{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:OSCPRLIKGZCLEWQQWJKJSY77SN","short_pith_number":"pith:OSCPRLIK","canonical_record":{"source":{"id":"2001.00248","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-01T17:34:00Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"1c9794f046956377b92a59f8ab99882b481f16581711dc83d2eaf7e5628a59f6","abstract_canon_sha256":"1c381c1af2c8cec546cc725e453dfc580f0e27948df103a38da5bb5ddee70cbc"},"schema_version":"1.0"},"canonical_sha256":"7484f8ad0a3644b25a10b2549963ff9359f1ec7d1dd6dd0b3b1dc0336edc5c07","source":{"kind":"arxiv","id":"2001.00248","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.00248","created_at":"2026-07-05T00:54:47Z"},{"alias_kind":"arxiv_version","alias_value":"2001.00248v2","created_at":"2026-07-05T00:54:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.00248","created_at":"2026-07-05T00:54:47Z"},{"alias_kind":"pith_short_12","alias_value":"OSCPRLIKGZCL","created_at":"2026-07-05T00:54:47Z"},{"alias_kind":"pith_short_16","alias_value":"OSCPRLIKGZCLEWQQ","created_at":"2026-07-05T00:54:47Z"},{"alias_kind":"pith_short_8","alias_value":"OSCPRLIK","created_at":"2026-07-05T00:54:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:OSCPRLIKGZCLEWQQWJKJSY77SN","target":"record","payload":{"canonical_record":{"source":{"id":"2001.00248","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-01T17:34:00Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"1c9794f046956377b92a59f8ab99882b481f16581711dc83d2eaf7e5628a59f6","abstract_canon_sha256":"1c381c1af2c8cec546cc725e453dfc580f0e27948df103a38da5bb5ddee70cbc"},"schema_version":"1.0"},"canonical_sha256":"7484f8ad0a3644b25a10b2549963ff9359f1ec7d1dd6dd0b3b1dc0336edc5c07","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:54:47.162042Z","signature_b64":"WQoigPWinB3Err8p6wORM9QRiTJK22F0abY9J5d21fQbc04Ceb2SoP1yHdnOLuVK3+amtskzPNWQWOyrzxfuDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7484f8ad0a3644b25a10b2549963ff9359f1ec7d1dd6dd0b3b1dc0336edc5c07","last_reissued_at":"2026-07-05T00:54:47.161628Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:54:47.161628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2001.00248","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":"2026-07-05T00:54:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ILFcF1XlUHCpqbL4YBWM8LkAyQlT3LkbodkEcS148fpbtwlCAdQ5YE6jr3SmgUh4tttUu0Nr37eqBC3VhJMtAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:18:47.551245Z"},"content_sha256":"63366d4f253003fc87db2855e0600b02850bd6717984cd742809b0fd94c14ee3","schema_version":"1.0","event_id":"sha256:63366d4f253003fc87db2855e0600b02850bd6717984cd742809b0fd94c14ee3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:OSCPRLIKGZCLEWQQWJKJSY77SN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Honglak Lee, Hyunjae Woo, Jongwook Choi, Sungryull Sohn","submitted_at":"2020-01-01T17:34:00Z","abstract_excerpt":"We propose and address a novel few-shot RL problem, where a task is characterized by a subtask graph which describes a set of subtasks and their dependencies that are unknown to the agent. The agent needs to quickly adapt to the task over few episodes during adaptation phase to maximize the return in the test phase. Instead of directly learning a meta-policy, we develop a Meta-learner with Subtask Graph Inference(MSGI), which infers the latent parameter of the task by interacting with the environment and maximizes the return given the latent parameter. To facilitate learning, we adopt an intri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.00248","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2001.00248/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":"2026-07-05T00:54:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vfCfQxbJwBSbuGn/+4iE8sQ4h0IrQfvmnvMdD8K3n9kuphV0OgvHU5cugJKfEpTpESmgpFZf8ZIo9wrafK0vAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:18:47.551647Z"},"content_sha256":"d4ec9708363e98688c5fde8ecc5705b683fba8e341bd3e57fc0335ec54188b31","schema_version":"1.0","event_id":"sha256:d4ec9708363e98688c5fde8ecc5705b683fba8e341bd3e57fc0335ec54188b31"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OSCPRLIKGZCLEWQQWJKJSY77SN/bundle.json","state_url":"https://pith.science/pith/OSCPRLIKGZCLEWQQWJKJSY77SN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OSCPRLIKGZCLEWQQWJKJSY77SN/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":"2026-07-06T17:18:47Z","links":{"resolver":"https://pith.science/pith/OSCPRLIKGZCLEWQQWJKJSY77SN","bundle":"https://pith.science/pith/OSCPRLIKGZCLEWQQWJKJSY77SN/bundle.json","state":"https://pith.science/pith/OSCPRLIKGZCLEWQQWJKJSY77SN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OSCPRLIKGZCLEWQQWJKJSY77SN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:OSCPRLIKGZCLEWQQWJKJSY77SN","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":"1c381c1af2c8cec546cc725e453dfc580f0e27948df103a38da5bb5ddee70cbc","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-01T17:34:00Z","title_canon_sha256":"1c9794f046956377b92a59f8ab99882b481f16581711dc83d2eaf7e5628a59f6"},"schema_version":"1.0","source":{"id":"2001.00248","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.00248","created_at":"2026-07-05T00:54:47Z"},{"alias_kind":"arxiv_version","alias_value":"2001.00248v2","created_at":"2026-07-05T00:54:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.00248","created_at":"2026-07-05T00:54:47Z"},{"alias_kind":"pith_short_12","alias_value":"OSCPRLIKGZCL","created_at":"2026-07-05T00:54:47Z"},{"alias_kind":"pith_short_16","alias_value":"OSCPRLIKGZCLEWQQ","created_at":"2026-07-05T00:54:47Z"},{"alias_kind":"pith_short_8","alias_value":"OSCPRLIK","created_at":"2026-07-05T00:54:47Z"}],"graph_snapshots":[{"event_id":"sha256:d4ec9708363e98688c5fde8ecc5705b683fba8e341bd3e57fc0335ec54188b31","target":"graph","created_at":"2026-07-05T00:54:47Z","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/2001.00248/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose and address a novel few-shot RL problem, where a task is characterized by a subtask graph which describes a set of subtasks and their dependencies that are unknown to the agent. The agent needs to quickly adapt to the task over few episodes during adaptation phase to maximize the return in the test phase. Instead of directly learning a meta-policy, we develop a Meta-learner with Subtask Graph Inference(MSGI), which infers the latent parameter of the task by interacting with the environment and maximizes the return given the latent parameter. To facilitate learning, we adopt an intri","authors_text":"Honglak Lee, Hyunjae Woo, Jongwook Choi, Sungryull Sohn","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-01T17:34:00Z","title":"Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.00248","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":"sha256:63366d4f253003fc87db2855e0600b02850bd6717984cd742809b0fd94c14ee3","target":"record","created_at":"2026-07-05T00:54:47Z","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":"1c381c1af2c8cec546cc725e453dfc580f0e27948df103a38da5bb5ddee70cbc","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-01T17:34:00Z","title_canon_sha256":"1c9794f046956377b92a59f8ab99882b481f16581711dc83d2eaf7e5628a59f6"},"schema_version":"1.0","source":{"id":"2001.00248","kind":"arxiv","version":2}},"canonical_sha256":"7484f8ad0a3644b25a10b2549963ff9359f1ec7d1dd6dd0b3b1dc0336edc5c07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7484f8ad0a3644b25a10b2549963ff9359f1ec7d1dd6dd0b3b1dc0336edc5c07","first_computed_at":"2026-07-05T00:54:47.161628Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:54:47.161628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WQoigPWinB3Err8p6wORM9QRiTJK22F0abY9J5d21fQbc04Ceb2SoP1yHdnOLuVK3+amtskzPNWQWOyrzxfuDA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:54:47.162042Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.00248","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63366d4f253003fc87db2855e0600b02850bd6717984cd742809b0fd94c14ee3","sha256:d4ec9708363e98688c5fde8ecc5705b683fba8e341bd3e57fc0335ec54188b31"],"state_sha256":"54178153a169b32ae9e1130222b1101a10025531a22b6c24d4964fbb8d004802"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CstPerUED7zWop+s0Y7qDg2v1mg3h9bOURAgQCNafjP4AayQ8ALuWgbBivztAnv68FBGNVGCZE49EVrug0drDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T17:18:47.553587Z","bundle_sha256":"59edb2467a08fe2940ce340fa5c4d27ebb1e48ea5f7d5d1effc6f49a410ee973"}}