{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:W3XM67W7Z52BXDXZG3Q7YNRIA7","short_pith_number":"pith:W3XM67W7","canonical_record":{"source":{"id":"2410.18076","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-23T17:58:45Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"64c5b308469caac12989855236599954cde746fe6913b22a7933657389a6b7df","abstract_canon_sha256":"9d814e7747f1bf4055a73deff85349184dee5431a18893d785db85d3119577a8"},"schema_version":"1.0"},"canonical_sha256":"b6eecf7edfcf741b8ef936e1fc362807efadebe83f6fe1f2abd49d308f4bcedf","source":{"kind":"arxiv","id":"2410.18076","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.18076","created_at":"2026-07-05T11:35:51Z"},{"alias_kind":"arxiv_version","alias_value":"2410.18076v4","created_at":"2026-07-05T11:35:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18076","created_at":"2026-07-05T11:35:51Z"},{"alias_kind":"pith_short_12","alias_value":"W3XM67W7Z52B","created_at":"2026-07-05T11:35:51Z"},{"alias_kind":"pith_short_16","alias_value":"W3XM67W7Z52BXDXZ","created_at":"2026-07-05T11:35:51Z"},{"alias_kind":"pith_short_8","alias_value":"W3XM67W7","created_at":"2026-07-05T11:35:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:W3XM67W7Z52BXDXZG3Q7YNRIA7","target":"record","payload":{"canonical_record":{"source":{"id":"2410.18076","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-23T17:58:45Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"64c5b308469caac12989855236599954cde746fe6913b22a7933657389a6b7df","abstract_canon_sha256":"9d814e7747f1bf4055a73deff85349184dee5431a18893d785db85d3119577a8"},"schema_version":"1.0"},"canonical_sha256":"b6eecf7edfcf741b8ef936e1fc362807efadebe83f6fe1f2abd49d308f4bcedf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:51.731895Z","signature_b64":"huLZQtM7I9U6Xk5y3rpUEbt0xHLjRKiARG0RpXw6RBkGvDbwt1YZdC8G3HvfU553ewDtg0/WTVo5zZ7iXD47Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6eecf7edfcf741b8ef936e1fc362807efadebe83f6fe1f2abd49d308f4bcedf","last_reissued_at":"2026-07-05T11:35:51.731446Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:51.731446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.18076","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:35:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZjkobgZPenqjIunobx87Se+HaSMJtrEanTSRZ2tJsIMxMVwWsNHQuWdTDrXA5gJG2+0pozqS/7QdpN7bZctBAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:11:09.701567Z"},"content_sha256":"1448e80ea4d796381552303abd46b5ed353ba8807c84832856ae3bbbc7f5945a","schema_version":"1.0","event_id":"sha256:1448e80ea4d796381552303abd46b5ed353ba8807c84832856ae3bbbc7f5945a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:W3XM67W7Z52BXDXZG3Q7YNRIA7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kevin Frans, Max Wilcoxson, Qiyang Li, Sergey Levine","submitted_at":"2024-10-23T17:58:45Z","abstract_excerpt":"Unsupervised pretraining has been transformative in many supervised domains. However, applying such ideas to reinforcement learning (RL) presents a unique challenge in that fine-tuning does not involve mimicking task-specific data, but rather exploring and locating the solution through iterative self-improvement. In this work, we study how unlabeled offline trajectory data can be leveraged to learn efficient exploration strategies. While prior data can be used to pretrain a set of low-level skills, or as additional off-policy data for online RL, it has been unclear how to combine these ideas e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18076","kind":"arxiv","version":4},"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/2410.18076/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":"2026-07-05T11:35:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1w++/jHaZS+rlYWme74I8C57m6O+uT2b4fmQCZ7aI/QQhnujaGaeA71lY/pTBCVvmgASzu2GlVB/qjnuG/sMAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:11:09.702462Z"},"content_sha256":"278bd0abd488e00c2e61fc4cd2cbc105181274ef94907304189c560a92602f94","schema_version":"1.0","event_id":"sha256:278bd0abd488e00c2e61fc4cd2cbc105181274ef94907304189c560a92602f94"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W3XM67W7Z52BXDXZG3Q7YNRIA7/bundle.json","state_url":"https://pith.science/pith/W3XM67W7Z52BXDXZG3Q7