{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PPLPO3FVZSTXRDBHGOYKC3AZIM","short_pith_number":"pith:PPLPO3FV","canonical_record":{"source":{"id":"2301.12950","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-30T14:50:46Z","cross_cats_sorted":["cs.AI","cs.PL","cs.RO"],"title_canon_sha256":"336876313af62c570f10e153b823e4572c2d170742f35dfeed5c2c21dfa62b69","abstract_canon_sha256":"8f6a10d32603cade028f2953c928469878a5df93f3fd8099aa72c701cfca73a9"},"schema_version":"1.0"},"canonical_sha256":"7bd6f76cb5cca7788c2733b0a16c19432032125f82215105297cc10168124876","source":{"kind":"arxiv","id":"2301.12950","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.12950","created_at":"2026-07-05T06:15:45Z"},{"alias_kind":"arxiv_version","alias_value":"2301.12950v2","created_at":"2026-07-05T06:15:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12950","created_at":"2026-07-05T06:15:45Z"},{"alias_kind":"pith_short_12","alias_value":"PPLPO3FVZSTX","created_at":"2026-07-05T06:15:45Z"},{"alias_kind":"pith_short_16","alias_value":"PPLPO3FVZSTXRDBH","created_at":"2026-07-05T06:15:45Z"},{"alias_kind":"pith_short_8","alias_value":"PPLPO3FV","created_at":"2026-07-05T06:15:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PPLPO3FVZSTXRDBHGOYKC3AZIM","target":"record","payload":{"canonical_record":{"source":{"id":"2301.12950","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-30T14:50:46Z","cross_cats_sorted":["cs.AI","cs.PL","cs.RO"],"title_canon_sha256":"336876313af62c570f10e153b823e4572c2d170742f35dfeed5c2c21dfa62b69","abstract_canon_sha256":"8f6a10d32603cade028f2953c928469878a5df93f3fd8099aa72c701cfca73a9"},"schema_version":"1.0"},"canonical_sha256":"7bd6f76cb5cca7788c2733b0a16c19432032125f82215105297cc10168124876","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:45.211639Z","signature_b64":"VJ/lcQB5Lt8QqHDDIVTC9piphyrBr4J/0WH3ToS9XY8+keN/hL5/RjEoFSwzp+05MgnWSLNjZboKw6EOcEUgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bd6f76cb5cca7788c2733b0a16c19432032125f82215105297cc10168124876","last_reissued_at":"2026-07-05T06:15:45.211066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:45.211066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.12950","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":"2026-07-05T06:15:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rqmW/J+/rXem5BfKGJgF90ahH8jC4BjRt6AlaoOXv/KHBPzAz2smdG4ty0/x8tGLPJKnQmXHnprxPyFMqFUjDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T02:06:55.228664Z"},"content_sha256":"40ea5db3c97e56fd47ea4de8377668ebfedd330d78548edf01decc836726923f","schema_version":"1.0","event_id":"sha256:40ea5db3c97e56fd47ea4de8377668ebfedd330d78548edf01decc836726923f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PPLPO3FVZSTXRDBHGOYKC3AZIM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.PL","cs.RO"],"primary_cat":"cs.LG","authors_text":"En-Pei Hu, Guan-Ting Liu, Hung-yi Lee, Pu-Jen Cheng, Shao-Hua Sun","submitted_at":"2023-01-30T14:50:46Z","abstract_excerpt":"Aiming to produce reinforcement learning (RL) policies that are human-interpretable and can generalize better to novel scenarios, Trivedi et al. (2021) present a method (LEAPS) that first learns a program embedding space to continuously parameterize diverse programs from a pre-generated program dataset, and then searches for a task-solving program in the learned program embedding space when given a task. Despite the encouraging results, the program policies that LEAPS can produce are limited by the distribution of the program dataset. Furthermore, during searching, LEAPS evaluates each candida"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12950","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/2301.12950/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":"2026-07-05T06:15:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ezcgcpxdJQpmBcoxYV9IQUdyv982rxZEKYaeh0DmeXmqfZBKH1eOAHcLKNcWgdOVkmnMSZac722H+xzAY55SBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T02:06:55.229324Z"},"content_sha256":"3b72d13b2ec0bc062b4709bfbd58c50e3ccb6edfe148e915ec62eca7dea4c11b","schema_version":"1.0","event_id":"sha256:3b72d13b2ec0bc062b4709bfbd58c50e3ccb6edfe148e915ec62eca7dea4c11b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PPLPO3FVZSTXRDBHGOYKC3AZIM/bundle.json","state_url":"https://pith.science/pith/PPLPO3FVZSTXRDBHGOYKC3AZIM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PPLPO3FVZSTXRDBHGOYKC3AZIM/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":"2026-08-15T02:06:55Z","links":{"resolver":"https://pith.science/pith/PPLPO3FVZSTXRDBHGOYKC3AZIM","bundle":"https://pith.science/pith/PPLPO3FVZSTXRDBHGOYKC3AZIM/bundle.json","state":"https://pith.science/pith/PPLPO3FVZSTXRDBHGOYKC3AZIM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PPLPO3FVZSTXRDBHGOYKC3AZIM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PPLPO3FVZSTXRDBHGOYKC3AZIM","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":"8f6a10d32603cade028f2953c928469878a5df93f3fd8099aa72c701cfca73a9","cross_cats_sorted":["cs.AI","cs.PL","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-30T14:50:46Z","title_canon_sha256":"336876313af62c570f10e153b823e4572c2d170742f35dfeed5c2c21dfa62b69"},"schema_version":"1.0","source":{"id":"2301.12950","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.12950","created_at":"2026-07-05T06:15:45Z"},{"alias_kind":"arxiv_version","alias_value":"2301.12950v2","created_at":"2026-07-05T06:15:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12950","created_at":"2026-07-05T06:15:45Z"},{"alias_kind":"pith_short_12","alias_value":"PPLPO3FVZSTX","created_at":"2026-07-05T06:15:45Z"},{"alias_kind":"pith_short_16","alias_value":"PPLPO3FVZSTXRDBH","created_at":"2026-07-05T06:15:45Z"},{"alias_kind":"pith_short_8","alias_value":"PPLPO3FV","created_at":"2026-07-05T06:15:45Z"}],"graph_snapshots":[{"event_id":"sha256:3b72d13b2ec0bc062b4709bfbd58c50e3ccb6edfe148e915ec62eca7dea4c11b","target":"graph","created_at":"2026-07-05T06:15:45Z","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/2301.12950/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aiming to produce reinforcement learning (RL) policies that are human-interpretable and can generalize better to novel scenarios, Trivedi et al. (2021) present a method (LEAPS) that first learns a program embedding space to continuously parameterize diverse programs from a pre-generated program dataset, and then searches for a task-solving program in the learned program embedding space when given a task. Despite the encouraging results, the program policies that LEAPS can produce are limited by the distribution of the program dataset. Furthermore, during searching, LEAPS evaluates each candida","authors_text":"En-Pei Hu, Guan-Ting Liu, Hung-yi Lee, Pu-Jen Cheng, Shao-Hua Sun","cross_cats":["cs.AI","cs.PL","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-30T14:50:46Z","title":"Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12950","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":"sha256:40ea5db3c97e56fd47ea4de8377668ebfedd330d78548edf01decc836726923f","target":"record","created_at":"2026-07-05T06:15:45Z","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":"8f6a10d32603cade028f2953c928469878a5df93f3fd8099aa72c701cfca73a9","cross_cats_sorted":["cs.AI","cs.PL","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-30T14:50:46Z","title_canon_sha256":"336876313af62c570f10e153b823e4572c2d170742f35dfeed5c2c21dfa62b69"},"schema_version":"1.0","source":{"id":"2301.12950","kind":"arxiv","version":2}},"canonical_sha256":"7bd6f76cb5cca7788c2733b0a16c19432032125f82215105297cc10168124876","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7bd6f76cb5cca7788c2733b0a16c19432032125f82215105297cc10168124876","first_computed_at":"2026-07-05T06:15:45.211066Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:15:45.211066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VJ/lcQB5Lt8QqHDDIVTC9piphyrBr4J/0WH3ToS9XY8+keN/hL5/RjEoFSwzp+05MgnWSLNjZboKw6EOcEUgCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:15:45.211639Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.12950","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40ea5db3c97e56fd47ea4de8377668ebfedd330d78548edf01decc836726923f","sha256:3b72d13b2ec0bc062b4709bfbd58c50e3ccb6edfe148e915ec62eca7dea4c11b"],"state_sha256":"e74363d4c63939f24ce5dec68e9bdfeec2fc537055187d4e67f027ddd3cf21bf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kcx7gZbuXFjodab8yacrzvIEqP8O7eFUckayFNit55QaS5acX6Doc5re95oHkP0sdByzpZJlex5dGZflLzfNCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T02:06:55.234880Z","bundle_sha256":"9d84c234476df139cff351075bcc89d67f419988438189531091f65b506d8121"}}