{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:BBU64I5X5K5FVXC7VOBF4B3FNX","short_pith_number":"pith:BBU64I5X","canonical_record":{"source":{"id":"2008.00614","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-03T02:24:20Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"d9a27055bba47ebe95ffe240694f95fd32f8ae80833602f96cfdf756deba70a4","abstract_canon_sha256":"22a44523d43e9de0c9ed126981b09be99cd12e1de46347e0b1f43a9c0b9a23fc"},"schema_version":"1.0"},"canonical_sha256":"0869ee23b7eaba5adc5fab825e07656dea0e11c5765bd7a85b276ad869d7f2cc","source":{"kind":"arxiv","id":"2008.00614","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.00614","created_at":"2026-07-05T01:24:09Z"},{"alias_kind":"arxiv_version","alias_value":"2008.00614v1","created_at":"2026-07-05T01:24:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.00614","created_at":"2026-07-05T01:24:09Z"},{"alias_kind":"pith_short_12","alias_value":"BBU64I5X5K5F","created_at":"2026-07-05T01:24:09Z"},{"alias_kind":"pith_short_16","alias_value":"BBU64I5X5K5FVXC7","created_at":"2026-07-05T01:24:09Z"},{"alias_kind":"pith_short_8","alias_value":"BBU64I5X","created_at":"2026-07-05T01:24:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:BBU64I5X5K5FVXC7VOBF4B3FNX","target":"record","payload":{"canonical_record":{"source":{"id":"2008.00614","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-03T02:24:20Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"d9a27055bba47ebe95ffe240694f95fd32f8ae80833602f96cfdf756deba70a4","abstract_canon_sha256":"22a44523d43e9de0c9ed126981b09be99cd12e1de46347e0b1f43a9c0b9a23fc"},"schema_version":"1.0"},"canonical_sha256":"0869ee23b7eaba5adc5fab825e07656dea0e11c5765bd7a85b276ad869d7f2cc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:24:09.269237Z","signature_b64":"4u4+MDQn2JK+YU7BiLVE4nbZwSND7HHy43jWmQFRp33qBT4tuHQefu8UfqLgQ5WBQtEVW2gFzwPGNN4Cj271Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0869ee23b7eaba5adc5fab825e07656dea0e11c5765bd7a85b276ad869d7f2cc","last_reissued_at":"2026-07-05T01:24:09.268880Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:24:09.268880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.00614","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":"2026-07-05T01:24:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LuSkhw6nOkegUWkumaVXi1mDM0lRsoYgErdl1CX8GHiB7Jvpac3NtPy5mOfmQ0jxHT9ksQ5wuhZUV8JPJuzSCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T22:32:02.097116Z"},"content_sha256":"d4aa3ea0201ed10c63a0656187cccb52c2be3b4e9bb181e551183c7790f296fc","schema_version":"1.0","event_id":"sha256:d4aa3ea0201ed10c63a0656187cccb52c2be3b4e9bb181e551183c7790f296fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:BBU64I5X5K5FVXC7VOBF4B3FNX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamics Generalization via Information Bottleneck in Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kimin Lee, Pieter Abbeel, Stas Tiomkin, Xingyu Lu","submitted_at":"2020-08-03T02:24:20Z","abstract_excerpt":"Despite the significant progress of deep reinforcement learning (RL) in solving sequential decision making problems, RL agents often overfit to training environments and struggle to adapt to new, unseen environments. This prevents robust applications of RL in real world situations, where system dynamics may deviate wildly from the training settings. In this work, our primary contribution is to propose an information theoretic regularization objective and an annealing-based optimization method to achieve better generalization ability in RL agents. We demonstrate the extreme generalization benef"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.00614","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/2008.00614/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":"2026-07-05T01:24:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HmHTHrzZGOwthn9W0061soB5sWNiF8hUP9hPO4DYFfVcqMPnzlf8aRfsNF0LVOYMPEzAqPRtNdNAdQ+jI34wBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T22:32:02.097933Z"},"content_sha256":"f8ef8c6889efbebcf4ac390e4f2f421fb45ba8497b965de46701d4636bbf8dc4","schema_version":"1.0","event_id":"sha256:f8ef8c6889efbebcf4ac390e4f2f421fb45ba8497b965de46701d4636bbf8dc4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BBU64I5X5K5FVXC7VOBF4B3FNX/bundle.json","state_url":"