHIKDU6V.json","view_paper":"https://pith.science/paper/XQ7D7FI3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.11118&json=true","fetch_graph":"https://pith.science/api/pith-number/XQ7D7FI3AWFTUQQ74MSHIKDU6V/graph.json","fetch_events":"https://pith.science/api/pith-number/XQ7D7FI3AWFTUQQ74MSHIKDU6V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XQ7D7FI3AWFTUQQ74MSHIKDU6V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XQ7D7FI3AWFTUQQ74MSHIKDU6V/action/storage_attestation","attest_author":"https://pith.science/pith/XQ7D7FI3AWFTUQQ74MSHIKDU6V/action/author_attestation","sign_citation":"https://pith.science/pith/XQ7D7FI3AWFTUQQ74MSHIKDU6V/action/citation_signature","submit_replication":"https://pith.science/pith/XQ7D7FI3AWFTUQQ74MSHIKDU6V/action/replication_record"}},"created_at":"2026-07-05T07:25:28.472167+00:00","updated_at":"2026-07-05T07:25:28.472167+00:00"}