{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:NM5A5WBK7VV2DQI3XYQAJVDA3S","short_pith_number":"pith:NM5A5WBK","canonical_record":{"source":{"id":"2307.12158","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-22T20:05:31Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"50b2c6ffec2f0a7f29ea5f7f3524229f0d2121e90ec6b3b22559e82542e929be","abstract_canon_sha256":"a824f504c3d275cb0ff8d93667f7ac7e519c1aa21b23b721175b6d8aee9d72bf"},"schema_version":"1.0"},"canonical_sha256":"6b3a0ed82afd6ba1c11bbe2004d460dc9d679275073e6ff35f909912034665b9","source":{"kind":"arxiv","id":"2307.12158","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.12158","created_at":"2026-07-05T06:33:50Z"},{"alias_kind":"arxiv_version","alias_value":"2307.12158v1","created_at":"2026-07-05T06:33:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.12158","created_at":"2026-07-05T06:33:50Z"},{"alias_kind":"pith_short_12","alias_value":"NM5A5WBK7VV2","created_at":"2026-07-05T06:33:50Z"},{"alias_kind":"pith_short_16","alias_value":"NM5A5WBK7VV2DQI3","created_at":"2026-07-05T06:33:50Z"},{"alias_kind":"pith_short_8","alias_value":"NM5A5WBK","created_at":"2026-07-05T06:33:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:NM5A5WBK7VV2DQI3XYQAJVDA3S","target":"record","payload":{"canonical_record":{"source":{"id":"2307.12158","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-22T20:05:31Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"50b2c6ffec2f0a7f29ea5f7f3524229f0d2121e90ec6b3b22559e82542e929be","abstract_canon_sha256":"a824f504c3d275cb0ff8d93667f7ac7e519c1aa21b23b721175b6d8aee9d72bf"},"schema_version":"1.0"},"canonical_sha256":"6b3a0ed82afd6ba1c11bbe2004d460dc9d679275073e6ff35f909912034665b9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:33:50.509832Z","signature_b64":"k9xfqEN4LFfiG+kN0BysOXDyvOUpCe9/h9rLlp7cbkLOPlK4Yf1YpxdWe8U5ZeUu8vcQV5CJ4HWjPb7aEJGqCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b3a0ed82afd6ba1c11bbe2004d460dc9d679275073e6ff35f909912034665b9","last_reissued_at":"2026-07-05T06:33:50.509369Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:33:50.509369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.12158","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":"2026-07-05T06:33:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cdOaURunhOaMQp40BwdvENu4mA4R6e0I/2jZx8BEyCsUURV0W/IhFwkvxOTyBlOWrWWbS0ntEhKUzhFcb1I9AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T10:23:28.760086Z"},"content_sha256":"f28bd1eaa0a7a7929ff7163e1b7f1e0e3f1d712f5edb389ea9b4eb14b8f8e5f2","schema_version":"1.0","event_id":"sha256:f28bd1eaa0a7a7929ff7163e1b7f1e0e3f1d712f5edb389ea9b4eb14b8f8e5f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:NM5A5WBK7VV2DQI3XYQAJVDA3S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DIP-RL: Demonstration-Inferred Preference Learning in Minecraft","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.LG","authors_text":"David Watkins, Ellen Novoseller, Josh Miller, Nicholas Waytowich, Vinicius G. Goecks","submitted_at":"2023-07-22T20:05:31Z","abstract_excerpt":"In machine learning for sequential decision-making, an algorithmic agent learns to interact with an environment while receiving feedback in the form of a reward signal. However, in many unstructured real-world settings, such a reward signal is unknown and humans cannot reliably craft a reward signal that correctly captures desired behavior. To solve tasks in such unstructured and open-ended environments, we present Demonstration-Inferred Preference Reinforcement Learning (DIP-RL), an algorithm that leverages human demonstrations in three distinct ways, including training an autoencoder, seedin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.12158","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/2307.12158/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":"2026-07-05T06:33:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zZ6BAj2+4/Xhor8vm9vYNlEaOlcftjl0K0tFqwmyzA5jR031BUsKhO6qWbhmzkI0Nx9QkDtUkq1IRrqx610/DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T10:23:28.760589Z"},"content_sha256":"494c564f66350a53b954bee131e51a42ea80a9517c66273ab8355cba4be09a90","schema_version":"1.0","event_id":"sha256:494c564f66350a53b954bee131e51a42ea80a9517c66273ab8355cba4be09a90"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NM5A5WBK7VV2DQI3XYQAJVDA3S/bundle.json","state_url":"https://