{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:DEBG4XDZQZPPZKVQLVYK5KFZY6","short_pith_number":"pith:DEBG4XDZ","canonical_record":{"source":{"id":"2210.15670","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-26T18:39:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"14540286a3d3d8fba7d812a1667cbbae3802b68fdc54035393ef28eb15e96240","abstract_canon_sha256":"7b32e9b43cc14f4394b26f0a0909d7d6e3f048e1b4b19f16650818631018d5a9"},"schema_version":"1.0"},"canonical_sha256":"19026e5c79865efcaab05d70aea8b9c7ae6e1503b674f5748c5fa6de4673af2c","source":{"kind":"arxiv","id":"2210.15670","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.15670","created_at":"2026-07-05T05:11:09Z"},{"alias_kind":"arxiv_version","alias_value":"2210.15670v1","created_at":"2026-07-05T05:11:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.15670","created_at":"2026-07-05T05:11:09Z"},{"alias_kind":"pith_short_12","alias_value":"DEBG4XDZQZPP","created_at":"2026-07-05T05:11:09Z"},{"alias_kind":"pith_short_16","alias_value":"DEBG4XDZQZPPZKVQ","created_at":"2026-07-05T05:11:09Z"},{"alias_kind":"pith_short_8","alias_value":"DEBG4XDZ","created_at":"2026-07-05T05:11:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:DEBG4XDZQZPPZKVQLVYK5KFZY6","target":"record","payload":{"canonical_record":{"source":{"id":"2210.15670","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-26T18:39:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"14540286a3d3d8fba7d812a1667cbbae3802b68fdc54035393ef28eb15e96240","abstract_canon_sha256":"7b32e9b43cc14f4394b26f0a0909d7d6e3f048e1b4b19f16650818631018d5a9"},"schema_version":"1.0"},"canonical_sha256":"19026e5c79865efcaab05d70aea8b9c7ae6e1503b674f5748c5fa6de4673af2c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:09.839189Z","signature_b64":"uNQx6Py19kgU7tYK4KBXWQqu3GxFnbkA6nr3Pl27dg6qibls4bi0Rf4B++tEWXz+/JN+30ua3pFz9bK126gTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19026e5c79865efcaab05d70aea8b9c7ae6e1503b674f5748c5fa6de4673af2c","last_reissued_at":"2026-07-05T05:11:09.838732Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:09.838732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.15670","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":"2026-07-05T05:11:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cJAfG8A/C4t4DEBkIoP4OMJubTsr4A7Q76r9pFdDyGMwD5wFc+yIRgD3yS1VB/kwEGDht0qP5c6/jsWyTh9/Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T19:46:58.388538Z"},"content_sha256":"63e72646d3eec1540839d86bc387e981089a12f4a9373f847621fc6c5a23e5c3","schema_version":"1.0","event_id":"sha256:63e72646d3eec1540839d86bc387e981089a12f4a9373f847621fc6c5a23e5c3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:DEBG4XDZQZPPZKVQLVYK5KFZY6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Knowledge-Guided Exploration in Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bing Liu, Jian Li, Lifeng Liu, Sahisnu Mazumder, Shuai Wang, Xiaotian Yin, Yingxuan Zhu","submitted_at":"2022-10-26T18:39:49Z","abstract_excerpt":"This paper proposes a new method to drastically speed up deep reinforcement learning (deep RL) training for problems that have the property of state-action permissibility (SAP). Two types of permissibility are defined under SAP. The first type says that after an action $a_t$ is performed in a state $s_t$ and the agent has reached the new state $s_{t+1}$, the agent can decide whether $a_t$ is permissible or not permissible in $s_t$. The second type says that even without performing $a_t$ in $s_t$, the agent can already decide whether $a_t$ is permissible or not in $s_t$. An action is not permis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.15670","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/2210.15670/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":"2026-07-05T05:11:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KRH1z4HWO+zneIZXkExH400Xw+aB4envaZRo/wVjD9iklu9vJSGEILIP+rU7atHnvA6tu99IxMnhvfihpdrkBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T19:46:58.389111Z"},"content_sha256":"9168c0e2f2ee5b437ce865d514497325521327815d2347a8a703035b209f264b","schema_version":"1.0","event_id":"sha256:9168c0e2f2ee5b437ce865d514497325521327815d2347a8a703035b209f264b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DEBG4XDZQZPPZKVQLVYK5KFZY6/bundle.json","state_url":"https