{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:SO3IYOLQO5JKKPGI6OZHLCMR7Z","short_pith_number":"pith:SO3IYOLQ","canonical_record":{"source":{"id":"2107.12931","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-27T16:39:45Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"c0b009b0b44c6cef92b1f947c7ca912980d74993d5c70ab24482d9473565409c","abstract_canon_sha256":"a942eb35d00188c34464b8eb5ed03abfa8151767a3eb9445c76a9c3dd78446b5"},"schema_version":"1.0"},"canonical_sha256":"93b68c39707752a53cc8f3b2758991fe6b9d614bfd23790d48ff19c8066b9ac8","source":{"kind":"arxiv","id":"2107.12931","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.12931","created_at":"2026-07-05T03:26:43Z"},{"alias_kind":"arxiv_version","alias_value":"2107.12931v2","created_at":"2026-07-05T03:26:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.12931","created_at":"2026-07-05T03:26:43Z"},{"alias_kind":"pith_short_12","alias_value":"SO3IYOLQO5JK","created_at":"2026-07-05T03:26:43Z"},{"alias_kind":"pith_short_16","alias_value":"SO3IYOLQO5JKKPGI","created_at":"2026-07-05T03:26:43Z"},{"alias_kind":"pith_short_8","alias_value":"SO3IYOLQ","created_at":"2026-07-05T03:26:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:SO3IYOLQO5JKKPGI6OZHLCMR7Z","target":"record","payload":{"canonical_record":{"source":{"id":"2107.12931","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-27T16:39:45Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"c0b009b0b44c6cef92b1f947c7ca912980d74993d5c70ab24482d9473565409c","abstract_canon_sha256":"a942eb35d00188c34464b8eb5ed03abfa8151767a3eb9445c76a9c3dd78446b5"},"schema_version":"1.0"},"canonical_sha256":"93b68c39707752a53cc8f3b2758991fe6b9d614bfd23790d48ff19c8066b9ac8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:43.224378Z","signature_b64":"4IeAU833MCdAZL8P90nWwtdLpALw5yHnymZ7IMNFIBmp8Lc6bVFXBh70Hb74Tw8xx2FbA+p/HhIhidQDqqBvDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93b68c39707752a53cc8f3b2758991fe6b9d614bfd23790d48ff19c8066b9ac8","last_reissued_at":"2026-07-05T03:26:43.223851Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:43.223851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.12931","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":"2026-07-05T03:26:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WKi0XMk2yxM1fR/k2SBtKS9M3/uUiz66Glg71O8ymD4aOUcjRNwd5dshl2fwlLUF5+61qJMWXyTZREWE9qnFDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T18:42:15.948366Z"},"content_sha256":"1f9ccf835f4b8d1ef1e7ab4fe8f361cd50dad52bd9d0cf1b9ea3331856aadb90","schema_version":"1.0","event_id":"sha256:1f9ccf835f4b8d1ef1e7ab4fe8f361cd50dad52bd9d0cf1b9ea3331856aadb90"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:SO3IYOLQO5JKKPGI6OZHLCMR7Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Autonomous Reinforcement Learning via Subgoal Curricula","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Archit Sharma, Chelsea Finn, Karol Hausman, Sergey Levine","submitted_at":"2021-07-27T16:39:45Z","abstract_excerpt":"Reinforcement learning (RL) promises to enable autonomous acquisition of complex behaviors for diverse agents. However, the success of current reinforcement learning algorithms is predicated on an often under-emphasised requirement -- each trial needs to start from a fixed initial state distribution. Unfortunately, resetting the environment to its initial state after each trial requires substantial amount of human supervision and extensive instrumentation of the environment which defeats the goal of autonomous acquisition of complex behaviors. In this work, we propose Value-accelerated Persist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.12931","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/2107.12931/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":"2026-07-05T03:26:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kVdQKziRnFUXSpvGc+TXFTqrAPi/L6Sv4IxliU+K7k7ya6oepwWU9o/vLukTGUS/j6UMogkhhxIzsHOLfYMhAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T18:42:15.949368Z"},"content_sha256":"4cb4633bb065592dd8511d7df6d8d03f7ffd37cfde2c6b7df49f70db314fb0f1","schema_version":"1.0","event_id":"sha256:4cb4633bb065592dd8511d7df6d8d03f7ffd37cfde2c6b7df49f70db314fb0f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SO3IYOLQO5JKKPGI6OZHLCMR7Z/bundle.json","state_url":"https://