https://pith.science/pith/BBU64I5X5K5FVXC7VOBF4B3FNX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BBU64I5X5K5FVXC7VOBF4B3FNX/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":"2026-08-19T22:32:02Z","links":{"resolver":"https://pith.science/pith/BBU64I5X5K5FVXC7VOBF4B3FNX","bundle":"https://pith.science/pith/BBU64I5X5K5FVXC7VOBF4B3FNX/bundle.json","state":"https://pith.science/pith/BBU64I5X5K5FVXC7VOBF4B3FNX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BBU64I5X5K5FVXC7VOBF4B3FNX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:BBU64I5X5K5FVXC7VOBF4B3FNX","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":"22a44523d43e9de0c9ed126981b09be99cd12e1de46347e0b1f43a9c0b9a23fc","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-03T02:24:20Z","title_canon_sha256":"d9a27055bba47ebe95ffe240694f95fd32f8ae80833602f96cfdf756deba70a4"},"schema_version":"1.0","source":{"id":"2008.00614","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.00614","created_at":"2026-07-05T01:24:09Z"},{"alias_kind":"arxiv_version","alias_value":"2008.00614v1","created_at":"2026-07-05T01:24:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.00614","created_at":"2026-07-05T01:24:09Z"},{"alias_kind":"pith_short_12","alias_value":"BBU64I5X5K5F","created_at":"2026-07-05T01:24:09Z"},{"alias_kind":"pith_short_16","alias_value":"BBU64I5X5K5FVXC7","created_at":"2026-07-05T01:24:09Z"},{"alias_kind":"pith_short_8","alias_value":"BBU64I5X","created_at":"2026-07-05T01:24:09Z"}],"graph_snapshots":[{"event_id":"sha256:f8ef8c6889efbebcf4ac390e4f2f421fb45ba8497b965de46701d4636bbf8dc4","target":"graph","created_at":"2026-07-05T01:24:09Z","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/2008.00614/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the significant progress of deep reinforcement learning (RL) in solving sequential decision making problems, RL agents often overfit to training environments and struggle to adapt to new, unseen environments. This prevents robust applications of RL in real world situations, where system dynamics may deviate wildly from the training settings. In this work, our primary contribution is to propose an information theoretic regularization objective and an annealing-based optimization method to achieve better generalization ability in RL agents. We demonstrate the extreme generalization benef","authors_text":"Kimin Lee, Pieter Abbeel, Stas Tiomkin, Xingyu Lu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-03T02:24:20Z","title":"Dynamics Generalization via Information Bottleneck in Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.00614","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:d4aa3ea0201ed10c63a0656187cccb52c2be3b4e9bb181e551183c7790f296fc","target":"record","created_at":"2026-07-05T01:24:09Z","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":"22a44523d43e9de0c9ed126981b09be99cd12e1de46347e0b1f43a9c0b9a23fc","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-03T02:24:20Z","title_canon_sha256":"d9a27055bba47ebe95ffe240694f95fd32f8ae80833602f96cfdf756deba70a4"},"schema_version":"1.0","source":{"id":"2008.00614","kind":"arxiv","version":1}},"canonical_sha256":"0869ee23b7eaba5adc5fab825e07656dea0e11c5765bd7a85b276ad869d7f2cc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0869ee23b7eaba5adc5fab825e07656dea0e11c5765bd7a85b276ad869d7f2cc","first_computed_at":"2026-07-05T01:24:09.268880Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:24:09.268880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4u4+MDQn2JK+YU7BiLVE4nbZwSND7HHy43jWmQFRp33qBT4tuHQefu8UfqLgQ5WBQtEVW2gFzwPGNN4Cj271Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:24:09.269237Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.00614","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4aa3ea0201ed10c63a0656187cccb52c2be3b4e9bb181e551183c7790f296fc","sha256:f8ef8c6889efbebcf4ac390e4f2f421fb45ba8497b965de46701d4636bbf8dc4"],"state_sha256":"16da33810a5d3327bdcd82f40ecacbb7b46e0c3ba2c627253bd5e7ab1246e0ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9e+FTeqE6zm6noFnB4QAP6pNnEb/EAlickHYQhC088zK9p+8Drm6pVVJKqsTUYAFY7JlezL8aZsqq4kP68HOAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T22:32:02.103125Z","bundle_sha256":"df51aadf6cf7eca4e33a5e47f86d10c7e86aeeb92ffddc05b8d6d3cc500bcdc3"}}