{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:RO23L3P6X236ZTB33GD3HMQLGR","short_pith_number":"pith:RO23L3P6","canonical_record":{"source":{"id":"2211.10861","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-20T03:55:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"661de9be2906d502345d9969d4c8882ae34717a675331d86c02e9c1c4c62d4e9","abstract_canon_sha256":"38bd9bf4b2909a8cdf30c8fd9c4f596d656d8b468e5671e45d1492db34e716aa"},"schema_version":"1.0"},"canonical_sha256":"8bb5b5edfebeb7eccc3bd987b3b20b347ba94767c691c63b47bd302c09365ea5","source":{"kind":"arxiv","id":"2211.10861","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.10861","created_at":"2026-07-05T05:17:35Z"},{"alias_kind":"arxiv_version","alias_value":"2211.10861v1","created_at":"2026-07-05T05:17:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.10861","created_at":"2026-07-05T05:17:35Z"},{"alias_kind":"pith_short_12","alias_value":"RO23L3P6X236","created_at":"2026-07-05T05:17:35Z"},{"alias_kind":"pith_short_16","alias_value":"RO23L3P6X236ZTB3","created_at":"2026-07-05T05:17:35Z"},{"alias_kind":"pith_short_8","alias_value":"RO23L3P6","created_at":"2026-07-05T05:17:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:RO23L3P6X236ZTB33GD3HMQLGR","target":"record","payload":{"canonical_record":{"source":{"id":"2211.10861","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-20T03:55:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"661de9be2906d502345d9969d4c8882ae34717a675331d86c02e9c1c4c62d4e9","abstract_canon_sha256":"38bd9bf4b2909a8cdf30c8fd9c4f596d656d8b468e5671e45d1492db34e716aa"},"schema_version":"1.0"},"canonical_sha256":"8bb5b5edfebeb7eccc3bd987b3b20b347ba94767c691c63b47bd302c09365ea5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:35.675387Z","signature_b64":"Vurzzs+WLxhe+Bq3RXUQIRgFfLONfuV2f/BYPiaY1fmsUsOpyFUlnQEFXZfuVpcYzE7oxxKp709zfZm7tdt7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bb5b5edfebeb7eccc3bd987b3b20b347ba94767c691c63b47bd302c09365ea5","last_reissued_at":"2026-07-05T05:17:35.674829Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:35.674829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.10861","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":"2026-07-05T05:17:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nuGKR8GgMEEAUdwyIM3dI3A6iZkTw4wAwy92T5EaWeemgL2nqQUloNs3/SvCzeVZ3o470mKbzgDmo5kNEOkHDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:19:33.671101Z"},"content_sha256":"73de68aeeb6edac8c3e9675772e881d11d34c595b9e1c7cf1c4d7482bf99babb","schema_version":"1.0","event_id":"sha256:73de68aeeb6edac8c3e9675772e881d11d34c595b9e1c7cf1c4d7482bf99babb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:RO23L3P6X236ZTB33GD3HMQLGR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Meta Reinforcement Learning for Preference-based Fast Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anji Liu, Jian Peng, Jianzhu Ma, Yitao Liang, Zhizhou Ren","submitted_at":"2022-11-20T03:55:09Z","abstract_excerpt":"Learning new task-specific skills from a few trials is a fundamental challenge for artificial intelligence. Meta reinforcement learning (meta-RL) tackles this problem by learning transferable policies that support few-shot adaptation to unseen tasks. Despite recent advances in meta-RL, most existing methods require the access to the environmental reward function of new tasks to infer the task objective, which is not realistic in many practical applications. To bridge this gap, we study the problem of few-shot adaptation in the context of human-in-the-loop reinforcement learning. We develop a m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.10861","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/2211.10861/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":"2026-07-05T05:17:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IO09eBZ4t4oZf1609UV8CI8sE4SkOEKxC5+its5npwydCrcyVT88BRq+CLB2jzoR56osuw/BAExOwZXKNmMnCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:19:33.671499Z"},"content_sha256":"790a7234da9db815715ed9f64c00cfb25deb9255347be3eba151c10be1637408","schema_version":"1.0","event_id":"sha256:790a7234da9db815715ed9f64c00cfb25deb9255347be3eba151c10be1637408"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RO23L3P6X236ZTB33GD3HMQLGR/bundle.json","state_url":"https://pith.science/