{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QEVDMBYQISA6DWQIAQ4B4CE6PW","short_pith_number":"pith:QEVDMBYQ","canonical_record":{"source":{"id":"2412.12650","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-17T08:19:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8a981ecefcad7ad24a9cb517152358f562aa422e0e158e85fb3f3a3581e860e8","abstract_canon_sha256":"f3a3c8aa93aca4eb1a60a0f443c0798f8cf5886588fe2aaf680bd6a1bf116cc4"},"schema_version":"1.0"},"canonical_sha256":"812a3607104481e1da0804381e089e7da3ebd0264fa9e1893af8775b2cd3b14e","source":{"kind":"arxiv","id":"2412.12650","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12650","created_at":"2026-07-05T09:50:38Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12650v1","created_at":"2026-07-05T09:50:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12650","created_at":"2026-07-05T09:50:38Z"},{"alias_kind":"pith_short_12","alias_value":"QEVDMBYQISA6","created_at":"2026-07-05T09:50:38Z"},{"alias_kind":"pith_short_16","alias_value":"QEVDMBYQISA6DWQI","created_at":"2026-07-05T09:50:38Z"},{"alias_kind":"pith_short_8","alias_value":"QEVDMBYQ","created_at":"2026-07-05T09:50:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QEVDMBYQISA6DWQIAQ4B4CE6PW","target":"record","payload":{"canonical_record":{"source":{"id":"2412.12650","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-17T08:19:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8a981ecefcad7ad24a9cb517152358f562aa422e0e158e85fb3f3a3581e860e8","abstract_canon_sha256":"f3a3c8aa93aca4eb1a60a0f443c0798f8cf5886588fe2aaf680bd6a1bf116cc4"},"schema_version":"1.0"},"canonical_sha256":"812a3607104481e1da0804381e089e7da3ebd0264fa9e1893af8775b2cd3b14e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:38.089998Z","signature_b64":"IPNdBAlByU5Ovm1XfI1ZCT+5gR+93Xjg1Fcoj3WauUocUojOoacDVNS06zAgYU1uEf5VQZmcNyW5Go7qs+ioDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"812a3607104481e1da0804381e089e7da3ebd0264fa9e1893af8775b2cd3b14e","last_reissued_at":"2026-07-05T09:50:38.089503Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:38.089503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.12650","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":"2026-07-05T09:50:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"57jFve9u2XnNY9VguFIuzwNBeH6XgoEeIEPb5rKovCbnhwuXWyYu2C8N+QVASlvQ8VoBPnfKlbmd9jHitElQCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T12:17:50.966646Z"},"content_sha256":"effb04037ea027af799ab7be475c6b01ef7775239e9e6ea3e67f51c19748c680","schema_version":"1.0","event_id":"sha256:effb04037ea027af799ab7be475c6b01ef7775239e9e6ea3e67f51c19748c680"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QEVDMBYQISA6DWQIAQ4B4CE6PW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural-Network-Driven Reward Prediction as a Heuristic: Advancing Q-Learning for Mobile Robot Path Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Hong Liu, Kaijie Yun, Yang Liu, Yiming Ji, Zongwu Xie","submitted_at":"2024-12-17T08:19:40Z","abstract_excerpt":"Q-learning is a widely used reinforcement learning technique for solving path planning problems. It primarily involves the interaction between an agent and its environment, enabling the agent to learn an optimal strategy that maximizes cumulative rewards. Although many studies have reported the effectiveness of Q-learning, it still faces slow convergence issues in practical applications. To address this issue, we propose the NDR-QL method, which utilizes neural network outputs as heuristic information to accelerate the convergence process of Q-learning. Specifically, we improved the dual-outpu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12650","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/2412.12650/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":"2026-07-05T09:50:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lFYNKUPI2CwzA9KbuKPU6GqnXlQWQQYNdIEw0avHHUpT9zAuAsalviN3ZlTjErnSgcDZD37/Kh+z63Oea9o3BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T12:17:50.967183Z"},"content_sha256":"74e55e6e3d11f5f4eea5f7e494706ff9e1582466b9a19f372f8a1e7bfcdd89a5","schema_version":"1.0","event_id":"sha256:74e55e6e3d11f5f4eea5f7e494706ff9e1582466b9a19f372f8a1e7bfcdd89a5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QEVDMBYQISA6DWQIAQ4B4CE6PW/bundle.json","state_url":"https://