{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:PNUSJMRZBJ3D3JRUWWD2M6O5LT","short_pith_number":"pith:PNUSJMRZ","canonical_record":{"source":{"id":"2112.02694","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-05T22:21:11Z","cross_cats_sorted":[],"title_canon_sha256":"e7d633550527657afc773f01b4eee27a64138ea4e583f3e3f1e09d91b0722398","abstract_canon_sha256":"5fafb9001feb9f12cc61006279964041e2a5199a248901c26fc031f5b05bfe1a"},"schema_version":"1.0"},"canonical_sha256":"7b6924b2390a763da634b587a679dd5cfcdf4d1a73aa064c922b1946d8ed5b0d","source":{"kind":"arxiv","id":"2112.02694","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.02694","created_at":"2026-07-05T03:37:56Z"},{"alias_kind":"arxiv_version","alias_value":"2112.02694v1","created_at":"2026-07-05T03:37:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.02694","created_at":"2026-07-05T03:37:56Z"},{"alias_kind":"pith_short_12","alias_value":"PNUSJMRZBJ3D","created_at":"2026-07-05T03:37:56Z"},{"alias_kind":"pith_short_16","alias_value":"PNUSJMRZBJ3D3JRU","created_at":"2026-07-05T03:37:56Z"},{"alias_kind":"pith_short_8","alias_value":"PNUSJMRZ","created_at":"2026-07-05T03:37:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:PNUSJMRZBJ3D3JRUWWD2M6O5LT","target":"record","payload":{"canonical_record":{"source":{"id":"2112.02694","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-05T22:21:11Z","cross_cats_sorted":[],"title_canon_sha256":"e7d633550527657afc773f01b4eee27a64138ea4e583f3e3f1e09d91b0722398","abstract_canon_sha256":"5fafb9001feb9f12cc61006279964041e2a5199a248901c26fc031f5b05bfe1a"},"schema_version":"1.0"},"canonical_sha256":"7b6924b2390a763da634b587a679dd5cfcdf4d1a73aa064c922b1946d8ed5b0d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:37:56.367272Z","signature_b64":"Dm/Lcor+RBdWLJzMBB37fAniwghcP6jhyb14s3Cr06IIRF6bmia5D8jsDMqryk53NTHbfXFw8GKUq5T3hOcSDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b6924b2390a763da634b587a679dd5cfcdf4d1a73aa064c922b1946d8ed5b0d","last_reissued_at":"2026-07-05T03:37:56.366922Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:37:56.366922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.02694","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:37:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Alj0A+JBO8+QIIfy3/AlbL0k/UjiC9THnsKnEbTWPK3eogJdFnwrueA+B8H7A04YiveRuR9TxclgR6WC2TfbCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:31:51.843650Z"},"content_sha256":"72b18b6d257f596a2bb913394e73e9a2f4073945e4432c1cd9a175e9793c09a6","schema_version":"1.0","event_id":"sha256:72b18b6d257f596a2bb913394e73e9a2f4073945e4432c1cd9a175e9793c09a6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:PNUSJMRZBJ3D3JRUWWD2M6O5LT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Benchmark for Out-of-Distribution Detection in Deep Reinforcement Learning","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aaqib Parvez Mohammed, Matias Valdenegro-Toro","submitted_at":"2021-12-05T22:21:11Z","abstract_excerpt":"Reinforcement Learning (RL) based solutions are being adopted in a variety of domains including robotics, health care and industrial automation. Most focus is given to when these solutions work well, but they fail when presented with out of distribution inputs. RL policies share the same faults as most machine learning models. Out of distribution detection for RL is generally not well covered in the literature, and there is a lack of benchmarks for this task. In this work we propose a benchmark to evaluate OOD detection methods in a Reinforcement Learning setting, by modifying the physical par"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.02694","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/2112.02694/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:37:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zfpwVvQsP5kFC0AZFKnkvMDMjzsBBwW+2v356H2EueQw6EbzMlLON+xAZwpG2WxOhsyvDb5stSv4fFNJnIWuCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:31:51.844241Z"},"content_sha256":"63b0d62ac69a740d676e86d93f57306f328b91a011410e43f2f4ccf07933980f","schema_version":"1.0","event_id":"sha256:63b0d62ac69a740d676e86d93f57306f328b91a011410e43f2f4ccf07933980f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PNUSJMRZBJ3D3JRUWWD2M6O5LT/bundle.json