{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GG5N7N3HU7UCARNCC4K7QV2LB4","short_pith_number":"pith:GG5N7N3H","canonical_record":{"source":{"id":"2406.07897","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T06:01:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"aa7fb7bd3bddd325353da04b1ad3b0cfd052e54bf7ed488898a4f2165923732f","abstract_canon_sha256":"438e322c86dfb804ef83e8552e3895bb232fb5bf38ca8960b0b36f2a14f2c767"},"schema_version":"1.0"},"canonical_sha256":"31badfb767a7e82045a21715f8574b0f0ed4ba43d2240f092b60df9e0b862109","source":{"kind":"arxiv","id":"2406.07897","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07897","created_at":"2026-07-05T08:30:40Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07897v1","created_at":"2026-07-05T08:30:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07897","created_at":"2026-07-05T08:30:40Z"},{"alias_kind":"pith_short_12","alias_value":"GG5N7N3HU7UC","created_at":"2026-07-05T08:30:40Z"},{"alias_kind":"pith_short_16","alias_value":"GG5N7N3HU7UCARNC","created_at":"2026-07-05T08:30:40Z"},{"alias_kind":"pith_short_8","alias_value":"GG5N7N3H","created_at":"2026-07-05T08:30:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GG5N7N3HU7UCARNCC4K7QV2LB4","target":"record","payload":{"canonical_record":{"source":{"id":"2406.07897","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T06:01:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"aa7fb7bd3bddd325353da04b1ad3b0cfd052e54bf7ed488898a4f2165923732f","abstract_canon_sha256":"438e322c86dfb804ef83e8552e3895bb232fb5bf38ca8960b0b36f2a14f2c767"},"schema_version":"1.0"},"canonical_sha256":"31badfb767a7e82045a21715f8574b0f0ed4ba43d2240f092b60df9e0b862109","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:40.193753Z","signature_b64":"oagrtjbFOz98NvAMdUd1LIaX64b7Iac3vd+urmZGOlxB86/ugScqjHVpaYSo2H8VOpFeSCrxiRm7ETRC0I2SDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31badfb767a7e82045a21715f8574b0f0ed4ba43d2240f092b60df9e0b862109","last_reissued_at":"2026-07-05T08:30:40.193247Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:40.193247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.07897","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":"2026-07-05T08:30:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i99cl5OWXCgOK30lxRmz8KwrhMMA6IvHy2VO7b0Dd+KJThnarFN5wZIuIpzhaUn/srFHZ1AvxyGjdTb4I+2yBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:39:06.534061Z"},"content_sha256":"b5893c45418d6df69990e78c7f2e71c1b4bafae7363387c189ce47c57901a97d","schema_version":"1.0","event_id":"sha256:b5893c45418d6df69990e78c7f2e71c1b4bafae7363387c189ce47c57901a97d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GG5N7N3HU7UCARNCC4K7QV2LB4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When Do Skills Help Reinforcement Learning? A Theoretical Analysis of Temporal Abstractions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Armando Solar-Lezama, Gabriel Poesia, Zhening Li","submitted_at":"2024-06-12T06:01:42Z","abstract_excerpt":"Skills are temporal abstractions that are intended to improve reinforcement learning (RL) performance through hierarchical RL. Despite our intuition about the properties of an environment that make skills useful, a precise characterization has been absent. We provide the first such characterization, focusing on the utility of deterministic skills in deterministic sparse-reward environments with finite action spaces. We show theoretically and empirically that RL performance gain from skills is worse in environments where solutions to states are less compressible. Additional theoretical results "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07897","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/2406.07897/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":"2026-07-05T08:30:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OvPwgx5S0+gkeIl78qtwRzqWOkW+Hw++tLuaPYRw406rqr1yAF6jkEihDSfdZrdTJ7QEBEFu1S06vaZdVUOjDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:39:06.534449Z"},"content_sha256":"5558b7682780af13a647b4142c84eb7f9aa0b38403fd121f2f6e2cdf7539c12e","schema_version":"1.0","event_id":"sha256:5558b7682780af13a647b4142c84eb7f9aa0b38403fd121f2f6e2cdf7539c12e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GG5N7N3HU7UCARNCC4K7QV2LB4/bundle.json","state_url":"https://