{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:X3H5TSIE3SMJMBJOIHQ32CPWDK","short_pith_number":"pith:X3H5TSIE","canonical_record":{"source":{"id":"1907.11740","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-07-26T18:19:25Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"20286f7123f41d6ecac5f7c3923b9d8831616944f7a8ef7d04e7d6850554add6","abstract_canon_sha256":"3f83c447cd4d0eb58511dffd72b13a959d681044c08f97aba78e977cf49495f4"},"schema_version":"1.0"},"canonical_sha256":"becfd9c904dc9896052e41e1bd09f61ab82c5b561727aa5e81688535c5339e34","source":{"kind":"arxiv","id":"1907.11740","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.11740","created_at":"2026-05-17T23:39:23Z"},{"alias_kind":"arxiv_version","alias_value":"1907.11740v1","created_at":"2026-05-17T23:39:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.11740","created_at":"2026-05-17T23:39:23Z"},{"alias_kind":"pith_short_12","alias_value":"X3H5TSIE3SMJ","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"X3H5TSIE3SMJMBJO","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"X3H5TSIE","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:X3H5TSIE3SMJMBJOIHQ32CPWDK","target":"record","payload":{"canonical_record":{"source":{"id":"1907.11740","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-07-26T18:19:25Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"20286f7123f41d6ecac5f7c3923b9d8831616944f7a8ef7d04e7d6850554add6","abstract_canon_sha256":"3f83c447cd4d0eb58511dffd72b13a959d681044c08f97aba78e977cf49495f4"},"schema_version":"1.0"},"canonical_sha256":"becfd9c904dc9896052e41e1bd09f61ab82c5b561727aa5e81688535c5339e34","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:23.232423Z","signature_b64":"m3V9GLviHT5ObXd2+yg7o9KlKmHw/8YE9pN+QzopTHEkQqOggo+rCe8n+/prqRePY7tRfdg3+Se9mJ671OByDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"becfd9c904dc9896052e41e1bd09f61ab82c5b561727aa5e81688535c5339e34","last_reissued_at":"2026-05-17T23:39:23.231854Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:23.231854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.11740","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":"2026-05-17T23:39:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UbtoUD0huqTk7F0cgDk+/v437mqv9zJHr3nMaiJuO8JjQej6QMcl9r/tL1JI7Uam8n92eISeAFmEd/+tglZbBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:56:32.722089Z"},"content_sha256":"5d8928d1a5b65370bf1be22069e9ff44c3b756bb621c670022419c4ae99f94ea","schema_version":"1.0","event_id":"sha256:5d8928d1a5b65370bf1be22069e9ff44c3b756bb621c670022419c4ae99f94ea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:X3H5TSIE3SMJMBJOIHQ32CPWDK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Environment Probing Interaction Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Abhinav Gupta, Lerrel Pinto, Wenxuan Zhou","submitted_at":"2019-07-26T18:19:25Z","abstract_excerpt":"A key challenge in reinforcement learning (RL) is environment generalization: a policy trained to solve a task in one environment often fails to solve the same task in a slightly different test environment. A common approach to improve inter-environment transfer is to learn policies that are invariant to the distribution of testing environments. However, we argue that instead of being invariant, the policy should identify the specific nuances of an environment and exploit them to achieve better performance. In this work, we propose the 'Environment-Probing' Interaction (EPI) policy, a policy t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.11740","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":""},"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":"2026-05-17T23:39:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0r6BY5tTQPSY82F7W9QxCWIQNEFfSszTraZzYtOh82IZNbpiuRqX3Jb9saEawUGSL9jU3sQIk274kA7y/Dg8BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:56:32.722766Z"},"content_sha256":"6cda73ce9cf6b6d1d79e19e3ea5cf0f8edb37b7d5e05133be1e981c2b1d899fb","schema_version":"1.0","event_id":"sha256:6cda73ce9cf6b6d1d79e19e3ea5cf0f8edb37b7d5e05133be1e981c2b1d899fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X3H5TSIE3SMJMBJOIHQ32CPWDK/bundle.json","state_url":