{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:EJDE2VZDN3JTJ7UBC5NABCSITU","short_pith_number":"pith:EJDE2VZD","canonical_record":{"source":{"id":"1710.03937","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-10-11T07:19:17Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"32db093c0219c74955609228af2fb820aa50dfe29bef170570fb5c5fe8423d85","abstract_canon_sha256":"a0d8a0bf40f9a949ac83872d25e5446f468d692bf6bf9e924db546f66a75ac25"},"schema_version":"1.0"},"canonical_sha256":"22464d57236ed334fe81175a008a489d39538f63703e62a83a7f486c46b50b6c","source":{"kind":"arxiv","id":"1710.03937","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.03937","created_at":"2026-05-17T23:54:56Z"},{"alias_kind":"arxiv_version","alias_value":"1710.03937v2","created_at":"2026-05-17T23:54:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.03937","created_at":"2026-05-17T23:54:56Z"},{"alias_kind":"pith_short_12","alias_value":"EJDE2VZDN3JT","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"EJDE2VZDN3JTJ7UB","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"EJDE2VZD","created_at":"2026-05-18T12:31:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:EJDE2VZDN3JTJ7UBC5NABCSITU","target":"record","payload":{"canonical_record":{"source":{"id":"1710.03937","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-10-11T07:19:17Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"32db093c0219c74955609228af2fb820aa50dfe29bef170570fb5c5fe8423d85","abstract_canon_sha256":"a0d8a0bf40f9a949ac83872d25e5446f468d692bf6bf9e924db546f66a75ac25"},"schema_version":"1.0"},"canonical_sha256":"22464d57236ed334fe81175a008a489d39538f63703e62a83a7f486c46b50b6c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:56.567721Z","signature_b64":"w71dy1KH7e0vDLeF1VabZI2v+FX6pNJDydDDDfYMoi36wWOOjaPZT+UU0FNlPzIqIYXNHglYIwdyRH1U95nqAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22464d57236ed334fe81175a008a489d39538f63703e62a83a7f486c46b50b6c","last_reissued_at":"2026-05-17T23:54:56.567205Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:56.567205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.03937","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:54:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MRqOM9J0Ojh5aR3IkyHMXZ4UndLtU3Fg90ybDZQyjugMbUB3TJzXbxhVPRaa6FjcMkV9eL2I7TPE2KSr0UQXAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T05:10:06.674580Z"},"content_sha256":"68be445e152d70a06f0fb465910889188ac35c717228e4bfbdf4fcaa39b15c6a","schema_version":"1.0","event_id":"sha256:68be445e152d70a06f0fb465910889188ac35c717228e4bfbdf4fcaa39b15c6a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:EJDE2VZDN3JTJ7UBC5NABCSITU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PRM-RL: Long-range Robotic Navigation Tasks by Combining Reinforcement Learning and Sampling-based Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Aleksandra Faust, Anthony Francis, James Davidson, Kenneth Oslund, Lydia Tapia, Marek Fiser, Oscar Ramirez","submitted_at":"2017-10-11T07:19:17Z","abstract_excerpt":"We present PRM-RL, a hierarchical method for long-range navigation task completion that combines sampling based path planning with reinforcement learning (RL). The RL agents learn short-range, point-to-point navigation policies that capture robot dynamics and task constraints without knowledge of the large-scale topology. Next, the sampling-based planners provide roadmaps which connect robot configurations that can be successfully navigated by the RL agent. The same RL agents are used to control the robot under the direction of the planning, enabling long-range navigation. We use the Probabili"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.03937","kind":"arxiv","version":2},"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":"2026-05-17T23:54:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DgYP3V9D4RgF5cA7Nt76HzsdwhqpykmAoD3UFtSTHXjJvjPYZeKtEVH5oznp+anpjBAwpvB1bNCkSX+6mGzyAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T05:10:06.675311Z"},"content_sha256":"3c654aefc9adbb3e5b082a2fef21a04498a6eb13e7801a56e5be7f7febd95d75","schema_version":"1.0","event_id":"sha256:3c654aefc9adbb3e5b082a2fef21a04498a6eb13e7801a56e5be7f7febd95d75"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EJDE2VZDN3JTJ7UBC5NABCSITU/bundle.json","state_url":"https://pith.science/pith/EJDE