{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:43GLTXCLJRGRYEMULUDHK7UIBA","short_pith_number":"pith:43GLTXCL","schema_version":"1.0","canonical_sha256":"e6ccb9dc4b4c4d1c11945d06757e880808c64b4dcb5cd0420c25263003cff4f6","source":{"kind":"arxiv","id":"2607.11607","version":1},"attestation_state":"computed","paper":{"title":"Auditing the Risk Claims of Distributional Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Hari Prasad","submitted_at":"2026-07-13T14:30:01Z","abstract_excerpt":"Distributional reinforcement learning agents learn full return distributions that are increasingly read at face value: for interpretability, risk-sensitive control, and safety monitoring. We ask a question theory anticipates but that has not been measured directly: are the risk claims of a trained distributional agent true? Our audit combines a decision-relevant screening metric (the excess Wasserstein gap between the top two actions, which equals the mass by which first-order stochastic dominance is violated), ground truth from snapshot-restart Monte Carlo, and a statistical harness (permutat"},"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":"2607.11607","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-13T14:30:01Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"9d71bde8d9dbcf8706ddb7eefdbc8e601e05b83c61e0a601b1a3c2f99f2f76b3","abstract_canon_sha256":"34a3b6890e34b57b3eeef84b20a7946d386a6f6c8f55ef68b3990bbf5134a5a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T02:22:14.688628Z","signature_b64":"U0d02Fg/T1E09AngrrSTKX4thTb/iika1yXDJpHQvA1wPbk5XI4gTlEiROY+i+SnUc28UnNtmCaGzLE1SQPNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6ccb9dc4b4c4d1c11945d06757e880808c64b4dcb5cd0420c25263003cff4f6","last_reissued_at":"2026-07-14T02:22:14.687781Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T02:22:14.687781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Auditing the Risk Claims of Distributional Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Hari Prasad","submitted_at":"2026-07-13T14:30:01Z","abstract_excerpt":"Distributional reinforcement learning agents learn full return distributions that are increasingly read at face value: for interpretability, risk-sensitive control, and safety monitoring. We ask a question theory anticipates but that has not been measured directly: are the risk claims of a trained distributional agent true? Our audit combines a decision-relevant screening metric (the excess Wasserstein gap between the top two actions, which equals the mass by which first-order stochastic dominance is violated), ground truth from snapshot-restart Monte Carlo, and a statistical harness (permutat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.11607","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/2607.11607/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":"2607.11607","created_at":"2026-07-14T02:22:14.688220+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.11607v1","created_at":"2026-07-14T02:22:14.688220+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.11607","created_at":"2026-07-14T02:22:14.688220+00:00"},{"alias_kind":"pith_short_12","alias_value":"43GLTXCLJRGR","created_at":"2026-07-14T02:22:14.688220+00:00"},{"alias_kind":"pith_short_16","alias_value":"43GLTXCLJRGRYEMU","created_at":"2026-07-14T02:22:14.688220+00:00"},{"alias_kind":"pith_short_8","alias_value":"43GLTXCL","created_at":"2026-07-14T02:22:14.688220+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/43GLTXCLJRGRYEMULUDHK7UIBA","json":"https://pith.science/pith/43GLTXCLJRGRYEMULUDHK7UIBA.json","graph_json":"https://pith.science/api/pith-number/43GLTXCLJRGRYEMULUDHK7UIBA/graph.json","events_json":"https://pith.science/api/pith-number/43GLTXCLJRGRYEMULUDHK7UIBA/events.json","paper":"https://pith.science/paper/43GLTXCL"},"agent_actions":{"view_html":"https://pith.science/pith/43GLTXCLJRGRYEMULUDHK7UIBA","download_json":"https://pith.science/pith/43GLTXCLJRGRYEMULUDHK7UIBA.json","view_paper":"https://pith.science/paper/43GLTXCL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.11607&json=true","fetch_graph":"https://pith.science/api/pith-number/43GLTXCLJRGRYEMULUDHK7UIBA/graph.json","fetch_events":"https://pith.science/api/pith-number/43GLTXCLJRGRYEMULUDHK7UIBA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/43GLTXCLJRGRYEMULUDHK7UIBA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/43GLTXCLJRGRYEMULUDHK7UIBA/action/storage_attestation","attest_author":"https://pith.science/pith/43GLTXCLJRGRYEMULUDHK7UIBA/action/author_attestation","sign_citation":"https://pith.science/pith/43GLTXCLJRGRYEMULUDHK7UIBA/action/citation_signature","submit_replication":"https://pith.science/pith/43GLTXCLJRGRYEMULUDHK7UIBA/action/replication_record"}},"created_at":"2026-07-14T02:22:14.688220+00:00","updated_at":"2026-07-14T02:22:14.688220+00:00"}