pith.science/pith/QEVDMBYQISA6DWQIAQ4B4CE6PW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QEVDMBYQISA6DWQIAQ4B4CE6PW/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":"2026-08-14T12:17:50Z","links":{"resolver":"https://pith.science/pith/QEVDMBYQISA6DWQIAQ4B4CE6PW","bundle":"https://pith.science/pith/QEVDMBYQISA6DWQIAQ4B4CE6PW/bundle.json","state":"https://pith.science/pith/QEVDMBYQISA6DWQIAQ4B4CE6PW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QEVDMBYQISA6DWQIAQ4B4CE6PW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QEVDMBYQISA6DWQIAQ4B4CE6PW","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":"f3a3c8aa93aca4eb1a60a0f443c0798f8cf5886588fe2aaf680bd6a1bf116cc4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-17T08:19:40Z","title_canon_sha256":"8a981ecefcad7ad24a9cb517152358f562aa422e0e158e85fb3f3a3581e860e8"},"schema_version":"1.0","source":{"id":"2412.12650","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12650","created_at":"2026-07-05T09:50:38Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12650v1","created_at":"2026-07-05T09:50:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12650","created_at":"2026-07-05T09:50:38Z"},{"alias_kind":"pith_short_12","alias_value":"QEVDMBYQISA6","created_at":"2026-07-05T09:50:38Z"},{"alias_kind":"pith_short_16","alias_value":"QEVDMBYQISA6DWQI","created_at":"2026-07-05T09:50:38Z"},{"alias_kind":"pith_short_8","alias_value":"QEVDMBYQ","created_at":"2026-07-05T09:50:38Z"}],"graph_snapshots":[{"event_id":"sha256:74e55e6e3d11f5f4eea5f7e494706ff9e1582466b9a19f372f8a1e7bfcdd89a5","target":"graph","created_at":"2026-07-05T09:50:38Z","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/2412.12650/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Q-learning is a widely used reinforcement learning technique for solving path planning problems. It primarily involves the interaction between an agent and its environment, enabling the agent to learn an optimal strategy that maximizes cumulative rewards. Although many studies have reported the effectiveness of Q-learning, it still faces slow convergence issues in practical applications. To address this issue, we propose the NDR-QL method, which utilizes neural network outputs as heuristic information to accelerate the convergence process of Q-learning. Specifically, we improved the dual-outpu","authors_text":"Hong Liu, Kaijie Yun, Yang Liu, Yiming Ji, Zongwu Xie","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-17T08:19:40Z","title":"Neural-Network-Driven Reward Prediction as a Heuristic: Advancing Q-Learning for Mobile Robot Path Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12650","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:effb04037ea027af799ab7be475c6b01ef7775239e9e6ea3e67f51c19748c680","target":"record","created_at":"2026-07-05T09:50:38Z","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":"f3a3c8aa93aca4eb1a60a0f443c0798f8cf5886588fe2aaf680bd6a1bf116cc4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-17T08:19:40Z","title_canon_sha256":"8a981ecefcad7ad24a9cb517152358f562aa422e0e158e85fb3f3a3581e860e8"},"schema_version":"1.0","source":{"id":"2412.12650","kind":"arxiv","version":1}},"canonical_sha256":"812a3607104481e1da0804381e089e7da3ebd0264fa9e1893af8775b2cd3b14e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"812a3607104481e1da0804381e089e7da3ebd0264fa9e1893af8775b2cd3b14e","first_computed_at":"2026-07-05T09:50:38.089503Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:38.089503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IPNdBAlByU5Ovm1XfI1ZCT+5gR+93Xjg1Fcoj3WauUocUojOoacDVNS06zAgYU1uEf5VQZmcNyW5Go7qs+ioDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:38.089998Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.12650","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:effb04037ea027af799ab7be475c6b01ef7775239e9e6ea3e67f51c19748c680","sha256:74e55e6e3d11f5f4eea5f7e494706ff9e1582466b9a19f372f8a1e7bfcdd89a5"],"state_sha256":"9d222582f2c81b3859136b06650048efde7da465b0c1cd1c4b464ec7e196cd73"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nuUbT3pqOqcQ+P9Uyc5wihtaIwsFAdkZ1NYFp5aWTOU4CjoqEUI/yxZ86hth9UCbrOQR9fcjDBWrPJBA120+AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T12:17:50.971845Z","bundle_sha256":"5097dba30eb9ace148a6f93e8b82e12e07d69409e2da7b0acf9b6a373faeac3e"}}