{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ZQRK7UQDGOJI7NLTBGCOUATNU5","short_pith_number":"pith:ZQRK7UQD","canonical_record":{"source":{"id":"2106.04799","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-09T04:14:27Z","cross_cats_sorted":[],"title_canon_sha256":"8554da61a096a8540a022f2e177c75a770f17465307dec9b1c5cc194ebca7d1e","abstract_canon_sha256":"49e91e0cc1c25260bfa05c63e663f669a466c5b6bfc11f131b77c90918c6de85"},"schema_version":"1.0"},"canonical_sha256":"cc22afd20333928fb5730984ea026da762f78b36655a86778b5dffda988c7d8c","source":{"kind":"arxiv","id":"2106.04799","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.04799","created_at":"2026-07-05T02:47:49Z"},{"alias_kind":"arxiv_version","alias_value":"2106.04799v1","created_at":"2026-07-05T02:47:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.04799","created_at":"2026-07-05T02:47:49Z"},{"alias_kind":"pith_short_12","alias_value":"ZQRK7UQDGOJI","created_at":"2026-07-05T02:47:49Z"},{"alias_kind":"pith_short_16","alias_value":"ZQRK7UQDGOJI7NLT","created_at":"2026-07-05T02:47:49Z"},{"alias_kind":"pith_short_8","alias_value":"ZQRK7UQD","created_at":"2026-07-05T02:47:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ZQRK7UQDGOJI7NLTBGCOUATNU5","target":"record","payload":{"canonical_record":{"source":{"id":"2106.04799","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-09T04:14:27Z","cross_cats_sorted":[],"title_canon_sha256":"8554da61a096a8540a022f2e177c75a770f17465307dec9b1c5cc194ebca7d1e","abstract_canon_sha256":"49e91e0cc1c25260bfa05c63e663f669a466c5b6bfc11f131b77c90918c6de85"},"schema_version":"1.0"},"canonical_sha256":"cc22afd20333928fb5730984ea026da762f78b36655a86778b5dffda988c7d8c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:47:49.264854Z","signature_b64":"7H1IsUT/XstwQ41uyz9aiBeD1LexSI/zG+Jqy4U7+ZgiRZNiS+4ZkZpf0JGmfY7pZ3Fk78knUy28MJ3u6MI3BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc22afd20333928fb5730984ea026da762f78b36655a86778b5dffda988c7d8c","last_reissued_at":"2026-07-05T02:47:49.264390Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:47:49.264390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.04799","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":"2026-07-05T02:47:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CAxZLa/PeyGn42lgnz1mFAv5yhUkcGG6CxMgLsE0Gv7UZjop3jZCPwWr+ltnZ5lHLjPIntWL+xzVm4tZZSzxCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:31:23.014826Z"},"content_sha256":"fa13fd517dfb056a9faafbf808594d34a3d1a9258e5e69bcb953bbfda894b0d4","schema_version":"1.0","event_id":"sha256:fa13fd517dfb056a9faafbf808594d34a3d1a9258e5e69bcb953bbfda894b0d4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ZQRK7UQDGOJI7NLTBGCOUATNU5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pretraining Representations for Data-Efficient Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aaron Courville, Ankesh Anand, Devon Hjelm, Laurent Charlin, Max Schwarzer, Michael Noukhovitch, Nitarshan Rajkumar, Philip Bachman","submitted_at":"2021-06-09T04:14:27Z","abstract_excerpt":"Data efficiency is a key challenge for deep reinforcement learning. We address this problem by using unlabeled data to pretrain an encoder which is then finetuned on a small amount of task-specific data. To encourage learning representations which capture diverse aspects of the underlying MDP, we employ a combination of latent dynamics modelling and unsupervised goal-conditioned RL. When limited to 100k steps of interaction on Atari games (equivalent to two hours of human experience), our approach significantly surpasses prior work combining offline representation pretraining with task-specifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.04799","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/2106.04799/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":"2026-07-05T02:47:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rzlg5hCvoQCgqqARlr0QeD4rvFPeU+guHm0RXy5LlYvAhIQA+36+jBoh2Xvc/80EfDnOfPJjM5MpAThSKft8Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:31:23.015406Z"},"content_sha256":"f70ca1e27ceccca006c7a0967e95fb89b04750286874deda7f5ce298e3e60c51","schema_version":"1.0","event_id":"sha256:f70ca1e27ceccca006c7a0967e95fb89b04750286874deda7f5ce298e3e60c51"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZQRK7UQDGOJI7NLTBGCOUATNU5/bundle.json","state_url":"https://pith.science