"https://pith.science/pith/X3H5TSIE3SMJMBJOIHQ32CPWDK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X3H5TSIE3SMJMBJOIHQ32CPWDK/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":"2026-05-25T18:56:32Z","links":{"resolver":"https://pith.science/pith/X3H5TSIE3SMJMBJOIHQ32CPWDK","bundle":"https://pith.science/pith/X3H5TSIE3SMJMBJOIHQ32CPWDK/bundle.json","state":"https://pith.science/pith/X3H5TSIE3SMJMBJOIHQ32CPWDK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X3H5TSIE3SMJMBJOIHQ32CPWDK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:X3H5TSIE3SMJMBJOIHQ32CPWDK","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":"3f83c447cd4d0eb58511dffd72b13a959d681044c08f97aba78e977cf49495f4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-07-26T18:19:25Z","title_canon_sha256":"20286f7123f41d6ecac5f7c3923b9d8831616944f7a8ef7d04e7d6850554add6"},"schema_version":"1.0","source":{"id":"1907.11740","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.11740","created_at":"2026-05-17T23:39:23Z"},{"alias_kind":"arxiv_version","alias_value":"1907.11740v1","created_at":"2026-05-17T23:39:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.11740","created_at":"2026-05-17T23:39:23Z"},{"alias_kind":"pith_short_12","alias_value":"X3H5TSIE3SMJ","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"X3H5TSIE3SMJMBJO","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"X3H5TSIE","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:6cda73ce9cf6b6d1d79e19e3ea5cf0f8edb37b7d5e05133be1e981c2b1d899fb","target":"graph","created_at":"2026-05-17T23:39:23Z","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"},"paper":{"abstract_excerpt":"A key challenge in reinforcement learning (RL) is environment generalization: a policy trained to solve a task in one environment often fails to solve the same task in a slightly different test environment. A common approach to improve inter-environment transfer is to learn policies that are invariant to the distribution of testing environments. However, we argue that instead of being invariant, the policy should identify the specific nuances of an environment and exploit them to achieve better performance. In this work, we propose the 'Environment-Probing' Interaction (EPI) policy, a policy t","authors_text":"Abhinav Gupta, Lerrel Pinto, Wenxuan Zhou","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-07-26T18:19:25Z","title":"Environment Probing Interaction Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.11740","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":"sha256:5d8928d1a5b65370bf1be22069e9ff44c3b756bb621c670022419c4ae99f94ea","target":"record","created_at":"2026-05-17T23:39:23Z","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":"3f83c447cd4d0eb58511dffd72b13a959d681044c08f97aba78e977cf49495f4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-07-26T18:19:25Z","title_canon_sha256":"20286f7123f41d6ecac5f7c3923b9d8831616944f7a8ef7d04e7d6850554add6"},"schema_version":"1.0","source":{"id":"1907.11740","kind":"arxiv","version":1}},"canonical_sha256":"becfd9c904dc9896052e41e1bd09f61ab82c5b561727aa5e81688535c5339e34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"becfd9c904dc9896052e41e1bd09f61ab82c5b561727aa5e81688535c5339e34","first_computed_at":"2026-05-17T23:39:23.231854Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:23.231854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m3V9GLviHT5ObXd2+yg7o9KlKmHw/8YE9pN+QzopTHEkQqOggo+rCe8n+/prqRePY7tRfdg3+Se9mJ671OByDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:23.232423Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.11740","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d8928d1a5b65370bf1be22069e9ff44c3b756bb621c670022419c4ae99f94ea","sha256:6cda73ce9cf6b6d1d79e19e3ea5cf0f8edb37b7d5e05133be1e981c2b1d899fb"],"state_sha256":"1a04e5875d20ed92e729495cef85afebcf28f24bd80ece042a367ededd80cbff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/8QR/eAc3/6befEIz0rhfOZZzwcBJSIqZeY6gLrzAX3ukX4lq9+lQrXc3uXMulb2I2GKWkUWnFp+XwZKpMBIDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T18:56:32.726495Z","bundle_sha256":"15102512ed0b12ce7da39ef4f8b558afc6ecb322816c6d419209c4ca61411727"}}