{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:YFLQ4KBZW2VSUBVMIX2KVUTKI5","short_pith_number":"pith:YFLQ4KBZ","canonical_record":{"source":{"id":"2107.01969","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-05T12:18:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c63ab21470ab855d4ed2851c18a67f0ff43a51ae7e95e7a690ce1744bed953d9","abstract_canon_sha256":"f216fb479b5658106f395e546194a0c3a51a6912332444bf58a828a0cc49ce29"},"schema_version":"1.0"},"canonical_sha256":"c1570e2839b6ab2a06ac45f4aad26a475d7b80ad3b631977fc78536cbcfd3a60","source":{"kind":"arxiv","id":"2107.01969","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.01969","created_at":"2026-07-05T02:55:02Z"},{"alias_kind":"arxiv_version","alias_value":"2107.01969v1","created_at":"2026-07-05T02:55:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.01969","created_at":"2026-07-05T02:55:02Z"},{"alias_kind":"pith_short_12","alias_value":"YFLQ4KBZW2VS","created_at":"2026-07-05T02:55:02Z"},{"alias_kind":"pith_short_16","alias_value":"YFLQ4KBZW2VSUBVM","created_at":"2026-07-05T02:55:02Z"},{"alias_kind":"pith_short_8","alias_value":"YFLQ4KBZ","created_at":"2026-07-05T02:55:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:YFLQ4KBZW2VSUBVMIX2KVUTKI5","target":"record","payload":{"canonical_record":{"source":{"id":"2107.01969","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-05T12:18:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c63ab21470ab855d4ed2851c18a67f0ff43a51ae7e95e7a690ce1744bed953d9","abstract_canon_sha256":"f216fb479b5658106f395e546194a0c3a51a6912332444bf58a828a0cc49ce29"},"schema_version":"1.0"},"canonical_sha256":"c1570e2839b6ab2a06ac45f4aad26a475d7b80ad3b631977fc78536cbcfd3a60","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:55:02.362339Z","signature_b64":"+iL7LCmnesIDA9mcWfyhekkqhqLZOAQc73E7PTMofhXpfNWMsEcKTZSQwJoVaXvpnUj6bolePhiUqnOg9DHrAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1570e2839b6ab2a06ac45f4aad26a475d7b80ad3b631977fc78536cbcfd3a60","last_reissued_at":"2026-07-05T02:55:02.361925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:55:02.361925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.01969","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":"2026-07-05T02:55:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EYAouH0BjOLbGNTy6OTMm1QPxyQ4sG/d4W+z6a7y+HHCrJ2lnhwHw54YphTLIs7aObtFUV2cN97TuERu0di8CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:45:34.329951Z"},"content_sha256":"e1b2134735443e07bb26a92635023af6e5318baa9c25fbd639df99b9806b37f3","schema_version":"1.0","event_id":"sha256:e1b2134735443e07bb26a92635023af6e5318baa9c25fbd639df99b9806b37f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:YFLQ4KBZW2VSUBVMIX2KVUTKI5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The MineRL BASALT Competition on Learning from Human Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anca Dragan, Anssi Kanervisto, Brandon Houghton, Cody Wild, Neel Alex, Nicholay Topin, Pieter Abbeel, Rohin Shah, Sharada Mohanty, Stephanie Milani, Steven H. Wang, Stuart Russell, William Guss","submitted_at":"2021-07-05T12:18:17Z","abstract_excerpt":"The last decade has seen a significant increase of interest in deep learning research, with many public successes that have demonstrated its potential. As such, these systems are now being incorporated into commercial products. With this comes an additional challenge: how can we build AI systems that solve tasks where there is not a crisp, well-defined specification? While multiple solutions have been proposed, in this competition we focus on one in particular: learning from human feedback. Rather than training AI systems using a predefined reward function or using a labeled dataset with a pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.01969","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/2107.01969/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":"2026-07-05T02:55:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qFrm7sV4dEsEXUkb3t87Xxbf1JhGDB5sM4d5ty5SYHicoe/pAoI6bQ4Ae5PWaRO7YcmztDGMSysM/63HJDoCBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:45:34.330342Z"},"content_sha256":"e02dd4cbc9622c7fa280f9fa16f0ce161a98e1bed4919fb69e85793afcee780f","schema_version":"1.0","event_id":"sha256:e02dd4cbc9622c7fa280f9fa16f0ce161a98e1bed4919fb69e85793afcee780f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YFLQ4KBZW2VSUBVMIX2KVUTKI5/bundle.json","state_url":"https://pith