/pith/ZQRK7UQDGOJI7NLTBGCOUATNU5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZQRK7UQDGOJI7NLTBGCOUATNU5/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":"2026-08-06T18:31:23Z","links":{"resolver":"https://pith.science/pith/ZQRK7UQDGOJI7NLTBGCOUATNU5","bundle":"https://pith.science/pith/ZQRK7UQDGOJI7NLTBGCOUATNU5/bundle.json","state":"https://pith.science/pith/ZQRK7UQDGOJI7NLTBGCOUATNU5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZQRK7UQDGOJI7NLTBGCOUATNU5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZQRK7UQDGOJI7NLTBGCOUATNU5","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":"49e91e0cc1c25260bfa05c63e663f669a466c5b6bfc11f131b77c90918c6de85","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-09T04:14:27Z","title_canon_sha256":"8554da61a096a8540a022f2e177c75a770f17465307dec9b1c5cc194ebca7d1e"},"schema_version":"1.0","source":{"id":"2106.04799","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.04799","created_at":"2026-07-05T02:47:49Z"},{"alias_kind":"arxiv_version","alias_value":"2106.04799v1","created_at":"2026-07-05T02:47:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.04799","created_at":"2026-07-05T02:47:49Z"},{"alias_kind":"pith_short_12","alias_value":"ZQRK7UQDGOJI","created_at":"2026-07-05T02:47:49Z"},{"alias_kind":"pith_short_16","alias_value":"ZQRK7UQDGOJI7NLT","created_at":"2026-07-05T02:47:49Z"},{"alias_kind":"pith_short_8","alias_value":"ZQRK7UQD","created_at":"2026-07-05T02:47:49Z"}],"graph_snapshots":[{"event_id":"sha256:f70ca1e27ceccca006c7a0967e95fb89b04750286874deda7f5ce298e3e60c51","target":"graph","created_at":"2026-07-05T02:47:49Z","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/2106.04799/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data efficiency is a key challenge for deep reinforcement learning. We address this problem by using unlabeled data to pretrain an encoder which is then finetuned on a small amount of task-specific data. To encourage learning representations which capture diverse aspects of the underlying MDP, we employ a combination of latent dynamics modelling and unsupervised goal-conditioned RL. When limited to 100k steps of interaction on Atari games (equivalent to two hours of human experience), our approach significantly surpasses prior work combining offline representation pretraining with task-specifi","authors_text":"Aaron Courville, Ankesh Anand, Devon Hjelm, Laurent Charlin, Max Schwarzer, Michael Noukhovitch, Nitarshan Rajkumar, Philip Bachman","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-09T04:14:27Z","title":"Pretraining Representations for Data-Efficient Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.04799","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:fa13fd517dfb056a9faafbf808594d34a3d1a9258e5e69bcb953bbfda894b0d4","target":"record","created_at":"2026-07-05T02:47:49Z","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":"49e91e0cc1c25260bfa05c63e663f669a466c5b6bfc11f131b77c90918c6de85","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-09T04:14:27Z","title_canon_sha256":"8554da61a096a8540a022f2e177c75a770f17465307dec9b1c5cc194ebca7d1e"},"schema_version":"1.0","source":{"id":"2106.04799","kind":"arxiv","version":1}},"canonical_sha256":"cc22afd20333928fb5730984ea026da762f78b36655a86778b5dffda988c7d8c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc22afd20333928fb5730984ea026da762f78b36655a86778b5dffda988c7d8c","first_computed_at":"2026-07-05T02:47:49.264390Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:47:49.264390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7H1IsUT/XstwQ41uyz9aiBeD1LexSI/zG+Jqy4U7+ZgiRZNiS+4ZkZpf0JGmfY7pZ3Fk78knUy28MJ3u6MI3BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:47:49.264854Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.04799","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa13fd517dfb056a9faafbf808594d34a3d1a9258e5e69bcb953bbfda894b0d4","sha256:f70ca1e27ceccca006c7a0967e95fb89b04750286874deda7f5ce298e3e60c51"],"state_sha256":"bc30dd7442962e558614fa00fcead6ff0e191684deb9a722e4d6ec775700d6a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9ZU1Hy6b0Mjvgcm3wdpAxRN6Fk2rkpN1NUepSLOkSv4NJqY4Sf7mL8EI9BUIoh5KO/gmL3C+EJ7pbNKsqejjAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T18:31:23.020350Z","bundle_sha256":"296ed125a64b16ac018df50dd8fe31b41b99b5fe0965992d1f87c514cd6f3141"}}