{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7HGUMUCXZER5CNOULKGYV3JZIE","short_pith_number":"pith:7HGUMUCX","canonical_record":{"source":{"id":"2307.15801","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-07-28T20:48:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a8c3c699c89339809f35dda695bacbd5b37d98c459fb7103cf361cf0f764a385","abstract_canon_sha256":"378de7cd9e1bde425a308f53c3f479b7ec862b75416971ca43cffc210d3d92c9"},"schema_version":"1.0"},"canonical_sha256":"f9cd465057c923d135d45a8d8aed39410867291155ea018e5cb96dd3e7b09686","source":{"kind":"arxiv","id":"2307.15801","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.15801","created_at":"2026-07-05T06:36:55Z"},{"alias_kind":"arxiv_version","alias_value":"2307.15801v2","created_at":"2026-07-05T06:36:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15801","created_at":"2026-07-05T06:36:55Z"},{"alias_kind":"pith_short_12","alias_value":"7HGUMUCXZER5","created_at":"2026-07-05T06:36:55Z"},{"alias_kind":"pith_short_16","alias_value":"7HGUMUCXZER5CNOU","created_at":"2026-07-05T06:36:55Z"},{"alias_kind":"pith_short_8","alias_value":"7HGUMUCX","created_at":"2026-07-05T06:36:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7HGUMUCXZER5CNOULKGYV3JZIE","target":"record","payload":{"canonical_record":{"source":{"id":"2307.15801","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-07-28T20:48:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a8c3c699c89339809f35dda695bacbd5b37d98c459fb7103cf361cf0f764a385","abstract_canon_sha256":"378de7cd9e1bde425a308f53c3f479b7ec862b75416971ca43cffc210d3d92c9"},"schema_version":"1.0"},"canonical_sha256":"f9cd465057c923d135d45a8d8aed39410867291155ea018e5cb96dd3e7b09686","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:36:55.606375Z","signature_b64":"GDCPR61o7Ivfb2hCkK2bz38zJ1I04GZ1MObWJubNb8haVY4as8VzRjedT9lDwrZiz7NBWD1YesR7LNhYUHVTDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9cd465057c923d135d45a8d8aed39410867291155ea018e5cb96dd3e7b09686","last_reissued_at":"2026-07-05T06:36:55.605896Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:36:55.605896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.15801","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":"2026-07-05T06:36:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o7wvYVoQp0fpsi9ckd1p4LAl6RW103yh4bNyOE3NhMhfAn7WG+2BU9y6tP5GpRQkIzbSvQvAFIPL86zkcmBcBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T02:15:19.754932Z"},"content_sha256":"51de7a20bee254a6193ee7f8f178082ab6526d1bfeb5091c112bf91125e266e2","schema_version":"1.0","event_id":"sha256:51de7a20bee254a6193ee7f8f178082ab6526d1bfeb5091c112bf91125e266e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7HGUMUCXZER5CNOULKGYV3JZIE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Primitive Skill-based Robot Learning from Human Evaluative Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Ayano Hiranaka, Chen Wang, Jiajun Wu, Li Fei-Fei, Minjune Hwang, Ruohan Zhang, Sharon Lee","submitted_at":"2023-07-28T20:48:30Z","abstract_excerpt":"Reinforcement learning (RL) algorithms face significant challenges when dealing with long-horizon robot manipulation tasks in real-world environments due to sample inefficiency and safety issues. To overcome these challenges, we propose a novel framework, SEED, which leverages two approaches: reinforcement learning from human feedback (RLHF) and primitive skill-based reinforcement learning. Both approaches are particularly effective in addressing sparse reward issues and the complexities involved in long-horizon tasks. By combining them, SEED reduces the human effort required in RLHF and incre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15801","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/2307.15801/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":"2026-07-05T06:36:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gfwfKe9/czxA7Vhs3HiJkWkIatkPgotiMhUhRdiQy8DSMo2SMhlcyDRaekKgQfQn79vrOC6HdZ+mqVD8qxeUDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T02:15:19.755270Z"},"content_sha256":"54ec8f64d5697308b949e73b28e90cc84458eb7410cd8f0aad62b04f9b8a152f","schema_version":"1.0","event_id":"sha256:54ec8f64d5697308b949e73b28e90cc84458eb7410cd8f0aad62b04f9b8a152f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7HGUMUCXZER5CNOULKGYV3JZIE/bundle.json","state_url":