://pith.science/pith/DEBG4XDZQZPPZKVQLVYK5KFZY6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DEBG4XDZQZPPZKVQLVYK5KFZY6/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":"2026-08-20T19:46:58Z","links":{"resolver":"https://pith.science/pith/DEBG4XDZQZPPZKVQLVYK5KFZY6","bundle":"https://pith.science/pith/DEBG4XDZQZPPZKVQLVYK5KFZY6/bundle.json","state":"https://pith.science/pith/DEBG4XDZQZPPZKVQLVYK5KFZY6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DEBG4XDZQZPPZKVQLVYK5KFZY6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DEBG4XDZQZPPZKVQLVYK5KFZY6","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":"7b32e9b43cc14f4394b26f0a0909d7d6e3f048e1b4b19f16650818631018d5a9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-26T18:39:49Z","title_canon_sha256":"14540286a3d3d8fba7d812a1667cbbae3802b68fdc54035393ef28eb15e96240"},"schema_version":"1.0","source":{"id":"2210.15670","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.15670","created_at":"2026-07-05T05:11:09Z"},{"alias_kind":"arxiv_version","alias_value":"2210.15670v1","created_at":"2026-07-05T05:11:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.15670","created_at":"2026-07-05T05:11:09Z"},{"alias_kind":"pith_short_12","alias_value":"DEBG4XDZQZPP","created_at":"2026-07-05T05:11:09Z"},{"alias_kind":"pith_short_16","alias_value":"DEBG4XDZQZPPZKVQ","created_at":"2026-07-05T05:11:09Z"},{"alias_kind":"pith_short_8","alias_value":"DEBG4XDZ","created_at":"2026-07-05T05:11:09Z"}],"graph_snapshots":[{"event_id":"sha256:9168c0e2f2ee5b437ce865d514497325521327815d2347a8a703035b209f264b","target":"graph","created_at":"2026-07-05T05:11:09Z","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/2210.15670/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes a new method to drastically speed up deep reinforcement learning (deep RL) training for problems that have the property of state-action permissibility (SAP). Two types of permissibility are defined under SAP. The first type says that after an action $a_t$ is performed in a state $s_t$ and the agent has reached the new state $s_{t+1}$, the agent can decide whether $a_t$ is permissible or not permissible in $s_t$. The second type says that even without performing $a_t$ in $s_t$, the agent can already decide whether $a_t$ is permissible or not in $s_t$. An action is not permis","authors_text":"Bing Liu, Jian Li, Lifeng Liu, Sahisnu Mazumder, Shuai Wang, Xiaotian Yin, Yingxuan Zhu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-26T18:39:49Z","title":"Knowledge-Guided Exploration in Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.15670","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":"sha256:63e72646d3eec1540839d86bc387e981089a12f4a9373f847621fc6c5a23e5c3","target":"record","created_at":"2026-07-05T05:11:09Z","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":"7b32e9b43cc14f4394b26f0a0909d7d6e3f048e1b4b19f16650818631018d5a9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-26T18:39:49Z","title_canon_sha256":"14540286a3d3d8fba7d812a1667cbbae3802b68fdc54035393ef28eb15e96240"},"schema_version":"1.0","source":{"id":"2210.15670","kind":"arxiv","version":1}},"canonical_sha256":"19026e5c79865efcaab05d70aea8b9c7ae6e1503b674f5748c5fa6de4673af2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19026e5c79865efcaab05d70aea8b9c7ae6e1503b674f5748c5fa6de4673af2c","first_computed_at":"2026-07-05T05:11:09.838732Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:11:09.838732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uNQx6Py19kgU7tYK4KBXWQqu3GxFnbkA6nr3Pl27dg6qibls4bi0Rf4B++tEWXz+/JN+30ua3pFz9bK126gTAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:11:09.839189Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.15670","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63e72646d3eec1540839d86bc387e981089a12f4a9373f847621fc6c5a23e5c3","sha256:9168c0e2f2ee5b437ce865d514497325521327815d2347a8a703035b209f264b"],"state_sha256":"f82bda7c2ec3255f5b533b54e5a307db01149af90b920e8d752694af119963ac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4VqjHHGY0vqfOCb6rRdxI2Eh6hKFC0r0KV9dkW25t60ueFVfZJGpCcpmK/DBQLOVJUK3Rb83zlIygLUGjEDoCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T19:46:58.392103Z","bundle_sha256":"d9ec42f501d66c8d63cc6443a23c1fcc48f73412b8e16531c0929111d1b39081"}}