{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:LBFETPENUBC5MBE3KGFN5S3NGG","short_pith_number":"pith:LBFETPEN","canonical_record":{"source":{"id":"1809.02591","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-07T17:32:19Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"f88843c49a1a17ab1e54a7f1add5a033271a3c6215a42ee771cf7e3f54f8e086","abstract_canon_sha256":"c11f39fa36ee219e80098ec6dc39f29d78627c16e6a080641c361cf2f56688ec"},"schema_version":"1.0"},"canonical_sha256":"584a49bc8da045d6049b518adecb6d31a9306d2189bff2854dc4f1cbbc45ee99","source":{"kind":"arxiv","id":"1809.02591","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.02591","created_at":"2026-07-05T01:58:53Z"},{"alias_kind":"arxiv_version","alias_value":"1809.02591v2","created_at":"2026-07-05T01:58:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.02591","created_at":"2026-07-05T01:58:53Z"},{"alias_kind":"pith_short_12","alias_value":"LBFETPENUBC5","created_at":"2026-07-05T01:58:53Z"},{"alias_kind":"pith_short_16","alias_value":"LBFETPENUBC5MBE3","created_at":"2026-07-05T01:58:53Z"},{"alias_kind":"pith_short_8","alias_value":"LBFETPEN","created_at":"2026-07-05T01:58:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:LBFETPENUBC5MBE3KGFN5S3NGG","target":"record","payload":{"canonical_record":{"source":{"id":"1809.02591","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-07T17:32:19Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"f88843c49a1a17ab1e54a7f1add5a033271a3c6215a42ee771cf7e3f54f8e086","abstract_canon_sha256":"c11f39fa36ee219e80098ec6dc39f29d78627c16e6a080641c361cf2f56688ec"},"schema_version":"1.0"},"canonical_sha256":"584a49bc8da045d6049b518adecb6d31a9306d2189bff2854dc4f1cbbc45ee99","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:58:53.422820Z","signature_b64":"ok3X2ULWDq6prgUBI939eKTGhAx/9XuEQqCKgSpYPtpXtCPIiTSMqnuHAfsA7nSOIcF/XtzanvvG/BjodbzKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"584a49bc8da045d6049b518adecb6d31a9306d2189bff2854dc4f1cbbc45ee99","last_reissued_at":"2026-07-05T01:58:53.422347Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:58:53.422347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.02591","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:58:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wcRULK3OIaFjjRwjbN969ojQNL/qhfuo2oYI2cU6g7hCiUroU+ffbCm5NaQRqFAtJ+v/U9DFCzpvE3rPKaq1DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:03:44.314062Z"},"content_sha256":"a319de1f02f72b18d6adf15081a1c15bbf083bcaa832a01df50573df02679ef7","schema_version":"1.0","event_id":"sha256:a319de1f02f72b18d6adf15081a1c15bbf083bcaa832a01df50573df02679ef7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:LBFETPENUBC5MBE3KGFN5S3NGG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Invariances for Policy Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Harm van Seijen, Philip Bachman, Remi Tachet","submitted_at":"2018-09-07T17:32:19Z","abstract_excerpt":"While recent progress has spawned very powerful machine learning systems, those agents remain extremely specialized and fail to transfer the knowledge they gain to similar yet unseen tasks. In this paper, we study a simple reinforcement learning problem and focus on learning policies that encode the proper invariances for generalization to different settings. We evaluate three potential methods for policy generalization: data augmentation, meta-learning and adversarial training. We find our data augmentation method to be effective, and study the potential of meta-learning and adversarial learn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.02591","kind":"arxiv","version":2},"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/1809.02591/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":"2026-07-05T01:58:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cta/TMn0CQZt0i2Pv7Gi2kAl40nvM/mSIpgGwzgoF+RhtN8PJF9KnYKvpgJRZzPzKC2NH0WlJy4wcQtzZ/miCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:03:44.314560Z"},"content_sha256":"dc8aa88974e43e77eb1e4104a346cce695bc61d89d9fe91f7a60897b44842314","schema_version":"1.0","event_id":"sha256:dc8aa88974e43e77eb1e4104a346cce695bc61d89d9fe91f7a60897b44842314"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LBFETPENUBC5MBE3KGFN5S3NGG/bundle.json","state_url":"https://pith.science/pith