{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:LPEJSQPQWBK55VZH3ZW6XAEU3E","short_pith_number":"pith:LPEJSQPQ","canonical_record":{"source":{"id":"1811.07745","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-19T15:15:18Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ccb9853a5008309257911272b849cf9b9d234823f1ad56c7147f1233ce9e0748","abstract_canon_sha256":"ec23e4bd05497a14d576798028a276a1055568c4d9c2d56a2b8abd62ec86099e"},"schema_version":"1.0"},"canonical_sha256":"5bc89941f0b055ded727de6deb8094d92420e412233199097f04a5c7b4de85fd","source":{"kind":"arxiv","id":"1811.07745","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.07745","created_at":"2026-05-18T00:00:23Z"},{"alias_kind":"arxiv_version","alias_value":"1811.07745v1","created_at":"2026-05-18T00:00:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.07745","created_at":"2026-05-18T00:00:23Z"},{"alias_kind":"pith_short_12","alias_value":"LPEJSQPQWBK5","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LPEJSQPQWBK55VZH","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LPEJSQPQ","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:LPEJSQPQWBK55VZH3ZW6XAEU3E","target":"record","payload":{"canonical_record":{"source":{"id":"1811.07745","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-19T15:15:18Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ccb9853a5008309257911272b849cf9b9d234823f1ad56c7147f1233ce9e0748","abstract_canon_sha256":"ec23e4bd05497a14d576798028a276a1055568c4d9c2d56a2b8abd62ec86099e"},"schema_version":"1.0"},"canonical_sha256":"5bc89941f0b055ded727de6deb8094d92420e412233199097f04a5c7b4de85fd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:23.557728Z","signature_b64":"O6VIAn4NtGSOkTqg85vETa84l2NDrWcSUG1PaMPcXREj5Le43+UTGs5ytQavR9RKNHW4KRsyVShnRh0WntwfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bc89941f0b055ded727de6deb8094d92420e412233199097f04a5c7b4de85fd","last_reissued_at":"2026-05-18T00:00:23.556767Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:23.556767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.07745","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":"2026-05-18T00:00:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tCjpflbXW5CvGRGBNSUHvLL2FOD0J9ksC9LToXlx67TfHmZnUC3uszlDieX+UnsLet//IjGGnzocyD93llKMBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T20:40:36.752192Z"},"content_sha256":"35be570403ac2d50aff5e229645c6d90a781a13421de6ce369d4b978a64cd734","schema_version":"1.0","event_id":"sha256:35be570403ac2d50aff5e229645c6d90a781a13421de6ce369d4b978a64cd734"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:LPEJSQPQWBK55VZH3ZW6XAEU3E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning with A* and a Deep Heuristic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adham Ghazali, Ariel Keselman, Majed Jubeh, Sergey Ten","submitted_at":"2018-11-19T15:15:18Z","abstract_excerpt":"A* is a popular path-finding algorithm, but it can only be applied to those domains where a good heuristic function is known. Inspired by recent methods combining Deep Neural Networks (DNNs) and trees, this study demonstrates how to train a heuristic represented by a DNN and combine it with A*. This new algorithm which we call aleph-star can be used efficiently in domains where the input to the heuristic could be processed by a neural network. We compare aleph-star to N-Step Deep Q-Learning (DQN Mnih et al. 2013) in a driving simulation with pixel-based input, and demonstrate significantly bet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.07745","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":""},"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":"2026-05-18T00:00:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I7YrZl1nhw0aPopIaQsd/yBaI2yWFzuzS91SQC9KXj+4MRzl+M0wiWqb1YIaoYaOlxzQ8IzjvJcCAVUkE32HCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T20:40:36.752559Z"},"content_sha256":"f1ac577158e0b9acf9ff93a143df33e777616306b1e76c672a8b23cca7a40336","schema_version":"1.0","event_id":"sha256:f1ac577158e0b9acf9ff93a143df33e777616306b1e76c672a8b23cca7a40336"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LPEJSQPQWBK55VZH3ZW6XAEU3E/bundle.json","state_url":"https://