{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Z6SHNSPDKGBQKNZZ23QV2AGDOR","short_pith_number":"pith:Z6SHNSPD","canonical_record":{"source":{"id":"2506.02050","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-01T06:36:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fbe7a3951a97b7f35193442292d118c7357513cab647d79ebf21107c0cbcfec7","abstract_canon_sha256":"bfe4012fc0e3c0983cdae9d9ef45c5603641b2142711f671100f40ea914fbcfa"},"schema_version":"1.0"},"canonical_sha256":"cfa476c9e35183053739d6e15d00c37452a3835e270a162dccdd0ca1d59d3ae7","source":{"kind":"arxiv","id":"2506.02050","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02050","created_at":"2026-07-05T11:14:31Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02050v1","created_at":"2026-07-05T11:14:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02050","created_at":"2026-07-05T11:14:31Z"},{"alias_kind":"pith_short_12","alias_value":"Z6SHNSPDKGBQ","created_at":"2026-07-05T11:14:31Z"},{"alias_kind":"pith_short_16","alias_value":"Z6SHNSPDKGBQKNZZ","created_at":"2026-07-05T11:14:31Z"},{"alias_kind":"pith_short_8","alias_value":"Z6SHNSPD","created_at":"2026-07-05T11:14:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Z6SHNSPDKGBQKNZZ23QV2AGDOR","target":"record","payload":{"canonical_record":{"source":{"id":"2506.02050","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-01T06:36:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fbe7a3951a97b7f35193442292d118c7357513cab647d79ebf21107c0cbcfec7","abstract_canon_sha256":"bfe4012fc0e3c0983cdae9d9ef45c5603641b2142711f671100f40ea914fbcfa"},"schema_version":"1.0"},"canonical_sha256":"cfa476c9e35183053739d6e15d00c37452a3835e270a162dccdd0ca1d59d3ae7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:31.442355Z","signature_b64":"JROEBr4AzHrFAlF6H1QTZxJ1wrA+lw+FCoSrRXgdrhIacrOZath+N0K3CU6TQta+3h7QWjRxcbSHQVc3RFhLDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfa476c9e35183053739d6e15d00c37452a3835e270a162dccdd0ca1d59d3ae7","last_reissued_at":"2026-07-05T11:14:31.441930Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:31.441930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.02050","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":"2026-07-05T11:14:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7m2gVnrF/EeqNZ/nnR9GOqpLkACvcy8upbPbC9CZdMPGtaZoAw9tqnawyqbY9039Dre8TYdFIlG4KLR0WBzOCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T01:27:07.644276Z"},"content_sha256":"f6278b627f33b0bb180b39999a3884725ea0c19d9ca489172241e6bcf69b9a20","schema_version":"1.0","event_id":"sha256:f6278b627f33b0bb180b39999a3884725ea0c19d9ca489172241e6bcf69b9a20"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Z6SHNSPDKGBQKNZZ23QV2AGDOR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Decoupled Hierarchical Reinforcement Learning with State Abstraction for Discrete Grids","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Qingyu Xiao, Youtian Du, Yuanlin Chang","submitted_at":"2025-06-01T06:36:19Z","abstract_excerpt":"Effective agent exploration remains a core challenge in reinforcement learning (RL) for complex discrete state-space environments, particularly under partial observability. This paper presents a decoupled hierarchical RL framework integrating state abstraction (DcHRL-SA) to address this issue. The proposed method employs a dual-level architecture, consisting of a high level RL-based actor and a low-level rule-based policy, to promote effective exploration. Additionally, state abstraction method is incorporated to cluster discrete states, effectively lowering state dimensionality. Experiments c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02050","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/2506.02050/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":"2026-07-05T11:14:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lIkoHnEu5JFIkRqF6gwpXzn9TWRhIIX0EVmIz/L+9HO+txbQBV1lI2s8CUs7TZ3sNkgEINd3NuKvwsFz8b79CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T01:27:07.644779Z"},"content_sha256":"4f068581c074f1d56175f1ed6b2b2a9783d7ac6b0585ef56a057b9395d6798b4","schema_version":"1.0","event_id":"sha256:4f068581c074f1d56175f1ed6b2b2a9783d7ac6b0585ef56a057b9395d6798b4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z6SHNSPDKGBQKNZZ23QV2AGDOR/bundle.json","state_url":"https://