{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:GZ5OVIGZ6XLIFT2WEVGG4GOMRJ","short_pith_number":"pith:GZ5OVIGZ","canonical_record":{"source":{"id":"2205.15752","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-31T12:39:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"19c5fbd279ea4859527f19b8ddd9aa70f81dab506bc8e839d82ed29abd86e19a","abstract_canon_sha256":"9341db40792dde44db4f9967888319942ab17d24fc1e0657115f1b7f5b5b4b24"},"schema_version":"1.0"},"canonical_sha256":"367aeaa0d9f5d682cf56254c6e19cc8a6d58d079e77ff502187f53cde769daec","source":{"kind":"arxiv","id":"2205.15752","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.15752","created_at":"2026-07-05T06:17:00Z"},{"alias_kind":"arxiv_version","alias_value":"2205.15752v2","created_at":"2026-07-05T06:17:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15752","created_at":"2026-07-05T06:17:00Z"},{"alias_kind":"pith_short_12","alias_value":"GZ5OVIGZ6XLI","created_at":"2026-07-05T06:17:00Z"},{"alias_kind":"pith_short_16","alias_value":"GZ5OVIGZ6XLIFT2W","created_at":"2026-07-05T06:17:00Z"},{"alias_kind":"pith_short_8","alias_value":"GZ5OVIGZ","created_at":"2026-07-05T06:17:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:GZ5OVIGZ6XLIFT2WEVGG4GOMRJ","target":"record","payload":{"canonical_record":{"source":{"id":"2205.15752","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-31T12:39:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"19c5fbd279ea4859527f19b8ddd9aa70f81dab506bc8e839d82ed29abd86e19a","abstract_canon_sha256":"9341db40792dde44db4f9967888319942ab17d24fc1e0657115f1b7f5b5b4b24"},"schema_version":"1.0"},"canonical_sha256":"367aeaa0d9f5d682cf56254c6e19cc8a6d58d079e77ff502187f53cde769daec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:00.332190Z","signature_b64":"GECQWI5hr9EGq7V4bjcyBryULd7CuqlVe5E2vdJGyl8K7IHCbBGg7h9QiLTwQ4q8VWvmezUPCmdChyl2jN8RBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"367aeaa0d9f5d682cf56254c6e19cc8a6d58d079e77ff502187f53cde769daec","last_reissued_at":"2026-07-05T06:17:00.331746Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:00.331746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.15752","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":"2026-07-05T06:17:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eKKYE1BgftyOpSTR4EyI5vP48gCKA8m9CdSzU3JJ6uv94jmm2lTj4JIOgEsa2mOCpPV7OYHglNA+ZR0/jCilBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:44:00.386034Z"},"content_sha256":"cd6b462b92ecc5385955bfbb73e4fdd9b8964ff9cd45eef4016aaa7344466094","schema_version":"1.0","event_id":"sha256:cd6b462b92ecc5385955bfbb73e4fdd9b8964ff9cd45eef4016aaa7344466094"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:GZ5OVIGZ6XLIFT2WEVGG4GOMRJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchies of Reward Machines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alessandra Russo, Anders Jonsson, Daniel Furelos-Blanco, Krysia Broda, Mark Law","submitted_at":"2022-05-31T12:39:24Z","abstract_excerpt":"Reward machines (RMs) are a recent formalism for representing the reward function of a reinforcement learning task through a finite-state machine whose edges encode subgoals of the task using high-level events. The structure of RMs enables the decomposition of a task into simpler and independently solvable subtasks that help tackle long-horizon and/or sparse reward tasks. We propose a formalism for further abstracting the subtask structure by endowing an RM with the ability to call other RMs, thus composing a hierarchy of RMs (HRM). We exploit HRMs by treating each call to an RM as an independ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15752","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/2205.15752/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":"2026-07-05T06:17:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qHq9KOt3hCCKxFgCuVd1LdGCcgIVB5Ndi9PlsnnH/l/khLPSDuyrjil5mhdjSZT6Jcd8sutewfA3iJo4DxZrDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:44:00.386420Z"},"content_sha256":"92d1da2729226b1991052a42e49898d40b6e1501ef86f61ffecaa481826ac102","schema_version":"1.0","event_id":"sha256:92d1da2729226b1991052a42e49898d40b6e1501ef86f61ffecaa481826ac102"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GZ5OVIGZ6XLIFT2WEVGG4GOMRJ/bundle.json","state_url":"https://pith.science