{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:DIWEEKY4CFOKJUG5RUJDO7OU7F","short_pith_number":"pith:DIWEEKY4","canonical_record":{"source":{"id":"2211.06351","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-11T16:56:02Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"90259bdfd971bba5a29302230eb6a2903306d34fea291ccc4c0f99b9c55e96c5","abstract_canon_sha256":"a24a6fa1c62773aeef4e6c6197451748410650e49d260c01f248f2458e1e9e1d"},"schema_version":"1.0"},"canonical_sha256":"1a2c422b1c115ca4d0dd8d12377dd4f96844166364dd27282de67c7dae19ae47","source":{"kind":"arxiv","id":"2211.06351","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.06351","created_at":"2026-07-05T05:15:20Z"},{"alias_kind":"arxiv_version","alias_value":"2211.06351v1","created_at":"2026-07-05T05:15:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.06351","created_at":"2026-07-05T05:15:20Z"},{"alias_kind":"pith_short_12","alias_value":"DIWEEKY4CFOK","created_at":"2026-07-05T05:15:20Z"},{"alias_kind":"pith_short_16","alias_value":"DIWEEKY4CFOKJUG5","created_at":"2026-07-05T05:15:20Z"},{"alias_kind":"pith_short_8","alias_value":"DIWEEKY4","created_at":"2026-07-05T05:15:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:DIWEEKY4CFOKJUG5RUJDO7OU7F","target":"record","payload":{"canonical_record":{"source":{"id":"2211.06351","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-11T16:56:02Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"90259bdfd971bba5a29302230eb6a2903306d34fea291ccc4c0f99b9c55e96c5","abstract_canon_sha256":"a24a6fa1c62773aeef4e6c6197451748410650e49d260c01f248f2458e1e9e1d"},"schema_version":"1.0"},"canonical_sha256":"1a2c422b1c115ca4d0dd8d12377dd4f96844166364dd27282de67c7dae19ae47","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:20.055805Z","signature_b64":"gnWmbVLVORrTOHY9g6l9260sYj8fyyp1ercxFNJ94UrnFhhjW3ARd2TbcsLQv4NIBWtUSWVfuUR6N/T9LgVjBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a2c422b1c115ca4d0dd8d12377dd4f96844166364dd27282de67c7dae19ae47","last_reissued_at":"2026-07-05T05:15:20.055394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:20.055394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.06351","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":"2026-07-05T05:15:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QSKmePRP9Wml+yrXxpyRhMiP8XoLz9m41h4qO0+ieZsAgb31YoZ88qAETeefcylyHdyajAxn3vpuXDGfJjRWDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T08:15:27.232641Z"},"content_sha256":"8bcbdc1fa760ed08aa32bcb24b1982ed79b3b5f333c60c4c1f9ee9b91cddc264","schema_version":"1.0","event_id":"sha256:8bcbdc1fa760ed08aa32bcb24b1982ed79b3b5f333c60c4c1f9ee9b91cddc264"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:DIWEEKY4CFOKJUG5RUJDO7OU7F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Emergency action termination for immediate reaction in hierarchical reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Artur Grudkowski, Jakub {\\L}yskawa, Mateusz Ostaszewski, Micha{\\l} Bortkiewicz, Pawe{\\l} Wawrzy\\'nski, Tomasz Trzci\\'nski","submitted_at":"2022-11-11T16:56:02Z","abstract_excerpt":"Hierarchical decomposition of control is unavoidable in large dynamical systems. In reinforcement learning (RL), it is usually solved with subgoals defined at higher policy levels and achieved at lower policy levels. Reaching these goals can take a substantial amount of time, during which it is not verified whether they are still worth pursuing. However, due to the randomness of the environment, these goals may become obsolete. In this paper, we address this gap in the state-of-the-art approaches and propose a method in which the validity of higher-level actions (thus lower-level goals) is con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.06351","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/2211.06351/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":"2026-07-05T05:15:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3QAra5sVXY4I2pmHwHSH7gp92kienOAfn9qF38RhZBwEIS2M1WP15v343qehs+NY5BHak+NIp4Gty7C0lvQpCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T08:15:27.233001Z"},"content_sha256":"b07863b180282dcdff4b70abdd3ee39d26ab8e1e778c12ba67aee8d924be9ae9","schema_version":"1.0","event_id":"sha256:b07863b180282dcdff4b70abdd3ee39d26ab8e1e778c12ba67aee8d924be9ae9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DIWEEKY4CFOKJUG5RUJDO7OU7F/bundle.json","state_url":"https://pith.science/