{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:V56ZQ5PWIPMYDUEPKIEYFYEHAW","short_pith_number":"pith:V56ZQ5PW","canonical_record":{"source":{"id":"2506.21039","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T06:35:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"95ec10578d5f6af63c8257d3c4ed09438646c90e0b6319e980615db5a2547e25","abstract_canon_sha256":"fa709003b23e041626a2a5347bd66ee183659c3a16c3537905db781670266398"},"schema_version":"1.0"},"canonical_sha256":"af7d9875f643d981d08f520982e08705a78ee60f1eed2e696ad1da1657befe87","source":{"kind":"arxiv","id":"2506.21039","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21039","created_at":"2026-05-21T01:04:14Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21039v3","created_at":"2026-05-21T01:04:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21039","created_at":"2026-05-21T01:04:14Z"},{"alias_kind":"pith_short_12","alias_value":"V56ZQ5PWIPMY","created_at":"2026-05-21T01:04:14Z"},{"alias_kind":"pith_short_16","alias_value":"V56ZQ5PWIPMYDUEP","created_at":"2026-05-21T01:04:14Z"},{"alias_kind":"pith_short_8","alias_value":"V56ZQ5PW","created_at":"2026-05-21T01:04:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:V56ZQ5PWIPMYDUEPKIEYFYEHAW","target":"record","payload":{"canonical_record":{"source":{"id":"2506.21039","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T06:35:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"95ec10578d5f6af63c8257d3c4ed09438646c90e0b6319e980615db5a2547e25","abstract_canon_sha256":"fa709003b23e041626a2a5347bd66ee183659c3a16c3537905db781670266398"},"schema_version":"1.0"},"canonical_sha256":"af7d9875f643d981d08f520982e08705a78ee60f1eed2e696ad1da1657befe87","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:14.934681Z","signature_b64":"QwSPOzuePE91JdxrlUWkkI7CMz3RpIjZUC28SOxR/Cw/Lf6ZAVir6p66O2zeq9WVIQAVMHGrbrxV0d7KjK/eCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af7d9875f643d981d08f520982e08705a78ee60f1eed2e696ad1da1657befe87","last_reissued_at":"2026-05-21T01:04:14.933769Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:14.933769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.21039","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T01:04:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2D9589iFgImFR+pXXhn5OsRpmFKhD8jYeAbbCSzKZPPRljn5mmviGYzoMpj1xs52H/B2c/u+SCnCZJzUNLa2DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:42:25.693755Z"},"content_sha256":"7e1237dd571d056567ddb65644ad81cdb3dfae76437e1fa07edf76582b867ea3","schema_version":"1.0","event_id":"sha256:7e1237dd571d056567ddb65644ad81cdb3dfae76437e1fa07edf76582b867ea3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:V56ZQ5PWIPMYDUEPKIEYFYEHAW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Strict Subgoal Execution: Reliable Long-Horizon Planning in Hierarchical Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jaebak Hwang, Jeongmo Kim, Sanghyeon Lee, Seungyul Han","submitted_at":"2025-06-26T06:35:42Z","abstract_excerpt":"Long-horizon goal-conditioned tasks pose fundamental challenges for reinforcement learning (RL), particularly when goals are distant and rewards are sparse. While hierarchical and graph-based methods offer partial solutions, their reliance on conventional hindsight relabeling often fails to correct subgoal infeasibility, leading to inefficient high-level planning. To address this, we propose Strict Subgoal Execution (SSE), a graph-based hierarchical RL framework that integrates Frontier Experience Replay (FER) to separate unreachable from admissible subgoals and streamline high-level decision "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21039","kind":"arxiv","version":3},"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/2506.21039/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":"2026-05-21T01:04:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g9lvJpqSh+u41Ai6cA6v3XxAWViIIEyKN8AryQifu0Uqe4/zMhx3TsmTPzrDLPJKle8ovj774tMrFgUHCq3tAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:42:25.694480Z"},"content_sha256":"de7f436c4ef7b4cb3c7003a769d4701fe14c1d1e86f9aafabd3be8ddefca6fe0","schema_version":"1.0","event_id":"sha256:de7f436c4ef7b4cb3c7003a769d4701fe14c1d1e86f9aafabd3be8ddefca6fe0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V56ZQ5PWIPMYDUEPKIEYFYEHAW/bundle.json","state_url":"https://pith.science