2VZDN3JTJ7UBC5NABCSITU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EJDE2VZDN3JTJ7UBC5NABCSITU/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":"2026-05-31T05:10:06Z","links":{"resolver":"https://pith.science/pith/EJDE2VZDN3JTJ7UBC5NABCSITU","bundle":"https://pith.science/pith/EJDE2VZDN3JTJ7UBC5NABCSITU/bundle.json","state":"https://pith.science/pith/EJDE2VZDN3JTJ7UBC5NABCSITU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EJDE2VZDN3JTJ7UBC5NABCSITU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:EJDE2VZDN3JTJ7UBC5NABCSITU","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":"a0d8a0bf40f9a949ac83872d25e5446f468d692bf6bf9e924db546f66a75ac25","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-10-11T07:19:17Z","title_canon_sha256":"32db093c0219c74955609228af2fb820aa50dfe29bef170570fb5c5fe8423d85"},"schema_version":"1.0","source":{"id":"1710.03937","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.03937","created_at":"2026-05-17T23:54:56Z"},{"alias_kind":"arxiv_version","alias_value":"1710.03937v2","created_at":"2026-05-17T23:54:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.03937","created_at":"2026-05-17T23:54:56Z"},{"alias_kind":"pith_short_12","alias_value":"EJDE2VZDN3JT","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"EJDE2VZDN3JTJ7UB","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"EJDE2VZD","created_at":"2026-05-18T12:31:12Z"}],"graph_snapshots":[{"event_id":"sha256:3c654aefc9adbb3e5b082a2fef21a04498a6eb13e7801a56e5be7f7febd95d75","target":"graph","created_at":"2026-05-17T23:54:56Z","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":"We present PRM-RL, a hierarchical method for long-range navigation task completion that combines sampling based path planning with reinforcement learning (RL). The RL agents learn short-range, point-to-point navigation policies that capture robot dynamics and task constraints without knowledge of the large-scale topology. Next, the sampling-based planners provide roadmaps which connect robot configurations that can be successfully navigated by the RL agent. The same RL agents are used to control the robot under the direction of the planning, enabling long-range navigation. We use the Probabili","authors_text":"Aleksandra Faust, Anthony Francis, James Davidson, Kenneth Oslund, Lydia Tapia, Marek Fiser, Oscar Ramirez","cross_cats":["cs.LG","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-10-11T07:19:17Z","title":"PRM-RL: Long-range Robotic Navigation Tasks by Combining Reinforcement Learning and Sampling-based Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.03937","kind":"arxiv","version":2},"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":"sha256:68be445e152d70a06f0fb465910889188ac35c717228e4bfbdf4fcaa39b15c6a","target":"record","created_at":"2026-05-17T23:54:56Z","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":"a0d8a0bf40f9a949ac83872d25e5446f468d692bf6bf9e924db546f66a75ac25","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-10-11T07:19:17Z","title_canon_sha256":"32db093c0219c74955609228af2fb820aa50dfe29bef170570fb5c5fe8423d85"},"schema_version":"1.0","source":{"id":"1710.03937","kind":"arxiv","version":2}},"canonical_sha256":"22464d57236ed334fe81175a008a489d39538f63703e62a83a7f486c46b50b6c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22464d57236ed334fe81175a008a489d39538f63703e62a83a7f486c46b50b6c","first_computed_at":"2026-05-17T23:54:56.567205Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:56.567205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w71dy1KH7e0vDLeF1VabZI2v+FX6pNJDydDDDfYMoi36wWOOjaPZT+UU0FNlPzIqIYXNHglYIwdyRH1U95nqAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:56.567721Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.03937","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68be445e152d70a06f0fb465910889188ac35c717228e4bfbdf4fcaa39b15c6a","sha256:3c654aefc9adbb3e5b082a2fef21a04498a6eb13e7801a56e5be7f7febd95d75"],"state_sha256":"cf0ba6fa5a9af4aa0a2d1ccd7eb5fd7815c328b5a506945f8e1b33393c0a48f7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SLE0irsjmvA/7jeiIlzS6AcwDTzHDTuH3KJ5qDq/kQj2vSr00Fc7B25c3smMgTm5kbm5cm+Dmv40ueWt2g5TCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T05:10:06.679092Z","bundle_sha256":"9a4ae19160b4c4994f4e14552e82377685beee3adb8cbd83efa4551a1462e160"}}