{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:3IOPEMSZ5LWZSV65X33464YOQN","short_pith_number":"pith:3IOPEMSZ","canonical_record":{"source":{"id":"2108.05382","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-11T18:04:08Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"84f81ca8dce942ca8bf7f644e60f12e4311567f66fbc56ab6fde3073297da6aa","abstract_canon_sha256":"c1922c9d76ca8dd01b026eb410ac9e0c5017dae1b61155e15fa4f52c80bd40cd"},"schema_version":"1.0"},"canonical_sha256":"da1cf23259eaed9957ddbef7cf730e836e38a961cb143dce3b4ecbc2dc4f7e90","source":{"kind":"arxiv","id":"2108.05382","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.05382","created_at":"2026-07-05T03:05:14Z"},{"alias_kind":"arxiv_version","alias_value":"2108.05382v1","created_at":"2026-07-05T03:05:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.05382","created_at":"2026-07-05T03:05:14Z"},{"alias_kind":"pith_short_12","alias_value":"3IOPEMSZ5LWZ","created_at":"2026-07-05T03:05:14Z"},{"alias_kind":"pith_short_16","alias_value":"3IOPEMSZ5LWZSV65","created_at":"2026-07-05T03:05:14Z"},{"alias_kind":"pith_short_8","alias_value":"3IOPEMSZ","created_at":"2026-07-05T03:05:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:3IOPEMSZ5LWZSV65X33464YOQN","target":"record","payload":{"canonical_record":{"source":{"id":"2108.05382","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-11T18:04:08Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"84f81ca8dce942ca8bf7f644e60f12e4311567f66fbc56ab6fde3073297da6aa","abstract_canon_sha256":"c1922c9d76ca8dd01b026eb410ac9e0c5017dae1b61155e15fa4f52c80bd40cd"},"schema_version":"1.0"},"canonical_sha256":"da1cf23259eaed9957ddbef7cf730e836e38a961cb143dce3b4ecbc2dc4f7e90","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:05:14.186239Z","signature_b64":"54h96ZTJtzbdWRS8mZ7eSZxgYdCHfIhUXbS1oeFODhnKT/JHn6hadr0OAf9v46QC4iVzDxT0IWENX8kWYhLcCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da1cf23259eaed9957ddbef7cf730e836e38a961cb143dce3b4ecbc2dc4f7e90","last_reissued_at":"2026-07-05T03:05:14.185876Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:05:14.185876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.05382","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":"2026-07-05T03:05:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jLyxTeX71fStcHcTlFZImTtTrt4veP9/38FRQS+MOOL+FKu1v3nZjKue1BzRHezD3Dpd7sIlP+FDywIb4Ik1Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T12:33:16.452138Z"},"content_sha256":"5e50ba95dbaa69e760728db9c346144b8f18708fa8840eaea8fe7fa64c23c2f6","schema_version":"1.0","event_id":"sha256:5e50ba95dbaa69e760728db9c346144b8f18708fa8840eaea8fe7fa64c23c2f6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:3IOPEMSZ5LWZSV65X33464YOQN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Skill Preferences: Learning to Extract and Execute Robotic Skills from Human Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Kimin Lee, Kourosh Hakhamaneshi, Michael Laskin, Pieter Abbeel, Xiaofei Wang","submitted_at":"2021-08-11T18:04:08Z","abstract_excerpt":"A promising approach to solving challenging long-horizon tasks has been to extract behavior priors (skills) by fitting generative models to large offline datasets of demonstrations. However, such generative models inherit the biases of the underlying data and result in poor and unusable skills when trained on imperfect demonstration data. To better align skill extraction with human intent we present Skill Preferences (SkiP), an algorithm that learns a model over human preferences and uses it to extract human-aligned skills from offline data. After extracting human-preferred skills, SkiP also u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.05382","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/2108.05382/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":"2026-07-05T03:05:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SY3IYUaZ+TTDJHZ9zIpoIfuJX3nqVxLuJMizAM3/W1ovH5H+DxRSw8eUAJK4/YPuDKJdulCzVELrJ3eYnEZTCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T12:33:16.453115Z"},"content_sha256":"08da0581ca0a31fe51f2266bd2657d54afe4cdb9199652c76f7664e3d2731029","schema_version":"1.0","event_id":"sha256:08da0581ca0a31fe51f2266bd2657d54afe4cdb9199652c76f7664e3d2731029"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3IOPEMSZ5LWZSV65X33464YOQN/bundle.json","state_url":"https://pith.science/pith/3IOPEMSZ5LWZSV65X33464YOQN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3IOPEMSZ5LWZSV65X33464YOQN/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":"2026-08-18T12:33:16Z","links":{"resolver":"https://pith.science/pith/3IOPEMSZ5LWZSV65X33464YOQN","bundle":"https://pith.science/pith/3IOPEMSZ5LWZSV65X33464YOQN/bundle.json","state":"https://pith.science/pith/3IOPEMSZ5LWZSV65X33464YOQN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3IOPEMSZ5LWZSV65X33464YOQN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3IOPEMSZ5LWZSV65X33464YOQN","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":"c1922c9d76ca8dd01b026eb410ac9e0c5017dae1b61155e15fa4f52c80bd40cd","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-11T18:04:08Z","title_canon_sha256":"84f81ca8dce942ca8bf7f644e60f12e4311567f66fbc56ab6fde3073297da6aa"},"schema_version":"1.0","source":{"id":"2108.05382","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.05382","created_at":"2026-07-05T03:05:14Z"},{"alias_kind":"arxiv_version","alias_value":"2108.05382v1","created_at":"2026-07-05T03:05:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.05382","created_at":"2026-07-05T03:05:14Z"},{"alias_kind":"pith_short_12","alias_value":"3IOPEMSZ5LWZ","created_at":"2026-07-05T03:05:14Z"},{"alias_kind":"pith_short_16","alias_value":"3IOPEMSZ5LWZSV65","created_at":"2026-07-05T03:05:14Z"},{"alias_kind":"pith_short_8","alias_value":"3IOPEMSZ","created_at":"2026-07-05T03:05:14Z"}],"graph_snapshots":[{"event_id":"sha256:08da0581ca0a31fe51f2266bd2657d54afe4cdb9199652c76f7664e3d2731029","target":"graph","created_at":"2026-07-05T03:05:14Z","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/2108.05382/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A promising approach to solving challenging long-horizon tasks has been to extract behavior priors (skills) by fitting generative models to large offline datasets of demonstrations. However, such generative models inherit the biases of the underlying data and result in poor and unusable skills when trained on imperfect demonstration data. To better align skill extraction with human intent we present Skill Preferences (SkiP), an algorithm that learns a model over human preferences and uses it to extract human-aligned skills from offline data. After extracting human-preferred skills, SkiP also u","authors_text":"Kimin Lee, Kourosh Hakhamaneshi, Michael Laskin, Pieter Abbeel, Xiaofei Wang","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-11T18:04:08Z","title":"Skill Preferences: Learning to Extract and Execute Robotic Skills from Human Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.05382","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":"sha256:5e50ba95dbaa69e760728db9c346144b8f18708fa8840eaea8fe7fa64c23c2f6","target":"record","created_at":"2026-07-05T03:05:14Z","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":"c1922c9d76ca8dd01b026eb410ac9e0c5017dae1b61155e15fa4f52c80bd40cd","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-11T18:04:08Z","title_canon_sha256":"84f81ca8dce942ca8bf7f644e60f12e4311567f66fbc56ab6fde3073297da6aa"},"schema_version":"1.0","source":{"id":"2108.05382","kind":"arxiv","version":1}},"canonical_sha256":"da1cf23259eaed9957ddbef7cf730e836e38a961cb143dce3b4ecbc2dc4f7e90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da1cf23259eaed9957ddbef7cf730e836e38a961cb143dce3b4ecbc2dc4f7e90","first_computed_at":"2026-07-05T03:05:14.185876Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:05:14.185876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"54h96ZTJtzbdWRS8mZ7eSZxgYdCHfIhUXbS1oeFODhnKT/JHn6hadr0OAf9v46QC4iVzDxT0IWENX8kWYhLcCw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:05:14.186239Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.05382","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e50ba95dbaa69e760728db9c346144b8f18708fa8840eaea8fe7fa64c23c2f6","sha256:08da0581ca0a31fe51f2266bd2657d54afe4cdb9199652c76f7664e3d2731029"],"state_sha256":"039b3114d4f05bc264dfe537666a1fc23e14b0e64e41793ce1e7cda2609e25db"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4woNVLeqAIxk/8c2szrnlTQYDXXISFbxqF7h7rP8CtqcziRZtkg/Lla/Op0WrSKpiOlhYKljDhcAdSZPItccDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T12:33:16.460828Z","bundle_sha256":"8a4355f840e4b1c61ef3e40a6870492d0f60d176f0067b0278e5e94b123f1599"}}