{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:BZYRJAXIUIZNZVVANKEY54YJYA","short_pith_number":"pith:BZYRJAXI","canonical_record":{"source":{"id":"2111.14629","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-29T15:42:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c9b3c8cf3b35f3a8dcb8de9f742a1d1cb3130a5ba962914dea5564fea824a193","abstract_canon_sha256":"ded80da8466c7615305534141f92f0b7a1ab32900b1c2a92fe828427036aea40"},"schema_version":"1.0"},"canonical_sha256":"0e711482e8a232dcd6a06a898ef309c02278ed85a5b7df677c8bced8df71ea9a","source":{"kind":"arxiv","id":"2111.14629","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.14629","created_at":"2026-07-05T03:35:53Z"},{"alias_kind":"arxiv_version","alias_value":"2111.14629v1","created_at":"2026-07-05T03:35:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.14629","created_at":"2026-07-05T03:35:53Z"},{"alias_kind":"pith_short_12","alias_value":"BZYRJAXIUIZN","created_at":"2026-07-05T03:35:53Z"},{"alias_kind":"pith_short_16","alias_value":"BZYRJAXIUIZNZVVA","created_at":"2026-07-05T03:35:53Z"},{"alias_kind":"pith_short_8","alias_value":"BZYRJAXI","created_at":"2026-07-05T03:35:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:BZYRJAXIUIZNZVVANKEY54YJYA","target":"record","payload":{"canonical_record":{"source":{"id":"2111.14629","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-29T15:42:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c9b3c8cf3b35f3a8dcb8de9f742a1d1cb3130a5ba962914dea5564fea824a193","abstract_canon_sha256":"ded80da8466c7615305534141f92f0b7a1ab32900b1c2a92fe828427036aea40"},"schema_version":"1.0"},"canonical_sha256":"0e711482e8a232dcd6a06a898ef309c02278ed85a5b7df677c8bced8df71ea9a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:53.885300Z","signature_b64":"Az1V9/yC6F5Gt+KQlvkODPvSNu4rqWb+mZTlD3+RD6nKr5K7Cz4bDZRD7qVR5lPT1alvkSYI5bXqh2lJTAC9BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e711482e8a232dcd6a06a898ef309c02278ed85a5b7df677c8bced8df71ea9a","last_reissued_at":"2026-07-05T03:35:53.884847Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:53.884847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.14629","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":"2026-07-05T03:35:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dGaZPjsgdVzRHhjw6v+DrBOMGJTYJWY+eAwHmbrTozoVIdXyPwIJz1I6WISAEP/UlB6OZk2Sp9q62sXaeneGDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T19:46:07.851135Z"},"content_sha256":"f9b2dd5c103ef3878ef3ce8d03080d51d47290bea9a9dc31cf7feee90e877f38","schema_version":"1.0","event_id":"sha256:f9b2dd5c103ef3878ef3ce8d03080d51d47290bea9a9dc31cf7feee90e877f38"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:BZYRJAXIUIZNZVVANKEY54YJYA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Zero-shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bogdan Mazoure, Ilya Kostrikov, Jonathan Tompson, Ofir Nachum","submitted_at":"2021-11-29T15:42:54Z","abstract_excerpt":"Reinforcement learning (RL) agents are widely used for solving complex sequential decision making tasks, but still exhibit difficulty in generalizing to scenarios not seen during training. While prior online approaches demonstrated that using additional signals beyond the reward function can lead to better generalization capabilities in RL agents, i.e. using self-supervised learning (SSL), they struggle in the offline RL setting, i.e. learning from a static dataset. We show that performance of online algorithms for generalization in RL can be hindered in the offline setting due to poor estimat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.14629","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/2111.14629/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":"2026-07-05T03:35:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2k5osmATtsoYJ0HTbMRQXcDkRTUe60pbpCW9Nl69wkno/bLb/874eDlHt79swTVthvKTO/DA20eipamEePIPDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T19:46:07.851633Z"},"content_sha256":"e7998ce6c2271718069b9bdf8b280526b2af7678e4cbab25762b1d02317cbaf3","schema_version":"1.0","event_id":"sha256:e7998ce6c2271718069b9bdf8b280526b2af7678e4cbab25762b1d02317cbaf3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BZYRJAXIUIZNZVVANKEY54YJYA/bundle.json","state_url":"https