{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:NJUV2E2RPFIHJB47Y6MPWI52SW","short_pith_number":"pith:NJUV2E2R","canonical_record":{"source":{"id":"1805.08882","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-22T21:57:34Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"fb38475509952fd8126b80cf8b403db57df3572edcbb9519b7a307ad99356d90","abstract_canon_sha256":"6c7fe772424b7f72eeec3b1f9add819b72a5e13d7a1451cc49ace42237bd249d"},"schema_version":"1.0"},"canonical_sha256":"6a695d1351795074879fc798fb23ba95b6dc5ae6df53270f1e39cda60a1665fe","source":{"kind":"arxiv","id":"1805.08882","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08882","created_at":"2026-05-18T00:10:44Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08882v2","created_at":"2026-05-18T00:10:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08882","created_at":"2026-05-18T00:10:44Z"},{"alias_kind":"pith_short_12","alias_value":"NJUV2E2RPFIH","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"NJUV2E2RPFIHJB47","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"NJUV2E2R","created_at":"2026-05-18T12:32:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:NJUV2E2RPFIHJB47Y6MPWI52SW","target":"record","payload":{"canonical_record":{"source":{"id":"1805.08882","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-22T21:57:34Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"fb38475509952fd8126b80cf8b403db57df3572edcbb9519b7a307ad99356d90","abstract_canon_sha256":"6c7fe772424b7f72eeec3b1f9add819b72a5e13d7a1451cc49ace42237bd249d"},"schema_version":"1.0"},"canonical_sha256":"6a695d1351795074879fc798fb23ba95b6dc5ae6df53270f1e39cda60a1665fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:44.487767Z","signature_b64":"QsetWtdKa4lc6DvMitVBhrW5gnv8p7xI9lqZ8hNVk9o88kHnJ3pv43B4vIB3xz5vmQhyWxNu1zZW/s5/XnSTBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a695d1351795074879fc798fb23ba95b6dc5ae6df53270f1e39cda60a1665fe","last_reissued_at":"2026-05-18T00:10:44.487158Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:44.487158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.08882","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":"2026-05-18T00:10:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1BatdeepzpYQ6hhTvnDAGRdIgbLU0UFPPG+sSRsxCEk9mXLc25TcEHwAydMXo2Z0eRtbul1yxYz+x44iW/F4DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:51:54.287625Z"},"content_sha256":"84187b05d8b48c95cacfa5849bc95e7bd47f1f1956ca038b4b83d975dc21b090","schema_version":"1.0","event_id":"sha256:84187b05d8b48c95cacfa5849bc95e7bd47f1f1956ca038b4b83d975dc21b090"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:NJUV2E2RPFIHJB47Y6MPWI52SW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-task Maximum Entropy Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Gleave, Oliver Habryka","submitted_at":"2018-05-22T21:57:34Z","abstract_excerpt":"Multi-task Inverse Reinforcement Learning (IRL) is the problem of inferring multiple reward functions from expert demonstrations. Prior work, built on Bayesian IRL, is unable to scale to complex environments due to computational constraints. This paper contributes a formulation of multi-task IRL in the more computationally efficient Maximum Causal Entropy (MCE) IRL framework. Experiments show our approach can perform one-shot imitation learning in a gridworld environment that single-task IRL algorithms need hundreds of demonstrations to solve. We outline preliminary work using meta-learning to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08882","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":""},"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":"2026-05-18T00:10:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WES4P6UTyyTuoeJOB7xziKBFwcZKK60cLu1+4B+WxOti0a4QiPQaLy8iA3qvPQ/FTDVY1kFGvqgdJovqWNbhAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:51:54.288196Z"},"content_sha256":"6cc92f954ed34fbac1b1e6d8e99f166a59351681f33adb8b72d0b1ec271ffb2b","schema_version":"1.0","event_id":"sha256:6cc92f954ed34fbac1b1e6d8e99f166a59351681f33adb8b72d0b1ec271ffb2b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NJUV2E2RPFIHJB47Y6MPWI52SW/bundle.json","state_