{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LMQY3EFKHVGPJ3WHN67GC3JBYL","short_pith_number":"pith:LMQY3EFK","canonical_record":{"source":{"id":"2405.03379","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-06T11:33:12Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"0bfce0a8adf81fca1aea8d08ce795fb6324e2a2113d7ed364c54db0b6a225785","abstract_canon_sha256":"8638615d0e046934daaea0ba46583f4b3daf2d4873d2f567bb28bff91276aa44"},"schema_version":"1.0"},"canonical_sha256":"5b218d90aa3d4cf4eec76fbe616d21c2cc1da1472a57fd1c4c71eead804286ae","source":{"kind":"arxiv","id":"2405.03379","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.03379","created_at":"2026-07-05T08:16:02Z"},{"alias_kind":"arxiv_version","alias_value":"2405.03379v1","created_at":"2026-07-05T08:16:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03379","created_at":"2026-07-05T08:16:02Z"},{"alias_kind":"pith_short_12","alias_value":"LMQY3EFKHVGP","created_at":"2026-07-05T08:16:02Z"},{"alias_kind":"pith_short_16","alias_value":"LMQY3EFKHVGPJ3WH","created_at":"2026-07-05T08:16:02Z"},{"alias_kind":"pith_short_8","alias_value":"LMQY3EFK","created_at":"2026-07-05T08:16:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LMQY3EFKHVGPJ3WHN67GC3JBYL","target":"record","payload":{"canonical_record":{"source":{"id":"2405.03379","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-06T11:33:12Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"0bfce0a8adf81fca1aea8d08ce795fb6324e2a2113d7ed364c54db0b6a225785","abstract_canon_sha256":"8638615d0e046934daaea0ba46583f4b3daf2d4873d2f567bb28bff91276aa44"},"schema_version":"1.0"},"canonical_sha256":"5b218d90aa3d4cf4eec76fbe616d21c2cc1da1472a57fd1c4c71eead804286ae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:02.250590Z","signature_b64":"QkA0dEoVq/XN7mJSK0zmxKfWtwG7OjeiLWWgppcdUQ0hq+cLzeLYtZXJNu0+aQakcuNVTXvJ3laMvlb/NxezBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b218d90aa3d4cf4eec76fbe616d21c2cc1da1472a57fd1c4c71eead804286ae","last_reissued_at":"2026-07-05T08:16:02.250102Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:02.250102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.03379","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":"2026-07-05T08:16:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BmCfaG6iD7yOZx6/EtAte4Hi0yrvu1EMwZUYkeqZBWf65xBT32tuFMF047uX3eNDwPGg70uMF9GOS4M7QtyjAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T17:17:26.507125Z"},"content_sha256":"765cef170748db1ea20e0cef37114e0511317969295bca388d06ac69efb08918","schema_version":"1.0","event_id":"sha256:765cef170748db1ea20e0cef37114e0511317969295bca388d06ac69efb08918"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LMQY3EFKHVGPJ3WHN67GC3JBYL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reverse Forward Curriculum Learning for Extreme Sample and Demonstration Efficiency in Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Arth Shukla, Hao Su, Stone Tao, Tse-kai Chan","submitted_at":"2024-05-06T11:33:12Z","abstract_excerpt":"Reinforcement learning (RL) presents a promising framework to learn policies through environment interaction, but often requires an infeasible amount of interaction data to solve complex tasks from sparse rewards. One direction includes augmenting RL with offline data demonstrating desired tasks, but past work often require a lot of high-quality demonstration data that is difficult to obtain, especially for domains such as robotics. Our approach consists of a reverse curriculum followed by a forward curriculum. Unique to our approach compared to past work is the ability to efficiently leverage"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03379","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/2405.03379/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":"2026-07-05T08:16:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Gbfe4XqHRNU3QR04h170zlOj4A8m4p/bbxTBit528Zy60ZiJwhQcQBqppiZdu6TZMdlhAcuIzFHVSfWHaIPDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T17:17:26.508191Z"},"content_sha256":"a0bc8e9bf25d5639b28ca4321404dbc83677b9bb38b79b638c45d79332c58e8b","schema_version":"1.0","event_id":"sha256:a0bc8e9bf25d5639b28ca4321404dbc83677b9bb38b79b638c45d79332c58e8b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LMQY3EFKHVGPJ3WHN67GC3JBYL/bundle.json","state_url":