/pith/GZ5OVIGZ6XLIFT2WEVGG4GOMRJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GZ5OVIGZ6XLIFT2WEVGG4GOMRJ/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":"2026-07-07T09:44:00Z","links":{"resolver":"https://pith.science/pith/GZ5OVIGZ6XLIFT2WEVGG4GOMRJ","bundle":"https://pith.science/pith/GZ5OVIGZ6XLIFT2WEVGG4GOMRJ/bundle.json","state":"https://pith.science/pith/GZ5OVIGZ6XLIFT2WEVGG4GOMRJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GZ5OVIGZ6XLIFT2WEVGG4GOMRJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GZ5OVIGZ6XLIFT2WEVGG4GOMRJ","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":"9341db40792dde44db4f9967888319942ab17d24fc1e0657115f1b7f5b5b4b24","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-31T12:39:24Z","title_canon_sha256":"19c5fbd279ea4859527f19b8ddd9aa70f81dab506bc8e839d82ed29abd86e19a"},"schema_version":"1.0","source":{"id":"2205.15752","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.15752","created_at":"2026-07-05T06:17:00Z"},{"alias_kind":"arxiv_version","alias_value":"2205.15752v2","created_at":"2026-07-05T06:17:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15752","created_at":"2026-07-05T06:17:00Z"},{"alias_kind":"pith_short_12","alias_value":"GZ5OVIGZ6XLI","created_at":"2026-07-05T06:17:00Z"},{"alias_kind":"pith_short_16","alias_value":"GZ5OVIGZ6XLIFT2W","created_at":"2026-07-05T06:17:00Z"},{"alias_kind":"pith_short_8","alias_value":"GZ5OVIGZ","created_at":"2026-07-05T06:17:00Z"}],"graph_snapshots":[{"event_id":"sha256:92d1da2729226b1991052a42e49898d40b6e1501ef86f61ffecaa481826ac102","target":"graph","created_at":"2026-07-05T06:17:00Z","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/2205.15752/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reward machines (RMs) are a recent formalism for representing the reward function of a reinforcement learning task through a finite-state machine whose edges encode subgoals of the task using high-level events. The structure of RMs enables the decomposition of a task into simpler and independently solvable subtasks that help tackle long-horizon and/or sparse reward tasks. We propose a formalism for further abstracting the subtask structure by endowing an RM with the ability to call other RMs, thus composing a hierarchy of RMs (HRM). We exploit HRMs by treating each call to an RM as an independ","authors_text":"Alessandra Russo, Anders Jonsson, Daniel Furelos-Blanco, Krysia Broda, Mark Law","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-31T12:39:24Z","title":"Hierarchies of Reward Machines"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15752","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:cd6b462b92ecc5385955bfbb73e4fdd9b8964ff9cd45eef4016aaa7344466094","target":"record","created_at":"2026-07-05T06:17:00Z","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":"9341db40792dde44db4f9967888319942ab17d24fc1e0657115f1b7f5b5b4b24","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-31T12:39:24Z","title_canon_sha256":"19c5fbd279ea4859527f19b8ddd9aa70f81dab506bc8e839d82ed29abd86e19a"},"schema_version":"1.0","source":{"id":"2205.15752","kind":"arxiv","version":2}},"canonical_sha256":"367aeaa0d9f5d682cf56254c6e19cc8a6d58d079e77ff502187f53cde769daec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"367aeaa0d9f5d682cf56254c6e19cc8a6d58d079e77ff502187f53cde769daec","first_computed_at":"2026-07-05T06:17:00.331746Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:17:00.331746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GECQWI5hr9EGq7V4bjcyBryULd7CuqlVe5E2vdJGyl8K7IHCbBGg7h9QiLTwQ4q8VWvmezUPCmdChyl2jN8RBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:17:00.332190Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.15752","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd6b462b92ecc5385955bfbb73e4fdd9b8964ff9cd45eef4016aaa7344466094","sha256:92d1da2729226b1991052a42e49898d40b6e1501ef86f61ffecaa481826ac102"],"state_sha256":"87bfde6c0f064e5efc91b2113b3b1cbfffc40c7697a983ae807ed1d710dd9e84"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2WBZtsgam46LZuGEdPuE8Pe2CJe8dkTQwZcTFUamlB0AJh0AitPxrZqkYM9ZK+7jYbRvVUhez46RRpAaPBhJDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T09:44:00.388339Z","bundle_sha256":"944a6164d7b42ad8a8353734143d91fe5082b49199fea65bd5955b9600ff90c2"}}