/pith/V56ZQ5PWIPMYDUEPKIEYFYEHAW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V56ZQ5PWIPMYDUEPKIEYFYEHAW/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":"2026-05-25T19:42:25Z","links":{"resolver":"https://pith.science/pith/V56ZQ5PWIPMYDUEPKIEYFYEHAW","bundle":"https://pith.science/pith/V56ZQ5PWIPMYDUEPKIEYFYEHAW/bundle.json","state":"https://pith.science/pith/V56ZQ5PWIPMYDUEPKIEYFYEHAW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V56ZQ5PWIPMYDUEPKIEYFYEHAW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:V56ZQ5PWIPMYDUEPKIEYFYEHAW","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":"fa709003b23e041626a2a5347bd66ee183659c3a16c3537905db781670266398","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T06:35:42Z","title_canon_sha256":"95ec10578d5f6af63c8257d3c4ed09438646c90e0b6319e980615db5a2547e25"},"schema_version":"1.0","source":{"id":"2506.21039","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21039","created_at":"2026-05-21T01:04:14Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21039v3","created_at":"2026-05-21T01:04:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21039","created_at":"2026-05-21T01:04:14Z"},{"alias_kind":"pith_short_12","alias_value":"V56ZQ5PWIPMY","created_at":"2026-05-21T01:04:14Z"},{"alias_kind":"pith_short_16","alias_value":"V56ZQ5PWIPMYDUEP","created_at":"2026-05-21T01:04:14Z"},{"alias_kind":"pith_short_8","alias_value":"V56ZQ5PW","created_at":"2026-05-21T01:04:14Z"}],"graph_snapshots":[{"event_id":"sha256:de7f436c4ef7b4cb3c7003a769d4701fe14c1d1e86f9aafabd3be8ddefca6fe0","target":"graph","created_at":"2026-05-21T01:04:14Z","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/2506.21039/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long-horizon goal-conditioned tasks pose fundamental challenges for reinforcement learning (RL), particularly when goals are distant and rewards are sparse. While hierarchical and graph-based methods offer partial solutions, their reliance on conventional hindsight relabeling often fails to correct subgoal infeasibility, leading to inefficient high-level planning. To address this, we propose Strict Subgoal Execution (SSE), a graph-based hierarchical RL framework that integrates Frontier Experience Replay (FER) to separate unreachable from admissible subgoals and streamline high-level decision ","authors_text":"Jaebak Hwang, Jeongmo Kim, Sanghyeon Lee, Seungyul Han","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T06:35:42Z","title":"Strict Subgoal Execution: Reliable Long-Horizon Planning in Hierarchical Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21039","kind":"arxiv","version":3},"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":"sha256:7e1237dd571d056567ddb65644ad81cdb3dfae76437e1fa07edf76582b867ea3","target":"record","created_at":"2026-05-21T01:04:14Z","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":"fa709003b23e041626a2a5347bd66ee183659c3a16c3537905db781670266398","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T06:35:42Z","title_canon_sha256":"95ec10578d5f6af63c8257d3c4ed09438646c90e0b6319e980615db5a2547e25"},"schema_version":"1.0","source":{"id":"2506.21039","kind":"arxiv","version":3}},"canonical_sha256":"af7d9875f643d981d08f520982e08705a78ee60f1eed2e696ad1da1657befe87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af7d9875f643d981d08f520982e08705a78ee60f1eed2e696ad1da1657befe87","first_computed_at":"2026-05-21T01:04:14.933769Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:14.933769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QwSPOzuePE91JdxrlUWkkI7CMz3RpIjZUC28SOxR/Cw/Lf6ZAVir6p66O2zeq9WVIQAVMHGrbrxV0d7KjK/eCg==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:14.934681Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.21039","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e1237dd571d056567ddb65644ad81cdb3dfae76437e1fa07edf76582b867ea3","sha256:de7f436c4ef7b4cb3c7003a769d4701fe14c1d1e86f9aafabd3be8ddefca6fe0"],"state_sha256":"8f3314c71c6cf3a05e4e2bb0ca62d2fc3255c74aad5875ed53211104deb0ebac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1TvxRssrLyGx5U8ZBZ6jlKGKtZETn6/QBT3KI8oEGmIHdy0G901HmZ/+6Dh6egxqrsw0rpKMujNHAgPxturrAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T19:42:25.697077Z","bundle_sha256":"14fb733c5a44b5cd72f5068e539d0564ec7a489ea55a202d33eadd67e1fb7881"}}