pith.science/pith/SO3IYOLQO5JKKPGI6OZHLCMR7Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SO3IYOLQO5JKKPGI6OZHLCMR7Z/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":"2026-08-13T18:42:15Z","links":{"resolver":"https://pith.science/pith/SO3IYOLQO5JKKPGI6OZHLCMR7Z","bundle":"https://pith.science/pith/SO3IYOLQO5JKKPGI6OZHLCMR7Z/bundle.json","state":"https://pith.science/pith/SO3IYOLQO5JKKPGI6OZHLCMR7Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SO3IYOLQO5JKKPGI6OZHLCMR7Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:SO3IYOLQO5JKKPGI6OZHLCMR7Z","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":"a942eb35d00188c34464b8eb5ed03abfa8151767a3eb9445c76a9c3dd78446b5","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-27T16:39:45Z","title_canon_sha256":"c0b009b0b44c6cef92b1f947c7ca912980d74993d5c70ab24482d9473565409c"},"schema_version":"1.0","source":{"id":"2107.12931","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.12931","created_at":"2026-07-05T03:26:43Z"},{"alias_kind":"arxiv_version","alias_value":"2107.12931v2","created_at":"2026-07-05T03:26:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.12931","created_at":"2026-07-05T03:26:43Z"},{"alias_kind":"pith_short_12","alias_value":"SO3IYOLQO5JK","created_at":"2026-07-05T03:26:43Z"},{"alias_kind":"pith_short_16","alias_value":"SO3IYOLQO5JKKPGI","created_at":"2026-07-05T03:26:43Z"},{"alias_kind":"pith_short_8","alias_value":"SO3IYOLQ","created_at":"2026-07-05T03:26:43Z"}],"graph_snapshots":[{"event_id":"sha256:4cb4633bb065592dd8511d7df6d8d03f7ffd37cfde2c6b7df49f70db314fb0f1","target":"graph","created_at":"2026-07-05T03:26:43Z","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/2107.12931/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) promises to enable autonomous acquisition of complex behaviors for diverse agents. However, the success of current reinforcement learning algorithms is predicated on an often under-emphasised requirement -- each trial needs to start from a fixed initial state distribution. Unfortunately, resetting the environment to its initial state after each trial requires substantial amount of human supervision and extensive instrumentation of the environment which defeats the goal of autonomous acquisition of complex behaviors. In this work, we propose Value-accelerated Persist","authors_text":"Abhishek Gupta, Archit Sharma, Chelsea Finn, Karol Hausman, Sergey Levine","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-27T16:39:45Z","title":"Autonomous Reinforcement Learning via Subgoal Curricula"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.12931","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":"sha256:1f9ccf835f4b8d1ef1e7ab4fe8f361cd50dad52bd9d0cf1b9ea3331856aadb90","target":"record","created_at":"2026-07-05T03:26:43Z","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":"a942eb35d00188c34464b8eb5ed03abfa8151767a3eb9445c76a9c3dd78446b5","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-27T16:39:45Z","title_canon_sha256":"c0b009b0b44c6cef92b1f947c7ca912980d74993d5c70ab24482d9473565409c"},"schema_version":"1.0","source":{"id":"2107.12931","kind":"arxiv","version":2}},"canonical_sha256":"93b68c39707752a53cc8f3b2758991fe6b9d614bfd23790d48ff19c8066b9ac8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93b68c39707752a53cc8f3b2758991fe6b9d614bfd23790d48ff19c8066b9ac8","first_computed_at":"2026-07-05T03:26:43.223851Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:26:43.223851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4IeAU833MCdAZL8P90nWwtdLpALw5yHnymZ7IMNFIBmp8Lc6bVFXBh70Hb74Tw8xx2FbA+p/HhIhidQDqqBvDA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:26:43.224378Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.12931","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f9ccf835f4b8d1ef1e7ab4fe8f361cd50dad52bd9d0cf1b9ea3331856aadb90","sha256:4cb4633bb065592dd8511d7df6d8d03f7ffd37cfde2c6b7df49f70db314fb0f1"],"state_sha256":"7fab315e8957e25e71d274440f9569e496bafb1e3b0f5e87a42d5f752142c54b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6M6fveJU4q2xIMCs6BHpuEV9e7YAH1UFUuFAiGCBU7x9pXH/f342m1ZzYE/2L8ZjOpq37Sn4J8qF+YZhwkV5BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T18:42:15.969145Z","bundle_sha256":"56fc671b209b5bf03e2d45c46ed36f215a795fe436ee51ec3caa0221d24ebebf"}}