://pith.science/pith/BZYRJAXIUIZNZVVANKEY54YJYA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BZYRJAXIUIZNZVVANKEY54YJYA/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":"2026-08-05T19:46:07Z","links":{"resolver":"https://pith.science/pith/BZYRJAXIUIZNZVVANKEY54YJYA","bundle":"https://pith.science/pith/BZYRJAXIUIZNZVVANKEY54YJYA/bundle.json","state":"https://pith.science/pith/BZYRJAXIUIZNZVVANKEY54YJYA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BZYRJAXIUIZNZVVANKEY54YJYA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:BZYRJAXIUIZNZVVANKEY54YJYA","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":"ded80da8466c7615305534141f92f0b7a1ab32900b1c2a92fe828427036aea40","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-29T15:42:54Z","title_canon_sha256":"c9b3c8cf3b35f3a8dcb8de9f742a1d1cb3130a5ba962914dea5564fea824a193"},"schema_version":"1.0","source":{"id":"2111.14629","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.14629","created_at":"2026-07-05T03:35:53Z"},{"alias_kind":"arxiv_version","alias_value":"2111.14629v1","created_at":"2026-07-05T03:35:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.14629","created_at":"2026-07-05T03:35:53Z"},{"alias_kind":"pith_short_12","alias_value":"BZYRJAXIUIZN","created_at":"2026-07-05T03:35:53Z"},{"alias_kind":"pith_short_16","alias_value":"BZYRJAXIUIZNZVVA","created_at":"2026-07-05T03:35:53Z"},{"alias_kind":"pith_short_8","alias_value":"BZYRJAXI","created_at":"2026-07-05T03:35:53Z"}],"graph_snapshots":[{"event_id":"sha256:e7998ce6c2271718069b9bdf8b280526b2af7678e4cbab25762b1d02317cbaf3","target":"graph","created_at":"2026-07-05T03:35:53Z","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/2111.14629/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) agents are widely used for solving complex sequential decision making tasks, but still exhibit difficulty in generalizing to scenarios not seen during training. While prior online approaches demonstrated that using additional signals beyond the reward function can lead to better generalization capabilities in RL agents, i.e. using self-supervised learning (SSL), they struggle in the offline RL setting, i.e. learning from a static dataset. We show that performance of online algorithms for generalization in RL can be hindered in the offline setting due to poor estimat","authors_text":"Bogdan Mazoure, Ilya Kostrikov, Jonathan Tompson, Ofir Nachum","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-29T15:42:54Z","title":"Improving Zero-shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.14629","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:f9b2dd5c103ef3878ef3ce8d03080d51d47290bea9a9dc31cf7feee90e877f38","target":"record","created_at":"2026-07-05T03:35:53Z","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":"ded80da8466c7615305534141f92f0b7a1ab32900b1c2a92fe828427036aea40","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-29T15:42:54Z","title_canon_sha256":"c9b3c8cf3b35f3a8dcb8de9f742a1d1cb3130a5ba962914dea5564fea824a193"},"schema_version":"1.0","source":{"id":"2111.14629","kind":"arxiv","version":1}},"canonical_sha256":"0e711482e8a232dcd6a06a898ef309c02278ed85a5b7df677c8bced8df71ea9a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e711482e8a232dcd6a06a898ef309c02278ed85a5b7df677c8bced8df71ea9a","first_computed_at":"2026-07-05T03:35:53.884847Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:35:53.884847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Az1V9/yC6F5Gt+KQlvkODPvSNu4rqWb+mZTlD3+RD6nKr5K7Cz4bDZRD7qVR5lPT1alvkSYI5bXqh2lJTAC9BA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:35:53.885300Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.14629","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9b2dd5c103ef3878ef3ce8d03080d51d47290bea9a9dc31cf7feee90e877f38","sha256:e7998ce6c2271718069b9bdf8b280526b2af7678e4cbab25762b1d02317cbaf3"],"state_sha256":"d8a47ad40d6676e0463d112e8fda6e2650a7977577d6b9e1fe4f02b484b6ee22"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PIDKBPpU6R9/IunoGznSXXDjE+JR+ceR8NLyzBN2ExubEmBf7WmrBa7/WRGp+NFaW2lleOdLelzMJQU5kb8rDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T19:46:07.856433Z","bundle_sha256":"0b9ed145e1947b1797da9daa5d4bd0d19b7f742f41d4f3162cfc1af52db192c3"}}