/LBFETPENUBC5MBE3KGFN5S3NGG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LBFETPENUBC5MBE3KGFN5S3NGG/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":"2026-08-06T15:03:44Z","links":{"resolver":"https://pith.science/pith/LBFETPENUBC5MBE3KGFN5S3NGG","bundle":"https://pith.science/pith/LBFETPENUBC5MBE3KGFN5S3NGG/bundle.json","state":"https://pith.science/pith/LBFETPENUBC5MBE3KGFN5S3NGG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LBFETPENUBC5MBE3KGFN5S3NGG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:LBFETPENUBC5MBE3KGFN5S3NGG","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":"c11f39fa36ee219e80098ec6dc39f29d78627c16e6a080641c361cf2f56688ec","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-07T17:32:19Z","title_canon_sha256":"f88843c49a1a17ab1e54a7f1add5a033271a3c6215a42ee771cf7e3f54f8e086"},"schema_version":"1.0","source":{"id":"1809.02591","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.02591","created_at":"2026-07-05T01:58:53Z"},{"alias_kind":"arxiv_version","alias_value":"1809.02591v2","created_at":"2026-07-05T01:58:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.02591","created_at":"2026-07-05T01:58:53Z"},{"alias_kind":"pith_short_12","alias_value":"LBFETPENUBC5","created_at":"2026-07-05T01:58:53Z"},{"alias_kind":"pith_short_16","alias_value":"LBFETPENUBC5MBE3","created_at":"2026-07-05T01:58:53Z"},{"alias_kind":"pith_short_8","alias_value":"LBFETPEN","created_at":"2026-07-05T01:58:53Z"}],"graph_snapshots":[{"event_id":"sha256:dc8aa88974e43e77eb1e4104a346cce695bc61d89d9fe91f7a60897b44842314","target":"graph","created_at":"2026-07-05T01:58:53Z","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/1809.02591/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While recent progress has spawned very powerful machine learning systems, those agents remain extremely specialized and fail to transfer the knowledge they gain to similar yet unseen tasks. In this paper, we study a simple reinforcement learning problem and focus on learning policies that encode the proper invariances for generalization to different settings. We evaluate three potential methods for policy generalization: data augmentation, meta-learning and adversarial training. We find our data augmentation method to be effective, and study the potential of meta-learning and adversarial learn","authors_text":"Harm van Seijen, Philip Bachman, Remi Tachet","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-07T17:32:19Z","title":"Learning Invariances for Policy Generalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.02591","kind":"arxiv","version":2},"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:a319de1f02f72b18d6adf15081a1c15bbf083bcaa832a01df50573df02679ef7","target":"record","created_at":"2026-07-05T01:58:53Z","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":"c11f39fa36ee219e80098ec6dc39f29d78627c16e6a080641c361cf2f56688ec","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-07T17:32:19Z","title_canon_sha256":"f88843c49a1a17ab1e54a7f1add5a033271a3c6215a42ee771cf7e3f54f8e086"},"schema_version":"1.0","source":{"id":"1809.02591","kind":"arxiv","version":2}},"canonical_sha256":"584a49bc8da045d6049b518adecb6d31a9306d2189bff2854dc4f1cbbc45ee99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"584a49bc8da045d6049b518adecb6d31a9306d2189bff2854dc4f1cbbc45ee99","first_computed_at":"2026-07-05T01:58:53.422347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:58:53.422347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ok3X2ULWDq6prgUBI939eKTGhAx/9XuEQqCKgSpYPtpXtCPIiTSMqnuHAfsA7nSOIcF/XtzanvvG/BjodbzKCg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:58:53.422820Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.02591","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a319de1f02f72b18d6adf15081a1c15bbf083bcaa832a01df50573df02679ef7","sha256:dc8aa88974e43e77eb1e4104a346cce695bc61d89d9fe91f7a60897b44842314"],"state_sha256":"5f1ba8362063ba91bbe94211501f4ee2176af9223fff2a7d6054799b9d53325c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zEHgyLZumYyRdCgGsGCrtzOLKU3UIRIWxO4PKT8jSvhnV8rCmD7lC+IFjFYTC4TNNEmE7JHjut4EnwZqnhgvBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T15:03:44.318458Z","bundle_sha256":"3b5f8d319689b3b89890b66c122286cd098479c0f5ce1582ae86e01a0bad6fa5"}}