pith.science/pith/NM5A5WBK7VV2DQI3XYQAJVDA3S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NM5A5WBK7VV2DQI3XYQAJVDA3S/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":"2026-08-22T10:23:28Z","links":{"resolver":"https://pith.science/pith/NM5A5WBK7VV2DQI3XYQAJVDA3S","bundle":"https://pith.science/pith/NM5A5WBK7VV2DQI3XYQAJVDA3S/bundle.json","state":"https://pith.science/pith/NM5A5WBK7VV2DQI3XYQAJVDA3S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NM5A5WBK7VV2DQI3XYQAJVDA3S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NM5A5WBK7VV2DQI3XYQAJVDA3S","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":"a824f504c3d275cb0ff8d93667f7ac7e519c1aa21b23b721175b6d8aee9d72bf","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-22T20:05:31Z","title_canon_sha256":"50b2c6ffec2f0a7f29ea5f7f3524229f0d2121e90ec6b3b22559e82542e929be"},"schema_version":"1.0","source":{"id":"2307.12158","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.12158","created_at":"2026-07-05T06:33:50Z"},{"alias_kind":"arxiv_version","alias_value":"2307.12158v1","created_at":"2026-07-05T06:33:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.12158","created_at":"2026-07-05T06:33:50Z"},{"alias_kind":"pith_short_12","alias_value":"NM5A5WBK7VV2","created_at":"2026-07-05T06:33:50Z"},{"alias_kind":"pith_short_16","alias_value":"NM5A5WBK7VV2DQI3","created_at":"2026-07-05T06:33:50Z"},{"alias_kind":"pith_short_8","alias_value":"NM5A5WBK","created_at":"2026-07-05T06:33:50Z"}],"graph_snapshots":[{"event_id":"sha256:494c564f66350a53b954bee131e51a42ea80a9517c66273ab8355cba4be09a90","target":"graph","created_at":"2026-07-05T06:33:50Z","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/2307.12158/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In machine learning for sequential decision-making, an algorithmic agent learns to interact with an environment while receiving feedback in the form of a reward signal. However, in many unstructured real-world settings, such a reward signal is unknown and humans cannot reliably craft a reward signal that correctly captures desired behavior. To solve tasks in such unstructured and open-ended environments, we present Demonstration-Inferred Preference Reinforcement Learning (DIP-RL), an algorithm that leverages human demonstrations in three distinct ways, including training an autoencoder, seedin","authors_text":"David Watkins, Ellen Novoseller, Josh Miller, Nicholas Waytowich, Vinicius G. Goecks","cross_cats":["cs.AI","cs.HC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-22T20:05:31Z","title":"DIP-RL: Demonstration-Inferred Preference Learning in Minecraft"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.12158","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:f28bd1eaa0a7a7929ff7163e1b7f1e0e3f1d712f5edb389ea9b4eb14b8f8e5f2","target":"record","created_at":"2026-07-05T06:33:50Z","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":"a824f504c3d275cb0ff8d93667f7ac7e519c1aa21b23b721175b6d8aee9d72bf","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-22T20:05:31Z","title_canon_sha256":"50b2c6ffec2f0a7f29ea5f7f3524229f0d2121e90ec6b3b22559e82542e929be"},"schema_version":"1.0","source":{"id":"2307.12158","kind":"arxiv","version":1}},"canonical_sha256":"6b3a0ed82afd6ba1c11bbe2004d460dc9d679275073e6ff35f909912034665b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b3a0ed82afd6ba1c11bbe2004d460dc9d679275073e6ff35f909912034665b9","first_computed_at":"2026-07-05T06:33:50.509369Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:33:50.509369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k9xfqEN4LFfiG+kN0BysOXDyvOUpCe9/h9rLlp7cbkLOPlK4Yf1YpxdWe8U5ZeUu8vcQV5CJ4HWjPb7aEJGqCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:33:50.509832Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.12158","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f28bd1eaa0a7a7929ff7163e1b7f1e0e3f1d712f5edb389ea9b4eb14b8f8e5f2","sha256:494c564f66350a53b954bee131e51a42ea80a9517c66273ab8355cba4be09a90"],"state_sha256":"80030d34925b0ba24efc75a8494830fb0c2d54f5ae0a57300a4d948cf3ce9545"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4GFbYv37MAqT6cZ0nwB3a0Tg4hbFVc8ezO91QQaPovEcpfBfZVa6J5z2/8UaBEMyTzjpSWFZWfLTrrh1ZQipDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T10:23:28.763923Z","bundle_sha256":"f8379bc5473aab73302539dccd0016efdabbf5a37f5385cc2b30764a6acea3e4"}}