YNRIA7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W3XM67W7Z52BXDXZG3Q7YNRIA7/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":"2026-08-10T12:11:09Z","links":{"resolver":"https://pith.science/pith/W3XM67W7Z52BXDXZG3Q7YNRIA7","bundle":"https://pith.science/pith/W3XM67W7Z52BXDXZG3Q7YNRIA7/bundle.json","state":"https://pith.science/pith/W3XM67W7Z52BXDXZG3Q7YNRIA7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W3XM67W7Z52BXDXZG3Q7YNRIA7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:W3XM67W7Z52BXDXZG3Q7YNRIA7","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":"9d814e7747f1bf4055a73deff85349184dee5431a18893d785db85d3119577a8","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-23T17:58:45Z","title_canon_sha256":"64c5b308469caac12989855236599954cde746fe6913b22a7933657389a6b7df"},"schema_version":"1.0","source":{"id":"2410.18076","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.18076","created_at":"2026-07-05T11:35:51Z"},{"alias_kind":"arxiv_version","alias_value":"2410.18076v4","created_at":"2026-07-05T11:35:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18076","created_at":"2026-07-05T11:35:51Z"},{"alias_kind":"pith_short_12","alias_value":"W3XM67W7Z52B","created_at":"2026-07-05T11:35:51Z"},{"alias_kind":"pith_short_16","alias_value":"W3XM67W7Z52BXDXZ","created_at":"2026-07-05T11:35:51Z"},{"alias_kind":"pith_short_8","alias_value":"W3XM67W7","created_at":"2026-07-05T11:35:51Z"}],"graph_snapshots":[{"event_id":"sha256:278bd0abd488e00c2e61fc4cd2cbc105181274ef94907304189c560a92602f94","target":"graph","created_at":"2026-07-05T11:35:51Z","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/2410.18076/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unsupervised pretraining has been transformative in many supervised domains. However, applying such ideas to reinforcement learning (RL) presents a unique challenge in that fine-tuning does not involve mimicking task-specific data, but rather exploring and locating the solution through iterative self-improvement. In this work, we study how unlabeled offline trajectory data can be leveraged to learn efficient exploration strategies. While prior data can be used to pretrain a set of low-level skills, or as additional off-policy data for online RL, it has been unclear how to combine these ideas e","authors_text":"Kevin Frans, Max Wilcoxson, Qiyang Li, Sergey Levine","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-23T17:58:45Z","title":"Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18076","kind":"arxiv","version":4},"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":"sha256:1448e80ea4d796381552303abd46b5ed353ba8807c84832856ae3bbbc7f5945a","target":"record","created_at":"2026-07-05T11:35:51Z","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":"9d814e7747f1bf4055a73deff85349184dee5431a18893d785db85d3119577a8","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-23T17:58:45Z","title_canon_sha256":"64c5b308469caac12989855236599954cde746fe6913b22a7933657389a6b7df"},"schema_version":"1.0","source":{"id":"2410.18076","kind":"arxiv","version":4}},"canonical_sha256":"b6eecf7edfcf741b8ef936e1fc362807efadebe83f6fe1f2abd49d308f4bcedf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6eecf7edfcf741b8ef936e1fc362807efadebe83f6fe1f2abd49d308f4bcedf","first_computed_at":"2026-07-05T11:35:51.731446Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:51.731446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"huLZQtM7I9U6Xk5y3rpUEbt0xHLjRKiARG0RpXw6RBkGvDbwt1YZdC8G3HvfU553ewDtg0/WTVo5zZ7iXD47Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:51.731895Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.18076","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1448e80ea4d796381552303abd46b5ed353ba8807c84832856ae3bbbc7f5945a","sha256:278bd0abd488e00c2e61fc4cd2cbc105181274ef94907304189c560a92602f94"],"state_sha256":"090892df53013468744fb644b700178c0c479f66d7d15aab141b55795f7b12ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rtVTvF8eTDJMGmekMix4LwAE4aOU8yEfbc4TK0DjtU52aRYCtPmdYhaBi4fNoIHrRNv4vm1Wxcw814Gw3D8hBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T12:11:09.710530Z","bundle_sha256":"3eafdfba18ff7ce034040290faa60fbc855858378386455c2d65205744c3bd79"}}