"https://pith.science/pith/LMQY3EFKHVGPJ3WHN67GC3JBYL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LMQY3EFKHVGPJ3WHN67GC3JBYL/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":"2026-08-13T17:17:26Z","links":{"resolver":"https://pith.science/pith/LMQY3EFKHVGPJ3WHN67GC3JBYL","bundle":"https://pith.science/pith/LMQY3EFKHVGPJ3WHN67GC3JBYL/bundle.json","state":"https://pith.science/pith/LMQY3EFKHVGPJ3WHN67GC3JBYL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LMQY3EFKHVGPJ3WHN67GC3JBYL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LMQY3EFKHVGPJ3WHN67GC3JBYL","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":"8638615d0e046934daaea0ba46583f4b3daf2d4873d2f567bb28bff91276aa44","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-06T11:33:12Z","title_canon_sha256":"0bfce0a8adf81fca1aea8d08ce795fb6324e2a2113d7ed364c54db0b6a225785"},"schema_version":"1.0","source":{"id":"2405.03379","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.03379","created_at":"2026-07-05T08:16:02Z"},{"alias_kind":"arxiv_version","alias_value":"2405.03379v1","created_at":"2026-07-05T08:16:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03379","created_at":"2026-07-05T08:16:02Z"},{"alias_kind":"pith_short_12","alias_value":"LMQY3EFKHVGP","created_at":"2026-07-05T08:16:02Z"},{"alias_kind":"pith_short_16","alias_value":"LMQY3EFKHVGPJ3WH","created_at":"2026-07-05T08:16:02Z"},{"alias_kind":"pith_short_8","alias_value":"LMQY3EFK","created_at":"2026-07-05T08:16:02Z"}],"graph_snapshots":[{"event_id":"sha256:a0bc8e9bf25d5639b28ca4321404dbc83677b9bb38b79b638c45d79332c58e8b","target":"graph","created_at":"2026-07-05T08:16:02Z","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/2405.03379/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) presents a promising framework to learn policies through environment interaction, but often requires an infeasible amount of interaction data to solve complex tasks from sparse rewards. One direction includes augmenting RL with offline data demonstrating desired tasks, but past work often require a lot of high-quality demonstration data that is difficult to obtain, especially for domains such as robotics. Our approach consists of a reverse curriculum followed by a forward curriculum. Unique to our approach compared to past work is the ability to efficiently leverage","authors_text":"Arth Shukla, Hao Su, Stone Tao, Tse-kai Chan","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-06T11:33:12Z","title":"Reverse Forward Curriculum Learning for Extreme Sample and Demonstration Efficiency in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03379","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":"sha256:765cef170748db1ea20e0cef37114e0511317969295bca388d06ac69efb08918","target":"record","created_at":"2026-07-05T08:16:02Z","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":"8638615d0e046934daaea0ba46583f4b3daf2d4873d2f567bb28bff91276aa44","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-06T11:33:12Z","title_canon_sha256":"0bfce0a8adf81fca1aea8d08ce795fb6324e2a2113d7ed364c54db0b6a225785"},"schema_version":"1.0","source":{"id":"2405.03379","kind":"arxiv","version":1}},"canonical_sha256":"5b218d90aa3d4cf4eec76fbe616d21c2cc1da1472a57fd1c4c71eead804286ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b218d90aa3d4cf4eec76fbe616d21c2cc1da1472a57fd1c4c71eead804286ae","first_computed_at":"2026-07-05T08:16:02.250102Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:16:02.250102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QkA0dEoVq/XN7mJSK0zmxKfWtwG7OjeiLWWgppcdUQ0hq+cLzeLYtZXJNu0+aQakcuNVTXvJ3laMvlb/NxezBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:16:02.250590Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.03379","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:765cef170748db1ea20e0cef37114e0511317969295bca388d06ac69efb08918","sha256:a0bc8e9bf25d5639b28ca4321404dbc83677b9bb38b79b638c45d79332c58e8b"],"state_sha256":"7ad8405cc77ca0bc8d1f9a276f80c3d1208aaf91e4093f4797922fe39e9bf5a3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nXMMebbZuB+FPLzQWQwbP1WE856cSHBxyweFvRB4hvxAuw/o9QlfTjZ1HD09HxQgDmUar9xbRxxQ/63hAdN5Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T17:17:26.589327Z","bundle_sha256":"9017cb1ee2f794bcb5bc4ea5be945e864ea5ef34240a16b5ff7615104806b113"}}