{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Q4BITHB6VN6ZJURZTKGROYPMNN","short_pith_number":"pith:Q4BITHB6","canonical_record":{"source":{"id":"2412.12700","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-17T09:16:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cd31b8ba8e0773d0e5fc9ae337f3ed2c7b69033533543747a0249cb5691cab7a","abstract_canon_sha256":"99d25c42793650b5d09b7c81213093afeef16ab2cb77de82d67d8d7500ec9ebd"},"schema_version":"1.0"},"canonical_sha256":"8702899c3eab7d94d2399a8d1761ec6b61795030d59e9c9fe75f9ab30f0e05f9","source":{"kind":"arxiv","id":"2412.12700","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12700","created_at":"2026-07-05T09:50:19Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12700v1","created_at":"2026-07-05T09:50:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12700","created_at":"2026-07-05T09:50:19Z"},{"alias_kind":"pith_short_12","alias_value":"Q4BITHB6VN6Z","created_at":"2026-07-05T09:50:19Z"},{"alias_kind":"pith_short_16","alias_value":"Q4BITHB6VN6ZJURZ","created_at":"2026-07-05T09:50:19Z"},{"alias_kind":"pith_short_8","alias_value":"Q4BITHB6","created_at":"2026-07-05T09:50:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Q4BITHB6VN6ZJURZTKGROYPMNN","target":"record","payload":{"canonical_record":{"source":{"id":"2412.12700","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-17T09:16:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cd31b8ba8e0773d0e5fc9ae337f3ed2c7b69033533543747a0249cb5691cab7a","abstract_canon_sha256":"99d25c42793650b5d09b7c81213093afeef16ab2cb77de82d67d8d7500ec9ebd"},"schema_version":"1.0"},"canonical_sha256":"8702899c3eab7d94d2399a8d1761ec6b61795030d59e9c9fe75f9ab30f0e05f9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:19.400034Z","signature_b64":"OM4vlaNkldwkZHmHjcJYMbCsnIPBY0owbyTqRIJnrPm81/us+z3jyegHbCvqs9qlyUILZ2U+AkeMeNCuKt8BDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8702899c3eab7d94d2399a8d1761ec6b61795030d59e9c9fe75f9ab30f0e05f9","last_reissued_at":"2026-07-05T09:50:19.399631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:19.399631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.12700","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":"2026-07-05T09:50:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CBkVx3PoIkVpHJ9YveAUH1bUZSI6xw6WKLpbTuMMV/8Xo/Jj6i8m9UI3ezkE+NNb2Q3Dk/SHSU2KAb/mKGRVDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T21:47:09.530194Z"},"content_sha256":"f4514e70d2f44ee60804087c8b3a4b5b6187a021062e509d409133f035706e6c","schema_version":"1.0","event_id":"sha256:f4514e70d2f44ee60804087c8b3a4b5b6187a021062e509d409133f035706e6c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Q4BITHB6VN6ZJURZTKGROYPMNN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ParMod: A Parallel and Modular Framework for Learning Non-Markovian Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bin Yu, Cong Tian, Ruixuan Miao, Xu Lu, Zhenhua Duan","submitted_at":"2024-12-17T09:16:53Z","abstract_excerpt":"The commonly used Reinforcement Learning (RL) model, MDPs (Markov Decision Processes), has a basic premise that rewards depend on the current state and action only. However, many real-world tasks are non-Markovian, which has long-term memory and dependency. The reward sparseness problem is further amplified in non-Markovian scenarios. Hence learning a non-Markovian task (NMT) is inherently more difficult than learning a Markovian one. In this paper, we propose a novel \\textbf{Par}allel and \\textbf{Mod}ular RL framework, ParMod, specifically for learning NMTs specified by temporal logic. With t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12700","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/2412.12700/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":"2026-07-05T09:50:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y6z0U4pXJgyjzYgF2QcuEeuTUK0ZH4WQThPXd8cqa4qJ4fyW5ukEqfnh4KIBVJru+08sJF/RkGLOIr7OprJyDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T21:47:09.530744Z"},"content_sha256":"fd2bc708215bff2cdda7df6f148f381d421c2c82acac50904535fffe6f436b05","schema_version":"1.0","event_id":"sha256:fd2bc708215bff2cdda7df6f148f381d421c2c82acac50904535fffe6f436b05"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q4BITHB6VN6ZJURZTKGROYPMNN/bundle.json","state_url":"https://pith.science/pith/Q4BITHB6VN6ZJURZTKGROYPMNN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q4BITHB6VN6ZJURZTKGROYPMNN/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":"2026-08-21T21:47:09Z","links":{"resolver":"https://pith.science/pith/Q4BITHB6VN6ZJURZTKGROYPMNN","bundle":"https://pith.science/pith/Q4BITHB6VN6ZJURZTKGROYPMNN/bundle.json","state":"https://pith.science/pith/Q4BITHB6VN6ZJURZTKGROYPMNN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q4BITHB6VN6ZJURZTKGROYPMNN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q4BITHB6VN6ZJURZTKGROYPMNN","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":"99d25c42793650b5d09b7c81213093afeef16ab2cb77de82d67d8d7500ec9ebd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-17T09:16:53Z","title_canon_sha256":"cd31b8ba8e0773d0e5fc9ae337f3ed2c7b69033533543747a0249cb5691cab7a"},"schema_version":"1.0","source":{"id":"2412.12700","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12700","created_at":"2026-07-05T09:50:19Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12700v1","created_at":"2026-07-05T09:50:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12700","created_at":"2026-07-05T09:50:19Z"},{"alias_kind":"pith_short_12","alias_value":"Q4BITHB6VN6Z","created_at":"2026-07-05T09:50:19Z"},{"alias_kind":"pith_short_16","alias_value":"Q4BITHB6VN6ZJURZ","created_at":"2026-07-05T09:50:19Z"},{"alias_kind":"pith_short_8","alias_value":"Q4BITHB6","created_at":"2026-07-05T09:50:19Z"}],"graph_snapshots":[{"event_id":"sha256:fd2bc708215bff2cdda7df6f148f381d421c2c82acac50904535fffe6f436b05","target":"graph","created_at":"2026-07-05T09:50:19Z","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/2412.12700/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The commonly used Reinforcement Learning (RL) model, MDPs (Markov Decision Processes), has a basic premise that rewards depend on the current state and action only. However, many real-world tasks are non-Markovian, which has long-term memory and dependency. The reward sparseness problem is further amplified in non-Markovian scenarios. Hence learning a non-Markovian task (NMT) is inherently more difficult than learning a Markovian one. In this paper, we propose a novel \\textbf{Par}allel and \\textbf{Mod}ular RL framework, ParMod, specifically for learning NMTs specified by temporal logic. With t","authors_text":"Bin Yu, Cong Tian, Ruixuan Miao, Xu Lu, Zhenhua Duan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-17T09:16:53Z","title":"ParMod: A Parallel and Modular Framework for Learning Non-Markovian Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12700","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:f4514e70d2f44ee60804087c8b3a4b5b6187a021062e509d409133f035706e6c","target":"record","created_at":"2026-07-05T09:50:19Z","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":"99d25c42793650b5d09b7c81213093afeef16ab2cb77de82d67d8d7500ec9ebd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-17T09:16:53Z","title_canon_sha256":"cd31b8ba8e0773d0e5fc9ae337f3ed2c7b69033533543747a0249cb5691cab7a"},"schema_version":"1.0","source":{"id":"2412.12700","kind":"arxiv","version":1}},"canonical_sha256":"8702899c3eab7d94d2399a8d1761ec6b61795030d59e9c9fe75f9ab30f0e05f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8702899c3eab7d94d2399a8d1761ec6b61795030d59e9c9fe75f9ab30f0e05f9","first_computed_at":"2026-07-05T09:50:19.399631Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:19.399631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OM4vlaNkldwkZHmHjcJYMbCsnIPBY0owbyTqRIJnrPm81/us+z3jyegHbCvqs9qlyUILZ2U+AkeMeNCuKt8BDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:19.400034Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.12700","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4514e70d2f44ee60804087c8b3a4b5b6187a021062e509d409133f035706e6c","sha256:fd2bc708215bff2cdda7df6f148f381d421c2c82acac50904535fffe6f436b05"],"state_sha256":"48654728047e821caf5b42424e8ef5f116fb738f2caa662deda8adbb4efe6526"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NeZ9EN9z8mh4q9jvIuTLKl89F9UJAWzzrMYAaRMLxqHhXqXQkmPS3SqO8C3fvcLBrB3JU9ylXcttslU/lrLQAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T21:47:09.536484Z","bundle_sha256":"f8dea3fe9b2dbb55f4df4a645ad13e605d8fc06c260826de769d10c8a7551de5"}}