.science/pith/YFLQ4KBZW2VSUBVMIX2KVUTKI5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YFLQ4KBZW2VSUBVMIX2KVUTKI5/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":"2026-07-06T18:45:34Z","links":{"resolver":"https://pith.science/pith/YFLQ4KBZW2VSUBVMIX2KVUTKI5","bundle":"https://pith.science/pith/YFLQ4KBZW2VSUBVMIX2KVUTKI5/bundle.json","state":"https://pith.science/pith/YFLQ4KBZW2VSUBVMIX2KVUTKI5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YFLQ4KBZW2VSUBVMIX2KVUTKI5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YFLQ4KBZW2VSUBVMIX2KVUTKI5","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":"f216fb479b5658106f395e546194a0c3a51a6912332444bf58a828a0cc49ce29","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-05T12:18:17Z","title_canon_sha256":"c63ab21470ab855d4ed2851c18a67f0ff43a51ae7e95e7a690ce1744bed953d9"},"schema_version":"1.0","source":{"id":"2107.01969","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.01969","created_at":"2026-07-05T02:55:02Z"},{"alias_kind":"arxiv_version","alias_value":"2107.01969v1","created_at":"2026-07-05T02:55:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.01969","created_at":"2026-07-05T02:55:02Z"},{"alias_kind":"pith_short_12","alias_value":"YFLQ4KBZW2VS","created_at":"2026-07-05T02:55:02Z"},{"alias_kind":"pith_short_16","alias_value":"YFLQ4KBZW2VSUBVM","created_at":"2026-07-05T02:55:02Z"},{"alias_kind":"pith_short_8","alias_value":"YFLQ4KBZ","created_at":"2026-07-05T02:55:02Z"}],"graph_snapshots":[{"event_id":"sha256:e02dd4cbc9622c7fa280f9fa16f0ce161a98e1bed4919fb69e85793afcee780f","target":"graph","created_at":"2026-07-05T02:55:02Z","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/2107.01969/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The last decade has seen a significant increase of interest in deep learning research, with many public successes that have demonstrated its potential. As such, these systems are now being incorporated into commercial products. With this comes an additional challenge: how can we build AI systems that solve tasks where there is not a crisp, well-defined specification? While multiple solutions have been proposed, in this competition we focus on one in particular: learning from human feedback. Rather than training AI systems using a predefined reward function or using a labeled dataset with a pre","authors_text":"Anca Dragan, Anssi Kanervisto, Brandon Houghton, Cody Wild, Neel Alex, Nicholay Topin, Pieter Abbeel, Rohin Shah, Sharada Mohanty, Stephanie Milani, Steven H. Wang, Stuart Russell, William Guss","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-05T12:18:17Z","title":"The MineRL BASALT Competition on Learning from Human Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.01969","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:e1b2134735443e07bb26a92635023af6e5318baa9c25fbd639df99b9806b37f3","target":"record","created_at":"2026-07-05T02:55:02Z","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":"f216fb479b5658106f395e546194a0c3a51a6912332444bf58a828a0cc49ce29","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-05T12:18:17Z","title_canon_sha256":"c63ab21470ab855d4ed2851c18a67f0ff43a51ae7e95e7a690ce1744bed953d9"},"schema_version":"1.0","source":{"id":"2107.01969","kind":"arxiv","version":1}},"canonical_sha256":"c1570e2839b6ab2a06ac45f4aad26a475d7b80ad3b631977fc78536cbcfd3a60","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1570e2839b6ab2a06ac45f4aad26a475d7b80ad3b631977fc78536cbcfd3a60","first_computed_at":"2026-07-05T02:55:02.361925Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:55:02.361925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+iL7LCmnesIDA9mcWfyhekkqhqLZOAQc73E7PTMofhXpfNWMsEcKTZSQwJoVaXvpnUj6bolePhiUqnOg9DHrAg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:55:02.362339Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.01969","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1b2134735443e07bb26a92635023af6e5318baa9c25fbd639df99b9806b37f3","sha256:e02dd4cbc9622c7fa280f9fa16f0ce161a98e1bed4919fb69e85793afcee780f"],"state_sha256":"4baafcbb2bd060a281442b8ab7a3887ab1f6f84880406417b67f5a28f01b9a23"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KeSq3u67httSyenRaOFcMPZUJ8RZ8sGHe38F5vcd6ap52kuoTDyvSVThPhGrDBBFtNA0Wr4AM+ZZkCjSnP9kCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:45:34.332413Z","bundle_sha256":"2caa8ab0463fabea64089cef378fdfebf2a97a132f77f435f8c072b3183806a9"}}