pith.science/pith/LPEJSQPQWBK55VZH3ZW6XAEU3E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LPEJSQPQWBK55VZH3ZW6XAEU3E/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":"2026-06-03T20:40:36Z","links":{"resolver":"https://pith.science/pith/LPEJSQPQWBK55VZH3ZW6XAEU3E","bundle":"https://pith.science/pith/LPEJSQPQWBK55VZH3ZW6XAEU3E/bundle.json","state":"https://pith.science/pith/LPEJSQPQWBK55VZH3ZW6XAEU3E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LPEJSQPQWBK55VZH3ZW6XAEU3E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:LPEJSQPQWBK55VZH3ZW6XAEU3E","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":"ec23e4bd05497a14d576798028a276a1055568c4d9c2d56a2b8abd62ec86099e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-19T15:15:18Z","title_canon_sha256":"ccb9853a5008309257911272b849cf9b9d234823f1ad56c7147f1233ce9e0748"},"schema_version":"1.0","source":{"id":"1811.07745","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.07745","created_at":"2026-05-18T00:00:23Z"},{"alias_kind":"arxiv_version","alias_value":"1811.07745v1","created_at":"2026-05-18T00:00:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.07745","created_at":"2026-05-18T00:00:23Z"},{"alias_kind":"pith_short_12","alias_value":"LPEJSQPQWBK5","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LPEJSQPQWBK55VZH","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LPEJSQPQ","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:f1ac577158e0b9acf9ff93a143df33e777616306b1e76c672a8b23cca7a40336","target":"graph","created_at":"2026-05-18T00:00:23Z","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"},"paper":{"abstract_excerpt":"A* is a popular path-finding algorithm, but it can only be applied to those domains where a good heuristic function is known. Inspired by recent methods combining Deep Neural Networks (DNNs) and trees, this study demonstrates how to train a heuristic represented by a DNN and combine it with A*. This new algorithm which we call aleph-star can be used efficiently in domains where the input to the heuristic could be processed by a neural network. We compare aleph-star to N-Step Deep Q-Learning (DQN Mnih et al. 2013) in a driving simulation with pixel-based input, and demonstrate significantly bet","authors_text":"Adham Ghazali, Ariel Keselman, Majed Jubeh, Sergey Ten","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-19T15:15:18Z","title":"Reinforcement Learning with A* and a Deep Heuristic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.07745","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":"sha256:35be570403ac2d50aff5e229645c6d90a781a13421de6ce369d4b978a64cd734","target":"record","created_at":"2026-05-18T00:00:23Z","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":"ec23e4bd05497a14d576798028a276a1055568c4d9c2d56a2b8abd62ec86099e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-19T15:15:18Z","title_canon_sha256":"ccb9853a5008309257911272b849cf9b9d234823f1ad56c7147f1233ce9e0748"},"schema_version":"1.0","source":{"id":"1811.07745","kind":"arxiv","version":1}},"canonical_sha256":"5bc89941f0b055ded727de6deb8094d92420e412233199097f04a5c7b4de85fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5bc89941f0b055ded727de6deb8094d92420e412233199097f04a5c7b4de85fd","first_computed_at":"2026-05-18T00:00:23.556767Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:23.556767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O6VIAn4NtGSOkTqg85vETa84l2NDrWcSUG1PaMPcXREj5Le43+UTGs5ytQavR9RKNHW4KRsyVShnRh0WntwfDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:23.557728Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.07745","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35be570403ac2d50aff5e229645c6d90a781a13421de6ce369d4b978a64cd734","sha256:f1ac577158e0b9acf9ff93a143df33e777616306b1e76c672a8b23cca7a40336"],"state_sha256":"fdc72be7e8ae9cb1004443a16804eacdf8aadc94cc23ed6d44f49df1a55302d1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qwfWnbvikR0aOP2xhu7BXyDgHu2dHizM0/0/dRiOAfDHlAnfy2huU9G1qvPDNqxdJEbh7NCNGunUEY9M9v8cCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T20:40:36.754682Z","bundle_sha256":"f4e7c35e1e4be44055e37f939ca4d3aaea6a091cfb9313d0aaf79f0e999b990a"}}