{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:WESWFSLJL6GWVKUJXKMSM3OEHL","short_pith_number":"pith:WESWFSLJ","canonical_record":{"source":{"id":"2110.05169","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-11T11:43:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"10606e872c016a569a708601c8b4aeffe53997d0dfcfb6c6fdfee469e6d4d613","abstract_canon_sha256":"3c07b8761ac31b5f2f46b8632198c39d64ffc96c8ee05ce7dad3704567cee346"},"schema_version":"1.0"},"canonical_sha256":"b12562c9695f8d6aaa89ba99266dc43af7575bf4604a6fc561d8de1c08807c98","source":{"kind":"arxiv","id":"2110.05169","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.05169","created_at":"2026-07-05T05:09:13Z"},{"alias_kind":"arxiv_version","alias_value":"2110.05169v3","created_at":"2026-07-05T05:09:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.05169","created_at":"2026-07-05T05:09:13Z"},{"alias_kind":"pith_short_12","alias_value":"WESWFSLJL6GW","created_at":"2026-07-05T05:09:13Z"},{"alias_kind":"pith_short_16","alias_value":"WESWFSLJL6GWVKUJ","created_at":"2026-07-05T05:09:13Z"},{"alias_kind":"pith_short_8","alias_value":"WESWFSLJ","created_at":"2026-07-05T05:09:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:WESWFSLJL6GWVKUJXKMSM3OEHL","target":"record","payload":{"canonical_record":{"source":{"id":"2110.05169","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-11T11:43:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"10606e872c016a569a708601c8b4aeffe53997d0dfcfb6c6fdfee469e6d4d613","abstract_canon_sha256":"3c07b8761ac31b5f2f46b8632198c39d64ffc96c8ee05ce7dad3704567cee346"},"schema_version":"1.0"},"canonical_sha256":"b12562c9695f8d6aaa89ba99266dc43af7575bf4604a6fc561d8de1c08807c98","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:13.238955Z","signature_b64":"fMI2RH6crREeE47hE0Qzkr1lufdWBHNwqE1zCVPshMYsVhJLteVJUvvOHFPTbkoqN+vgorsYP6EdlSJh3blCCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b12562c9695f8d6aaa89ba99266dc43af7575bf4604a6fc561d8de1c08807c98","last_reissued_at":"2026-07-05T05:09:13.238524Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:13.238524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.05169","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:09:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6sb3swM2ecgDvC1tJyajZt9+uvlhppouaIJKcMayn4B4JO9zCwxX6JgP8p9Y4kjilhFwpJ6T+/R4Ox0MScTkCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T20:22:16.299762Z"},"content_sha256":"6e78d5368573e2f263fe75e6b8467c7c6e07572c318e29a7b1e814e85f1d7a09","schema_version":"1.0","event_id":"sha256:6e78d5368573e2f263fe75e6b8467c7c6e07572c318e29a7b1e814e85f1d7a09"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:WESWFSLJL6GWVKUJXKMSM3OEHL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning a subspace of policies for online adaptation in Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jean-Baptiste Gaya, Laure Soulier, Ludovic Denoyer","submitted_at":"2021-10-11T11:43:34Z","abstract_excerpt":"Deep Reinforcement Learning (RL) is mainly studied in a setting where the training and the testing environments are similar. But in many practical applications, these environments may differ. For instance, in control systems, the robot(s) on which a policy is learned might differ from the robot(s) on which a policy will run. It can be caused by different internal factors (e.g., calibration issues, system attrition, defective modules) or also by external changes (e.g., weather conditions). There is a need to develop RL methods that generalize well to variations of the training conditions. In th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.05169","kind":"arxiv","version":3},"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/2110.05169/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":"2026-07-05T05:09:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0iaJdPBo0PA9Y/4rRxoEqyhDfJVJhdv01dPEtw7cWmqQwsA+ONZiEEjEq282RWm8FdQ8LgwuJe2tbby8wCdCDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T20:22:16.300143Z"},"content_sha256":"f5469447bd23dbe1c1bfca8e4dd027bc18fe8312498c8a20e95765030d0e8e48","schema_version":"1.0","event_id":"sha256:f5469447bd23dbe1c1bfca8e4dd027bc18fe8312498c8a20e95765030d0e8e48"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WESWFSLJL6GWVKUJXKMSM3OEHL/bundle.json","state_url":"https://pith.science