pith/RO23L3P6X236ZTB33GD3HMQLGR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RO23L3P6X236ZTB33GD3HMQLGR/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":"2026-07-06T17:19:33Z","links":{"resolver":"https://pith.science/pith/RO23L3P6X236ZTB33GD3HMQLGR","bundle":"https://pith.science/pith/RO23L3P6X236ZTB33GD3HMQLGR/bundle.json","state":"https://pith.science/pith/RO23L3P6X236ZTB33GD3HMQLGR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RO23L3P6X236ZTB33GD3HMQLGR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RO23L3P6X236ZTB33GD3HMQLGR","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":"38bd9bf4b2909a8cdf30c8fd9c4f596d656d8b468e5671e45d1492db34e716aa","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-20T03:55:09Z","title_canon_sha256":"661de9be2906d502345d9969d4c8882ae34717a675331d86c02e9c1c4c62d4e9"},"schema_version":"1.0","source":{"id":"2211.10861","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.10861","created_at":"2026-07-05T05:17:35Z"},{"alias_kind":"arxiv_version","alias_value":"2211.10861v1","created_at":"2026-07-05T05:17:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.10861","created_at":"2026-07-05T05:17:35Z"},{"alias_kind":"pith_short_12","alias_value":"RO23L3P6X236","created_at":"2026-07-05T05:17:35Z"},{"alias_kind":"pith_short_16","alias_value":"RO23L3P6X236ZTB3","created_at":"2026-07-05T05:17:35Z"},{"alias_kind":"pith_short_8","alias_value":"RO23L3P6","created_at":"2026-07-05T05:17:35Z"}],"graph_snapshots":[{"event_id":"sha256:790a7234da9db815715ed9f64c00cfb25deb9255347be3eba151c10be1637408","target":"graph","created_at":"2026-07-05T05:17:35Z","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/2211.10861/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning new task-specific skills from a few trials is a fundamental challenge for artificial intelligence. Meta reinforcement learning (meta-RL) tackles this problem by learning transferable policies that support few-shot adaptation to unseen tasks. Despite recent advances in meta-RL, most existing methods require the access to the environmental reward function of new tasks to infer the task objective, which is not realistic in many practical applications. To bridge this gap, we study the problem of few-shot adaptation in the context of human-in-the-loop reinforcement learning. We develop a m","authors_text":"Anji Liu, Jian Peng, Jianzhu Ma, Yitao Liang, Zhizhou Ren","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-20T03:55:09Z","title":"Efficient Meta Reinforcement Learning for Preference-based Fast Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.10861","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":"sha256:73de68aeeb6edac8c3e9675772e881d11d34c595b9e1c7cf1c4d7482bf99babb","target":"record","created_at":"2026-07-05T05:17:35Z","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":"38bd9bf4b2909a8cdf30c8fd9c4f596d656d8b468e5671e45d1492db34e716aa","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-20T03:55:09Z","title_canon_sha256":"661de9be2906d502345d9969d4c8882ae34717a675331d86c02e9c1c4c62d4e9"},"schema_version":"1.0","source":{"id":"2211.10861","kind":"arxiv","version":1}},"canonical_sha256":"8bb5b5edfebeb7eccc3bd987b3b20b347ba94767c691c63b47bd302c09365ea5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8bb5b5edfebeb7eccc3bd987b3b20b347ba94767c691c63b47bd302c09365ea5","first_computed_at":"2026-07-05T05:17:35.674829Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:17:35.674829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vurzzs+WLxhe+Bq3RXUQIRgFfLONfuV2f/BYPiaY1fmsUsOpyFUlnQEFXZfuVpcYzE7oxxKp709zfZm7tdt7BA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:17:35.675387Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.10861","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73de68aeeb6edac8c3e9675772e881d11d34c595b9e1c7cf1c4d7482bf99babb","sha256:790a7234da9db815715ed9f64c00cfb25deb9255347be3eba151c10be1637408"],"state_sha256":"133cb5468a29ec7ff9a79443845bdb4efc13d9991172dfd018f7b5fdc73697d0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E5cefwQvOcIlzFpOZTj8alxjR6zKEsD/RzAE0QwMWFKIkD9/gWBBKL0xTloYdtkdZkY+RfNSgVxTbke1i82SBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T17:19:33.673525Z","bundle_sha256":"7680644d93df139e40f4e504012256133145eb9df0da1ad115b479378d4c2cfc"}}