pith.science/pith/Z6SHNSPDKGBQKNZZ23QV2AGDOR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z6SHNSPDKGBQKNZZ23QV2AGDOR/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":"2026-08-22T01:27:07Z","links":{"resolver":"https://pith.science/pith/Z6SHNSPDKGBQKNZZ23QV2AGDOR","bundle":"https://pith.science/pith/Z6SHNSPDKGBQKNZZ23QV2AGDOR/bundle.json","state":"https://pith.science/pith/Z6SHNSPDKGBQKNZZ23QV2AGDOR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z6SHNSPDKGBQKNZZ23QV2AGDOR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Z6SHNSPDKGBQKNZZ23QV2AGDOR","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":"bfe4012fc0e3c0983cdae9d9ef45c5603641b2142711f671100f40ea914fbcfa","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-01T06:36:19Z","title_canon_sha256":"fbe7a3951a97b7f35193442292d118c7357513cab647d79ebf21107c0cbcfec7"},"schema_version":"1.0","source":{"id":"2506.02050","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02050","created_at":"2026-07-05T11:14:31Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02050v1","created_at":"2026-07-05T11:14:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02050","created_at":"2026-07-05T11:14:31Z"},{"alias_kind":"pith_short_12","alias_value":"Z6SHNSPDKGBQ","created_at":"2026-07-05T11:14:31Z"},{"alias_kind":"pith_short_16","alias_value":"Z6SHNSPDKGBQKNZZ","created_at":"2026-07-05T11:14:31Z"},{"alias_kind":"pith_short_8","alias_value":"Z6SHNSPD","created_at":"2026-07-05T11:14:31Z"}],"graph_snapshots":[{"event_id":"sha256:4f068581c074f1d56175f1ed6b2b2a9783d7ac6b0585ef56a057b9395d6798b4","target":"graph","created_at":"2026-07-05T11:14:31Z","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/2506.02050/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Effective agent exploration remains a core challenge in reinforcement learning (RL) for complex discrete state-space environments, particularly under partial observability. This paper presents a decoupled hierarchical RL framework integrating state abstraction (DcHRL-SA) to address this issue. The proposed method employs a dual-level architecture, consisting of a high level RL-based actor and a low-level rule-based policy, to promote effective exploration. Additionally, state abstraction method is incorporated to cluster discrete states, effectively lowering state dimensionality. Experiments c","authors_text":"Qingyu Xiao, Youtian Du, Yuanlin Chang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-01T06:36:19Z","title":"Decoupled Hierarchical Reinforcement Learning with State Abstraction for Discrete Grids"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02050","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:f6278b627f33b0bb180b39999a3884725ea0c19d9ca489172241e6bcf69b9a20","target":"record","created_at":"2026-07-05T11:14:31Z","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":"bfe4012fc0e3c0983cdae9d9ef45c5603641b2142711f671100f40ea914fbcfa","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-01T06:36:19Z","title_canon_sha256":"fbe7a3951a97b7f35193442292d118c7357513cab647d79ebf21107c0cbcfec7"},"schema_version":"1.0","source":{"id":"2506.02050","kind":"arxiv","version":1}},"canonical_sha256":"cfa476c9e35183053739d6e15d00c37452a3835e270a162dccdd0ca1d59d3ae7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cfa476c9e35183053739d6e15d00c37452a3835e270a162dccdd0ca1d59d3ae7","first_computed_at":"2026-07-05T11:14:31.441930Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:31.441930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JROEBr4AzHrFAlF6H1QTZxJ1wrA+lw+FCoSrRXgdrhIacrOZath+N0K3CU6TQta+3h7QWjRxcbSHQVc3RFhLDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:31.442355Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02050","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6278b627f33b0bb180b39999a3884725ea0c19d9ca489172241e6bcf69b9a20","sha256:4f068581c074f1d56175f1ed6b2b2a9783d7ac6b0585ef56a057b9395d6798b4"],"state_sha256":"af85b3e1d2612898e2881d123b07ef5f69f89f15f58b0386455b426fd9676c21"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QfZGDfk7yjVeuoDfaiWz1bcQPSNSrfsCKttngPgA6btzfrSX0kQ4nlXv+sYK7r2B2ynILsNr335notxcQ+6mBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T01:27:07.652608Z","bundle_sha256":"5b0a6b970eb55d39cfd339bd1e3b8daa1ada0640a602c6d87c7be40cddb60071"}}