","state_url":"https://pith.science/pith/PNUSJMRZBJ3D3JRUWWD2M6O5LT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PNUSJMRZBJ3D3JRUWWD2M6O5LT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T03:31:51Z","links":{"resolver":"https://pith.science/pith/PNUSJMRZBJ3D3JRUWWD2M6O5LT","bundle":"https://pith.science/pith/PNUSJMRZBJ3D3JRUWWD2M6O5LT/bundle.json","state":"https://pith.science/pith/PNUSJMRZBJ3D3JRUWWD2M6O5LT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PNUSJMRZBJ3D3JRUWWD2M6O5LT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PNUSJMRZBJ3D3JRUWWD2M6O5LT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5fafb9001feb9f12cc61006279964041e2a5199a248901c26fc031f5b05bfe1a","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-05T22:21:11Z","title_canon_sha256":"e7d633550527657afc773f01b4eee27a64138ea4e583f3e3f1e09d91b0722398"},"schema_version":"1.0","source":{"id":"2112.02694","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.02694","created_at":"2026-07-05T03:37:56Z"},{"alias_kind":"arxiv_version","alias_value":"2112.02694v1","created_at":"2026-07-05T03:37:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.02694","created_at":"2026-07-05T03:37:56Z"},{"alias_kind":"pith_short_12","alias_value":"PNUSJMRZBJ3D","created_at":"2026-07-05T03:37:56Z"},{"alias_kind":"pith_short_16","alias_value":"PNUSJMRZBJ3D3JRU","created_at":"2026-07-05T03:37:56Z"},{"alias_kind":"pith_short_8","alias_value":"PNUSJMRZ","created_at":"2026-07-05T03:37:56Z"}],"graph_snapshots":[{"event_id":"sha256:63b0d62ac69a740d676e86d93f57306f328b91a011410e43f2f4ccf07933980f","target":"graph","created_at":"2026-07-05T03:37:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2112.02694/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) based solutions are being adopted in a variety of domains including robotics, health care and industrial automation. Most focus is given to when these solutions work well, but they fail when presented with out of distribution inputs. RL policies share the same faults as most machine learning models. Out of distribution detection for RL is generally not well covered in the literature, and there is a lack of benchmarks for this task. In this work we propose a benchmark to evaluate OOD detection methods in a Reinforcement Learning setting, by modifying the physical par","authors_text":"Aaqib Parvez Mohammed, Matias Valdenegro-Toro","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-05T22:21:11Z","title":"Benchmark for Out-of-Distribution Detection in Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.02694","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:72b18b6d257f596a2bb913394e73e9a2f4073945e4432c1cd9a175e9793c09a6","target":"record","created_at":"2026-07-05T03:37:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5fafb9001feb9f12cc61006279964041e2a5199a248901c26fc031f5b05bfe1a","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-05T22:21:11Z","title_canon_sha256":"e7d633550527657afc773f01b4eee27a64138ea4e583f3e3f1e09d91b0722398"},"schema_version":"1.0","source":{"id":"2112.02694","kind":"arxiv","version":1}},"canonical_sha256":"7b6924b2390a763da634b587a679dd5cfcdf4d1a73aa064c922b1946d8ed5b0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b6924b2390a763da634b587a679dd5cfcdf4d1a73aa064c922b1946d8ed5b0d","first_computed_at":"2026-07-05T03:37:56.366922Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:37:56.366922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Dm/Lcor+RBdWLJzMBB37fAniwghcP6jhyb14s3Cr06IIRF6bmia5D8jsDMqryk53NTHbfXFw8GKUq5T3hOcSDA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:37:56.367272Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.02694","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72b18b6d257f596a2bb913394e73e9a2f4073945e4432c1cd9a175e9793c09a6","sha256:63b0d62ac69a740d676e86d93f57306f328b91a011410e43f2f4ccf07933980f"],"state_sha256":"3d1ac9d4c6e7d9918880602f904957493ef5279cd264c6098b41f5d9e963881a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LeF+7Az+pjtrVF25zM2P09ge8xYIIpHecB7o8Uhd2Elh85N3KzKBjSfpHFDm/dRDdFRZgLzK5cfRHPQupfrKDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T03:31:51.849101Z","bundle_sha256":"45e9ac2a55b685404ec8d13c35f516dab786bf0689e025796cfc9128d3954a41"}}