{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ROCWD4BOC6HAM6T3EUVZVY2DWW","short_pith_number":"pith:ROCWD4BO","canonical_record":{"source":{"id":"2101.05265","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-13T18:55:43Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"b89c435b3e450e15ac22e203e8ad53649ce404e018d09ebd7288d6f89926399f","abstract_canon_sha256":"e7cf69e405dfec471d8399e8bd77019b66278fa5d1a3a1996c83dea4879bdcd6"},"schema_version":"1.0"},"canonical_sha256":"8b8561f02e178e067a7b252b9ae343b5a906f3e0772290e601796bb2047d4aa0","source":{"kind":"arxiv","id":"2101.05265","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.05265","created_at":"2026-07-05T02:24:13Z"},{"alias_kind":"arxiv_version","alias_value":"2101.05265v2","created_at":"2026-07-05T02:24:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.05265","created_at":"2026-07-05T02:24:13Z"},{"alias_kind":"pith_short_12","alias_value":"ROCWD4BOC6HA","created_at":"2026-07-05T02:24:13Z"},{"alias_kind":"pith_short_16","alias_value":"ROCWD4BOC6HAM6T3","created_at":"2026-07-05T02:24:13Z"},{"alias_kind":"pith_short_8","alias_value":"ROCWD4BO","created_at":"2026-07-05T02:24:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ROCWD4BOC6HAM6T3EUVZVY2DWW","target":"record","payload":{"canonical_record":{"source":{"id":"2101.05265","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-13T18:55:43Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"b89c435b3e450e15ac22e203e8ad53649ce404e018d09ebd7288d6f89926399f","abstract_canon_sha256":"e7cf69e405dfec471d8399e8bd77019b66278fa5d1a3a1996c83dea4879bdcd6"},"schema_version":"1.0"},"canonical_sha256":"8b8561f02e178e067a7b252b9ae343b5a906f3e0772290e601796bb2047d4aa0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:24:13.306872Z","signature_b64":"rGnSqEDk0JFKKJx3zI4o8OTBRcKf0iUdTmYtKWbbT/1R42KwtRbAM01xDQyN1EhQ9zOhuHt4fqkiaz7BHQNoDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b8561f02e178e067a7b252b9ae343b5a906f3e0772290e601796bb2047d4aa0","last_reissued_at":"2026-07-05T02:24:13.306449Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:24:13.306449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2101.05265","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":"2026-07-05T02:24:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yarvLpJIYZLAzFPOmmaq8fU1/v5pIqyg1+CB7RCaTPJ/cuN96Dzc7Br6pnJVCyI8rbKg+Ltuqe+XPvLbVfyFDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:32:44.395122Z"},"content_sha256":"b7852ede4a3c4dc9940a7e2d63e6a8d64f357ed8dab866c59977bc7a0b6e8eec","schema_version":"1.0","event_id":"sha256:b7852ede4a3c4dc9940a7e2d63e6a8d64f357ed8dab866c59977bc7a0b6e8eec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ROCWD4BOC6HAM6T3EUVZVY2DWW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Marc G. Bellemare, Marlos C. Machado, Pablo Samuel Castro, Rishabh Agarwal","submitted_at":"2021-01-13T18:55:43Z","abstract_excerpt":"Reinforcement learning methods trained on few environments rarely learn policies that generalize to unseen environments. To improve generalization, we incorporate the inherent sequential structure in reinforcement learning into the representation learning process. This approach is orthogonal to recent approaches, which rarely exploit this structure explicitly. Specifically, we introduce a theoretically motivated policy similarity metric (PSM) for measuring behavioral similarity between states. PSM assigns high similarity to states for which the optimal policies in those states as well as in fu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.05265","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/2101.05265/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":"2026-07-05T02:24:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+9DOiNWKZPKdLSFlrZds3OOQ4ms2eC44ay0q9nlARDwoonJ/d06QqMThCK81/BMMyTzjfjUA9IqosHypvKbfAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:32:44.395654Z"},"content_sha256":"f6f04eb05550b40fd0bde76203fdc84ffbe25b3d48a368257ea08fbea0950a2a","schema_version":"1.0","event_id":"sha256:f6f04eb05550b40fd0bde76203fdc84ffbe25b3d48a368257ea08fbea0950a2a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ROCWD4BOC6HAM6T3EUVZVY2DWW/bundle.json","state_url":"https://pith.science/pith