/pith/WESWFSLJL6GWVKUJXKMSM3OEHL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WESWFSLJL6GWVKUJXKMSM3OEHL/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":"2026-07-24T20:22:16Z","links":{"resolver":"https://pith.science/pith/WESWFSLJL6GWVKUJXKMSM3OEHL","bundle":"https://pith.science/pith/WESWFSLJL6GWVKUJXKMSM3OEHL/bundle.json","state":"https://pith.science/pith/WESWFSLJL6GWVKUJXKMSM3OEHL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WESWFSLJL6GWVKUJXKMSM3OEHL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WESWFSLJL6GWVKUJXKMSM3OEHL","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":"3c07b8761ac31b5f2f46b8632198c39d64ffc96c8ee05ce7dad3704567cee346","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-11T11:43:34Z","title_canon_sha256":"10606e872c016a569a708601c8b4aeffe53997d0dfcfb6c6fdfee469e6d4d613"},"schema_version":"1.0","source":{"id":"2110.05169","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.05169","created_at":"2026-07-05T05:09:13Z"},{"alias_kind":"arxiv_version","alias_value":"2110.05169v3","created_at":"2026-07-05T05:09:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.05169","created_at":"2026-07-05T05:09:13Z"},{"alias_kind":"pith_short_12","alias_value":"WESWFSLJL6GW","created_at":"2026-07-05T05:09:13Z"},{"alias_kind":"pith_short_16","alias_value":"WESWFSLJL6GWVKUJ","created_at":"2026-07-05T05:09:13Z"},{"alias_kind":"pith_short_8","alias_value":"WESWFSLJ","created_at":"2026-07-05T05:09:13Z"}],"graph_snapshots":[{"event_id":"sha256:f5469447bd23dbe1c1bfca8e4dd027bc18fe8312498c8a20e95765030d0e8e48","target":"graph","created_at":"2026-07-05T05:09:13Z","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/2110.05169/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep Reinforcement Learning (RL) is mainly studied in a setting where the training and the testing environments are similar. But in many practical applications, these environments may differ. For instance, in control systems, the robot(s) on which a policy is learned might differ from the robot(s) on which a policy will run. It can be caused by different internal factors (e.g., calibration issues, system attrition, defective modules) or also by external changes (e.g., weather conditions). There is a need to develop RL methods that generalize well to variations of the training conditions. In th","authors_text":"Jean-Baptiste Gaya, Laure Soulier, Ludovic Denoyer","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-11T11:43:34Z","title":"Learning a subspace of policies for online adaptation in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.05169","kind":"arxiv","version":3},"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":"sha256:6e78d5368573e2f263fe75e6b8467c7c6e07572c318e29a7b1e814e85f1d7a09","target":"record","created_at":"2026-07-05T05:09:13Z","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":"3c07b8761ac31b5f2f46b8632198c39d64ffc96c8ee05ce7dad3704567cee346","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-11T11:43:34Z","title_canon_sha256":"10606e872c016a569a708601c8b4aeffe53997d0dfcfb6c6fdfee469e6d4d613"},"schema_version":"1.0","source":{"id":"2110.05169","kind":"arxiv","version":3}},"canonical_sha256":"b12562c9695f8d6aaa89ba99266dc43af7575bf4604a6fc561d8de1c08807c98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b12562c9695f8d6aaa89ba99266dc43af7575bf4604a6fc561d8de1c08807c98","first_computed_at":"2026-07-05T05:09:13.238524Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:09:13.238524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fMI2RH6crREeE47hE0Qzkr1lufdWBHNwqE1zCVPshMYsVhJLteVJUvvOHFPTbkoqN+vgorsYP6EdlSJh3blCCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:09:13.238955Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.05169","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e78d5368573e2f263fe75e6b8467c7c6e07572c318e29a7b1e814e85f1d7a09","sha256:f5469447bd23dbe1c1bfca8e4dd027bc18fe8312498c8a20e95765030d0e8e48"],"state_sha256":"eeb76a737c1b6335abf2cd0482cc301cd23821287d25cebaa8dfbcbd0ecd59d4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8mtWaA8gZB3x7k3/pCWedivbtpdR4WM3b1j7JiTGsqK79fcXEEnM7jMfX1i4wJzf6nhBNj+TFtapQcPnGUssCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T20:22:16.302339Z","bundle_sha256":"c0b0878ea43066f2c35ab6f10a9341f051dcee55d0d06aa5e3e79aefbb208085"}}