url":"https://pith.science/pith/NJUV2E2RPFIHJB47Y6MPWI52SW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NJUV2E2RPFIHJB47Y6MPWI52SW/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":"2026-05-27T14:51:54Z","links":{"resolver":"https://pith.science/pith/NJUV2E2RPFIHJB47Y6MPWI52SW","bundle":"https://pith.science/pith/NJUV2E2RPFIHJB47Y6MPWI52SW/bundle.json","state":"https://pith.science/pith/NJUV2E2RPFIHJB47Y6MPWI52SW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NJUV2E2RPFIHJB47Y6MPWI52SW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:NJUV2E2RPFIHJB47Y6MPWI52SW","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":"6c7fe772424b7f72eeec3b1f9add819b72a5e13d7a1451cc49ace42237bd249d","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-22T21:57:34Z","title_canon_sha256":"fb38475509952fd8126b80cf8b403db57df3572edcbb9519b7a307ad99356d90"},"schema_version":"1.0","source":{"id":"1805.08882","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08882","created_at":"2026-05-18T00:10:44Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08882v2","created_at":"2026-05-18T00:10:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08882","created_at":"2026-05-18T00:10:44Z"},{"alias_kind":"pith_short_12","alias_value":"NJUV2E2RPFIH","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"NJUV2E2RPFIHJB47","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"NJUV2E2R","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:6cc92f954ed34fbac1b1e6d8e99f166a59351681f33adb8b72d0b1ec271ffb2b","target":"graph","created_at":"2026-05-18T00:10:44Z","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"},"paper":{"abstract_excerpt":"Multi-task Inverse Reinforcement Learning (IRL) is the problem of inferring multiple reward functions from expert demonstrations. Prior work, built on Bayesian IRL, is unable to scale to complex environments due to computational constraints. This paper contributes a formulation of multi-task IRL in the more computationally efficient Maximum Causal Entropy (MCE) IRL framework. Experiments show our approach can perform one-shot imitation learning in a gridworld environment that single-task IRL algorithms need hundreds of demonstrations to solve. We outline preliminary work using meta-learning to","authors_text":"Adam Gleave, Oliver Habryka","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-22T21:57:34Z","title":"Multi-task Maximum Entropy Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08882","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":"sha256:84187b05d8b48c95cacfa5849bc95e7bd47f1f1956ca038b4b83d975dc21b090","target":"record","created_at":"2026-05-18T00:10:44Z","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":"6c7fe772424b7f72eeec3b1f9add819b72a5e13d7a1451cc49ace42237bd249d","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-22T21:57:34Z","title_canon_sha256":"fb38475509952fd8126b80cf8b403db57df3572edcbb9519b7a307ad99356d90"},"schema_version":"1.0","source":{"id":"1805.08882","kind":"arxiv","version":2}},"canonical_sha256":"6a695d1351795074879fc798fb23ba95b6dc5ae6df53270f1e39cda60a1665fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a695d1351795074879fc798fb23ba95b6dc5ae6df53270f1e39cda60a1665fe","first_computed_at":"2026-05-18T00:10:44.487158Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:10:44.487158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QsetWtdKa4lc6DvMitVBhrW5gnv8p7xI9lqZ8hNVk9o88kHnJ3pv43B4vIB3xz5vmQhyWxNu1zZW/s5/XnSTBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:10:44.487767Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.08882","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84187b05d8b48c95cacfa5849bc95e7bd47f1f1956ca038b4b83d975dc21b090","sha256:6cc92f954ed34fbac1b1e6d8e99f166a59351681f33adb8b72d0b1ec271ffb2b"],"state_sha256":"79418b9c1871f7f916199758e64fbfbc5ba8bb773fc6390c9d5d04db736de70c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bvLWtmU5n1TSFjmYNLkWvWyy/TPGWT/C90LvFvqCWsSbl4xP3De8mXmvTyabdJd8bcPP+ZTmHnH6EQwwJ4h6Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T14:51:54.295017Z","bundle_sha256":"4327a5b816bd86813bebb5027308c40ae096135eaa47952c4628875e09a1f95c"}}