/ROCWD4BOC6HAM6T3EUVZVY2DWW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ROCWD4BOC6HAM6T3EUVZVY2DWW/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":"2026-08-08T08:32:44Z","links":{"resolver":"https://pith.science/pith/ROCWD4BOC6HAM6T3EUVZVY2DWW","bundle":"https://pith.science/pith/ROCWD4BOC6HAM6T3EUVZVY2DWW/bundle.json","state":"https://pith.science/pith/ROCWD4BOC6HAM6T3EUVZVY2DWW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ROCWD4BOC6HAM6T3EUVZVY2DWW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ROCWD4BOC6HAM6T3EUVZVY2DWW","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":"e7cf69e405dfec471d8399e8bd77019b66278fa5d1a3a1996c83dea4879bdcd6","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-13T18:55:43Z","title_canon_sha256":"b89c435b3e450e15ac22e203e8ad53649ce404e018d09ebd7288d6f89926399f"},"schema_version":"1.0","source":{"id":"2101.05265","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.05265","created_at":"2026-07-05T02:24:13Z"},{"alias_kind":"arxiv_version","alias_value":"2101.05265v2","created_at":"2026-07-05T02:24:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.05265","created_at":"2026-07-05T02:24:13Z"},{"alias_kind":"pith_short_12","alias_value":"ROCWD4BOC6HA","created_at":"2026-07-05T02:24:13Z"},{"alias_kind":"pith_short_16","alias_value":"ROCWD4BOC6HAM6T3","created_at":"2026-07-05T02:24:13Z"},{"alias_kind":"pith_short_8","alias_value":"ROCWD4BO","created_at":"2026-07-05T02:24:13Z"}],"graph_snapshots":[{"event_id":"sha256:f6f04eb05550b40fd0bde76203fdc84ffbe25b3d48a368257ea08fbea0950a2a","target":"graph","created_at":"2026-07-05T02:24:13Z","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/2101.05265/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning methods trained on few environments rarely learn policies that generalize to unseen environments. To improve generalization, we incorporate the inherent sequential structure in reinforcement learning into the representation learning process. This approach is orthogonal to recent approaches, which rarely exploit this structure explicitly. Specifically, we introduce a theoretically motivated policy similarity metric (PSM) for measuring behavioral similarity between states. PSM assigns high similarity to states for which the optimal policies in those states as well as in fu","authors_text":"Marc G. Bellemare, Marlos C. Machado, Pablo Samuel Castro, Rishabh Agarwal","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-13T18:55:43Z","title":"Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.05265","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:b7852ede4a3c4dc9940a7e2d63e6a8d64f357ed8dab866c59977bc7a0b6e8eec","target":"record","created_at":"2026-07-05T02:24:13Z","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":"e7cf69e405dfec471d8399e8bd77019b66278fa5d1a3a1996c83dea4879bdcd6","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-13T18:55:43Z","title_canon_sha256":"b89c435b3e450e15ac22e203e8ad53649ce404e018d09ebd7288d6f89926399f"},"schema_version":"1.0","source":{"id":"2101.05265","kind":"arxiv","version":2}},"canonical_sha256":"8b8561f02e178e067a7b252b9ae343b5a906f3e0772290e601796bb2047d4aa0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b8561f02e178e067a7b252b9ae343b5a906f3e0772290e601796bb2047d4aa0","first_computed_at":"2026-07-05T02:24:13.306449Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:24:13.306449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rGnSqEDk0JFKKJx3zI4o8OTBRcKf0iUdTmYtKWbbT/1R42KwtRbAM01xDQyN1EhQ9zOhuHt4fqkiaz7BHQNoDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:24:13.306872Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.05265","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7852ede4a3c4dc9940a7e2d63e6a8d64f357ed8dab866c59977bc7a0b6e8eec","sha256:f6f04eb05550b40fd0bde76203fdc84ffbe25b3d48a368257ea08fbea0950a2a"],"state_sha256":"1f9d55bccfb08fae9f5254b7ee4a114f73bda0c7e0d80038508ac7e735df5e77"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gVv/yHbQJGMrhA4cLRxqxC4fYO8tTTOUK5gf0kHHJvvun7mIz5cRYzHrUbkq8sG1X6EMbb1YqkDns3WqXt8VDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T08:32:44.400686Z","bundle_sha256":"a91d2f2d5feabc4dcc7716cd55f83a6bb00ffabd93059157a167c59fa565daee"}}