pith/DIWEEKY4CFOKJUG5RUJDO7OU7F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DIWEEKY4CFOKJUG5RUJDO7OU7F/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":"2026-07-19T08:15:27Z","links":{"resolver":"https://pith.science/pith/DIWEEKY4CFOKJUG5RUJDO7OU7F","bundle":"https://pith.science/pith/DIWEEKY4CFOKJUG5RUJDO7OU7F/bundle.json","state":"https://pith.science/pith/DIWEEKY4CFOKJUG5RUJDO7OU7F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DIWEEKY4CFOKJUG5RUJDO7OU7F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DIWEEKY4CFOKJUG5RUJDO7OU7F","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":"a24a6fa1c62773aeef4e6c6197451748410650e49d260c01f248f2458e1e9e1d","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-11T16:56:02Z","title_canon_sha256":"90259bdfd971bba5a29302230eb6a2903306d34fea291ccc4c0f99b9c55e96c5"},"schema_version":"1.0","source":{"id":"2211.06351","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.06351","created_at":"2026-07-05T05:15:20Z"},{"alias_kind":"arxiv_version","alias_value":"2211.06351v1","created_at":"2026-07-05T05:15:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.06351","created_at":"2026-07-05T05:15:20Z"},{"alias_kind":"pith_short_12","alias_value":"DIWEEKY4CFOK","created_at":"2026-07-05T05:15:20Z"},{"alias_kind":"pith_short_16","alias_value":"DIWEEKY4CFOKJUG5","created_at":"2026-07-05T05:15:20Z"},{"alias_kind":"pith_short_8","alias_value":"DIWEEKY4","created_at":"2026-07-05T05:15:20Z"}],"graph_snapshots":[{"event_id":"sha256:b07863b180282dcdff4b70abdd3ee39d26ab8e1e778c12ba67aee8d924be9ae9","target":"graph","created_at":"2026-07-05T05:15:20Z","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/2211.06351/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hierarchical decomposition of control is unavoidable in large dynamical systems. In reinforcement learning (RL), it is usually solved with subgoals defined at higher policy levels and achieved at lower policy levels. Reaching these goals can take a substantial amount of time, during which it is not verified whether they are still worth pursuing. However, due to the randomness of the environment, these goals may become obsolete. In this paper, we address this gap in the state-of-the-art approaches and propose a method in which the validity of higher-level actions (thus lower-level goals) is con","authors_text":"Artur Grudkowski, Jakub {\\L}yskawa, Mateusz Ostaszewski, Micha{\\l} Bortkiewicz, Pawe{\\l} Wawrzy\\'nski, Tomasz Trzci\\'nski","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-11T16:56:02Z","title":"Emergency action termination for immediate reaction in hierarchical reinforcement learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.06351","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":"sha256:8bcbdc1fa760ed08aa32bcb24b1982ed79b3b5f333c60c4c1f9ee9b91cddc264","target":"record","created_at":"2026-07-05T05:15:20Z","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":"a24a6fa1c62773aeef4e6c6197451748410650e49d260c01f248f2458e1e9e1d","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-11T16:56:02Z","title_canon_sha256":"90259bdfd971bba5a29302230eb6a2903306d34fea291ccc4c0f99b9c55e96c5"},"schema_version":"1.0","source":{"id":"2211.06351","kind":"arxiv","version":1}},"canonical_sha256":"1a2c422b1c115ca4d0dd8d12377dd4f96844166364dd27282de67c7dae19ae47","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a2c422b1c115ca4d0dd8d12377dd4f96844166364dd27282de67c7dae19ae47","first_computed_at":"2026-07-05T05:15:20.055394Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:15:20.055394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gnWmbVLVORrTOHY9g6l9260sYj8fyyp1ercxFNJ94UrnFhhjW3ARd2TbcsLQv4NIBWtUSWVfuUR6N/T9LgVjBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:15:20.055805Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.06351","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8bcbdc1fa760ed08aa32bcb24b1982ed79b3b5f333c60c4c1f9ee9b91cddc264","sha256:b07863b180282dcdff4b70abdd3ee39d26ab8e1e778c12ba67aee8d924be9ae9"],"state_sha256":"3d009713db5c5d4b22ae9bc1b802e0d9d3c7478df04f16664863760407a77546"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9WO9ZmRPgwu6tmsAsY5O9UFAoEKRtRts2roPWIyrO/yd/RYp9oenOaGq542V5tsdEEsnX+ru+K3v/HfIynleDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-19T08:15:27.235622Z","bundle_sha256":"8df8bcf25e9a208e64d0a9804a0aa70a676a7c887e304d88069d708ff3990c0d"}}