pith.science/pith/GG5N7N3HU7UCARNCC4K7QV2LB4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GG5N7N3HU7UCARNCC4K7QV2LB4/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":"2026-07-07T07:39:06Z","links":{"resolver":"https://pith.science/pith/GG5N7N3HU7UCARNCC4K7QV2LB4","bundle":"https://pith.science/pith/GG5N7N3HU7UCARNCC4K7QV2LB4/bundle.json","state":"https://pith.science/pith/GG5N7N3HU7UCARNCC4K7QV2LB4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GG5N7N3HU7UCARNCC4K7QV2LB4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GG5N7N3HU7UCARNCC4K7QV2LB4","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":"438e322c86dfb804ef83e8552e3895bb232fb5bf38ca8960b0b36f2a14f2c767","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T06:01:42Z","title_canon_sha256":"aa7fb7bd3bddd325353da04b1ad3b0cfd052e54bf7ed488898a4f2165923732f"},"schema_version":"1.0","source":{"id":"2406.07897","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07897","created_at":"2026-07-05T08:30:40Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07897v1","created_at":"2026-07-05T08:30:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07897","created_at":"2026-07-05T08:30:40Z"},{"alias_kind":"pith_short_12","alias_value":"GG5N7N3HU7UC","created_at":"2026-07-05T08:30:40Z"},{"alias_kind":"pith_short_16","alias_value":"GG5N7N3HU7UCARNC","created_at":"2026-07-05T08:30:40Z"},{"alias_kind":"pith_short_8","alias_value":"GG5N7N3H","created_at":"2026-07-05T08:30:40Z"}],"graph_snapshots":[{"event_id":"sha256:5558b7682780af13a647b4142c84eb7f9aa0b38403fd121f2f6e2cdf7539c12e","target":"graph","created_at":"2026-07-05T08:30:40Z","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/2406.07897/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Skills are temporal abstractions that are intended to improve reinforcement learning (RL) performance through hierarchical RL. Despite our intuition about the properties of an environment that make skills useful, a precise characterization has been absent. We provide the first such characterization, focusing on the utility of deterministic skills in deterministic sparse-reward environments with finite action spaces. We show theoretically and empirically that RL performance gain from skills is worse in environments where solutions to states are less compressible. Additional theoretical results ","authors_text":"Armando Solar-Lezama, Gabriel Poesia, Zhening Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T06:01:42Z","title":"When Do Skills Help Reinforcement Learning? A Theoretical Analysis of Temporal Abstractions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07897","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:b5893c45418d6df69990e78c7f2e71c1b4bafae7363387c189ce47c57901a97d","target":"record","created_at":"2026-07-05T08:30:40Z","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":"438e322c86dfb804ef83e8552e3895bb232fb5bf38ca8960b0b36f2a14f2c767","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T06:01:42Z","title_canon_sha256":"aa7fb7bd3bddd325353da04b1ad3b0cfd052e54bf7ed488898a4f2165923732f"},"schema_version":"1.0","source":{"id":"2406.07897","kind":"arxiv","version":1}},"canonical_sha256":"31badfb767a7e82045a21715f8574b0f0ed4ba43d2240f092b60df9e0b862109","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31badfb767a7e82045a21715f8574b0f0ed4ba43d2240f092b60df9e0b862109","first_computed_at":"2026-07-05T08:30:40.193247Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:30:40.193247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oagrtjbFOz98NvAMdUd1LIaX64b7Iac3vd+urmZGOlxB86/ugScqjHVpaYSo2H8VOpFeSCrxiRm7ETRC0I2SDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:30:40.193753Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.07897","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5893c45418d6df69990e78c7f2e71c1b4bafae7363387c189ce47c57901a97d","sha256:5558b7682780af13a647b4142c84eb7f9aa0b38403fd121f2f6e2cdf7539c12e"],"state_sha256":"c3d5a1cdf8f71324e48269a36918106712962d415307d1ee0d9f0cfd9e017b9c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MVJmgEGr+bU2voQn6rM1Uq1AVEFsf5a4HzyB22LJGxS0A+cIcUSnkjQ6XnxoP8eQOTCwhBk6z9/gX/Dd5GUXCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:39:06.536858Z","bundle_sha256":"f9939f0a0f15cd73b8036c920046163b11b1be81bbb03693c98308f71914818d"}}