{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:WSLXEFE5THR6WPVZC7M3A55QEV","short_pith_number":"pith:WSLXEFE5","canonical_record":{"source":{"id":"2206.07568","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-15T14:34:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cd1467383d98ae7cb86f7a0eefbd7149d04978f38f08d14a2ecd67797f3cef13","abstract_canon_sha256":"44bb76acd2c0d65d8ea3f9d389adbc9d3bd0ed4ab41d72624a2d68179a20bc0f"},"schema_version":"1.0"},"canonical_sha256":"b49772149d99e3eb3eb917d9b077b025652ac9d97611abe3071d782fcb0a3f81","source":{"kind":"arxiv","id":"2206.07568","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.07568","created_at":"2026-07-05T05:43:12Z"},{"alias_kind":"arxiv_version","alias_value":"2206.07568v2","created_at":"2026-07-05T05:43:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07568","created_at":"2026-07-05T05:43:12Z"},{"alias_kind":"pith_short_12","alias_value":"WSLXEFE5THR6","created_at":"2026-07-05T05:43:12Z"},{"alias_kind":"pith_short_16","alias_value":"WSLXEFE5THR6WPVZ","created_at":"2026-07-05T05:43:12Z"},{"alias_kind":"pith_short_8","alias_value":"WSLXEFE5","created_at":"2026-07-05T05:43:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:WSLXEFE5THR6WPVZC7M3A55QEV","target":"record","payload":{"canonical_record":{"source":{"id":"2206.07568","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-15T14:34:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cd1467383d98ae7cb86f7a0eefbd7149d04978f38f08d14a2ecd67797f3cef13","abstract_canon_sha256":"44bb76acd2c0d65d8ea3f9d389adbc9d3bd0ed4ab41d72624a2d68179a20bc0f"},"schema_version":"1.0"},"canonical_sha256":"b49772149d99e3eb3eb917d9b077b025652ac9d97611abe3071d782fcb0a3f81","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:43:12.017887Z","signature_b64":"SA6x+2Z9/RsMLcD9KOQdHJvdbeQDX9DxApG6qDZQdp8MmaeGStcPdZdQ5aYQXci59lTli+U7InFhIDG3VVgHAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b49772149d99e3eb3eb917d9b077b025652ac9d97611abe3071d782fcb0a3f81","last_reissued_at":"2026-07-05T05:43:12.017464Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:43:12.017464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.07568","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":"2026-07-05T05:43:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lhH5ap1lbpS8BnV7SP2sfMIkWBuE2R1UYgBJkQZb5Ltrq8W4MqS90KFOK/VHMtgDuF48PMEGj0jmmIx8uipGCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:18:15.071216Z"},"content_sha256":"c40d249efe55c7a4b481e72143582b743918e517d35cebc7a20da8a6ef19b295","schema_version":"1.0","event_id":"sha256:c40d249efe55c7a4b481e72143582b743918e517d35cebc7a20da8a6ef19b295"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:WSLXEFE5THR6WPVZC7M3A55QEV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Contrastive Learning as Goal-Conditioned Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine, Tianjun Zhang","submitted_at":"2022-06-15T14:34:15Z","abstract_excerpt":"In reinforcement learning (RL), it is easier to solve a task if given a good representation. While deep RL should automatically acquire such good representations, prior work often finds that learning representations in an end-to-end fashion is unstable and instead equip RL algorithms with additional representation learning parts (e.g., auxiliary losses, data augmentation). How can we design RL algorithms that directly acquire good representations? In this paper, instead of adding representation learning parts to an existing RL algorithm, we show (contrastive) representation learning methods ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07568","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/2206.07568/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":"2026-07-05T05:43:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CnhhndQjIozt4cS0QyinzLAxDt9Fp20DEwmxEnS12gC/JbFo0ekKoKNPRf3WxUf25rf3i50Y8hDRpTznTxZSDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:18:15.071750Z"},"content_sha256":"bfea7beeac4a9932de67acbc428f51082870f54c9896144e879dd192255aa40b","schema_version":"1.0","event_id":"sha256:bfea7beeac4a9932de67acbc428f51082870f54c9896144e879dd192255aa40b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WSLXEFE5THR6WPVZC7M3A55QEV/bundle.json","state_url":"https://pith.science/pith/WSLXEFE5THR6WPVZC7M3A55QEV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WSLXEFE5THR6WPVZC7M3A55QEV/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":"2026-08-07T12:18:15Z","links":{"resolver":"https://pith.science/pith/WSLXEFE5THR6WPVZC7M3A55QEV","bundle":"https://pith.science/pith/WSLXEFE5THR6WPVZC7M3A55QEV/bundle.json","state":"https://pith.science/pith/WSLXEFE5THR6WPVZC7M3A55QEV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WSLXEFE5THR6WPVZC7M3A55QEV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:WSLXEFE5THR6WPVZC7M3A55QEV","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":"44bb76acd2c0d65d8ea3f9d389adbc9d3bd0ed4ab41d72624a2d68179a20bc0f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-15T14:34:15Z","title_canon_sha256":"cd1467383d98ae7cb86f7a0eefbd7149d04978f38f08d14a2ecd67797f3cef13"},"schema_version":"1.0","source":{"id":"2206.07568","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.07568","created_at":"2026-07-05T05:43:12Z"},{"alias_kind":"arxiv_version","alias_value":"2206.07568v2","created_at":"2026-07-05T05:43:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07568","created_at":"2026-07-05T05:43:12Z"},{"alias_kind":"pith_short_12","alias_value":"WSLXEFE5THR6","created_at":"2026-07-05T05:43:12Z"},{"alias_kind":"pith_short_16","alias_value":"WSLXEFE5THR6WPVZ","created_at":"2026-07-05T05:43:12Z"},{"alias_kind":"pith_short_8","alias_value":"WSLXEFE5","created_at":"2026-07-05T05:43:12Z"}],"graph_snapshots":[{"event_id":"sha256:bfea7beeac4a9932de67acbc428f51082870f54c9896144e879dd192255aa40b","target":"graph","created_at":"2026-07-05T05:43:12Z","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/2206.07568/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In reinforcement learning (RL), it is easier to solve a task if given a good representation. While deep RL should automatically acquire such good representations, prior work often finds that learning representations in an end-to-end fashion is unstable and instead equip RL algorithms with additional representation learning parts (e.g., auxiliary losses, data augmentation). How can we design RL algorithms that directly acquire good representations? In this paper, instead of adding representation learning parts to an existing RL algorithm, we show (contrastive) representation learning methods ca","authors_text":"Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine, Tianjun Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-15T14:34:15Z","title":"Contrastive Learning as Goal-Conditioned Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07568","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:c40d249efe55c7a4b481e72143582b743918e517d35cebc7a20da8a6ef19b295","target":"record","created_at":"2026-07-05T05:43:12Z","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":"44bb76acd2c0d65d8ea3f9d389adbc9d3bd0ed4ab41d72624a2d68179a20bc0f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-15T14:34:15Z","title_canon_sha256":"cd1467383d98ae7cb86f7a0eefbd7149d04978f38f08d14a2ecd67797f3cef13"},"schema_version":"1.0","source":{"id":"2206.07568","kind":"arxiv","version":2}},"canonical_sha256":"b49772149d99e3eb3eb917d9b077b025652ac9d97611abe3071d782fcb0a3f81","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b49772149d99e3eb3eb917d9b077b025652ac9d97611abe3071d782fcb0a3f81","first_computed_at":"2026-07-05T05:43:12.017464Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:43:12.017464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SA6x+2Z9/RsMLcD9KOQdHJvdbeQDX9DxApG6qDZQdp8MmaeGStcPdZdQ5aYQXci59lTli+U7InFhIDG3VVgHAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:43:12.017887Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.07568","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c40d249efe55c7a4b481e72143582b743918e517d35cebc7a20da8a6ef19b295","sha256:bfea7beeac4a9932de67acbc428f51082870f54c9896144e879dd192255aa40b"],"state_sha256":"63337d19081d5517745ee6cc0e2e6c7df96b7aadd96224a873687fa72a2160e2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wXhjEvVrOJNQw4oTFy1witx+IEz7Lc60hOWl3vmwpejWn7TD4nbUD9bMPPXn0kln1yhqcwBS7+A2EElig++tCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T12:18:15.077008Z","bundle_sha256":"a5be9c7adc572cfb84b8c3266c3bdc536e7ba7f2bc97b713af05ec6f74e4b5a9"}}