"https://pith.science/pith/7HGUMUCXZER5CNOULKGYV3JZIE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7HGUMUCXZER5CNOULKGYV3JZIE/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":"2026-08-22T02:15:19Z","links":{"resolver":"https://pith.science/pith/7HGUMUCXZER5CNOULKGYV3JZIE","bundle":"https://pith.science/pith/7HGUMUCXZER5CNOULKGYV3JZIE/bundle.json","state":"https://pith.science/pith/7HGUMUCXZER5CNOULKGYV3JZIE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7HGUMUCXZER5CNOULKGYV3JZIE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7HGUMUCXZER5CNOULKGYV3JZIE","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":"378de7cd9e1bde425a308f53c3f479b7ec862b75416971ca43cffc210d3d92c9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-07-28T20:48:30Z","title_canon_sha256":"a8c3c699c89339809f35dda695bacbd5b37d98c459fb7103cf361cf0f764a385"},"schema_version":"1.0","source":{"id":"2307.15801","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.15801","created_at":"2026-07-05T06:36:55Z"},{"alias_kind":"arxiv_version","alias_value":"2307.15801v2","created_at":"2026-07-05T06:36:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15801","created_at":"2026-07-05T06:36:55Z"},{"alias_kind":"pith_short_12","alias_value":"7HGUMUCXZER5","created_at":"2026-07-05T06:36:55Z"},{"alias_kind":"pith_short_16","alias_value":"7HGUMUCXZER5CNOU","created_at":"2026-07-05T06:36:55Z"},{"alias_kind":"pith_short_8","alias_value":"7HGUMUCX","created_at":"2026-07-05T06:36:55Z"}],"graph_snapshots":[{"event_id":"sha256:54ec8f64d5697308b949e73b28e90cc84458eb7410cd8f0aad62b04f9b8a152f","target":"graph","created_at":"2026-07-05T06:36:55Z","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/2307.15801/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) algorithms face significant challenges when dealing with long-horizon robot manipulation tasks in real-world environments due to sample inefficiency and safety issues. To overcome these challenges, we propose a novel framework, SEED, which leverages two approaches: reinforcement learning from human feedback (RLHF) and primitive skill-based reinforcement learning. Both approaches are particularly effective in addressing sparse reward issues and the complexities involved in long-horizon tasks. By combining them, SEED reduces the human effort required in RLHF and incre","authors_text":"Ayano Hiranaka, Chen Wang, Jiajun Wu, Li Fei-Fei, Minjune Hwang, Ruohan Zhang, Sharon Lee","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-07-28T20:48:30Z","title":"Primitive Skill-based Robot Learning from Human Evaluative Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15801","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":"sha256:51de7a20bee254a6193ee7f8f178082ab6526d1bfeb5091c112bf91125e266e2","target":"record","created_at":"2026-07-05T06:36:55Z","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":"378de7cd9e1bde425a308f53c3f479b7ec862b75416971ca43cffc210d3d92c9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-07-28T20:48:30Z","title_canon_sha256":"a8c3c699c89339809f35dda695bacbd5b37d98c459fb7103cf361cf0f764a385"},"schema_version":"1.0","source":{"id":"2307.15801","kind":"arxiv","version":2}},"canonical_sha256":"f9cd465057c923d135d45a8d8aed39410867291155ea018e5cb96dd3e7b09686","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9cd465057c923d135d45a8d8aed39410867291155ea018e5cb96dd3e7b09686","first_computed_at":"2026-07-05T06:36:55.605896Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:36:55.605896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GDCPR61o7Ivfb2hCkK2bz38zJ1I04GZ1MObWJubNb8haVY4as8VzRjedT9lDwrZiz7NBWD1YesR7LNhYUHVTDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:36:55.606375Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.15801","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51de7a20bee254a6193ee7f8f178082ab6526d1bfeb5091c112bf91125e266e2","sha256:54ec8f64d5697308b949e73b28e90cc84458eb7410cd8f0aad62b04f9b8a152f"],"state_sha256":"14fe02b5e17f5311f40e46b75d421f074cbd2ff80b211ac076e008422604aeb3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SXM/ABgOZJE9iaSrO0MJm034kjIdG31mWyP5EitaBm/3MuNN0RMJM9ug0WxWpNDPD3Xlx/BT8EkC8eoR5/HHCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T02:15:19.759581Z","bundle_sha256":"89c216a915911fe53812d678c18ab6f0b81f8286d670e9614b76d34dcef825ea"}}