{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5FFG5GLVC2H2GNTD7LXAG43M6Q","short_pith_number":"pith:5FFG5GLV","canonical_record":{"source":{"id":"2512.07775","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-12-08T17:56:57Z","cross_cats_sorted":[],"title_canon_sha256":"8ef638ebb2dc2419d19b780aaf6b607d4750b95bdb0b84382054a3578b47cc9b","abstract_canon_sha256":"f9ebe30c29aad80617b9b7baaab56fade7b9f9c8f186bff63110eee8802df2a8"},"schema_version":"1.0"},"canonical_sha256":"e94a6e9975168fa33663faee03736cf4103a7974d33e162124c3617e838abaea","source":{"kind":"arxiv","id":"2512.07775","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.07775","created_at":"2026-05-18T03:10:11Z"},{"alias_kind":"arxiv_version","alias_value":"2512.07775v2","created_at":"2026-05-18T03:10:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.07775","created_at":"2026-05-18T03:10:11Z"},{"alias_kind":"pith_short_12","alias_value":"5FFG5GLVC2H2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"5FFG5GLVC2H2GNTD","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"5FFG5GLV","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5FFG5GLVC2H2GNTD7LXAG43M6Q","target":"record","payload":{"canonical_record":{"source":{"id":"2512.07775","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-12-08T17:56:57Z","cross_cats_sorted":[],"title_canon_sha256":"8ef638ebb2dc2419d19b780aaf6b607d4750b95bdb0b84382054a3578b47cc9b","abstract_canon_sha256":"f9ebe30c29aad80617b9b7baaab56fade7b9f9c8f186bff63110eee8802df2a8"},"schema_version":"1.0"},"canonical_sha256":"e94a6e9975168fa33663faee03736cf4103a7974d33e162124c3617e838abaea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:10:11.631376Z","signature_b64":"gkuU26DaG7Ia9WbClbWxL2ZFil2wYM4cXAiGBRnE90etOfgsoAYuHIrGrAM0EaKqlqOofYBIdjVzsZIyBPdHDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e94a6e9975168fa33663faee03736cf4103a7974d33e162124c3617e838abaea","last_reissued_at":"2026-05-18T03:10:11.630696Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:10:11.630696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2512.07775","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":"2026-05-18T03:10:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uidAKCjl4YiyvuPDGbhDmEgoAnoSygu8V9o4UTVj1kQ64hRyzAfUOHFg7Z+knx/+RCaAYav+jq5P4zY8LFy1Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T10:47:08.469063Z"},"content_sha256":"613eb11d25285c0a6161b3e290e403df6c09028ba5c28cc16b5a24b043d4c8f2","schema_version":"1.0","event_id":"sha256:613eb11d25285c0a6161b3e290e403df6c09028ba5c28cc16b5a24b043d4c8f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5FFG5GLVC2H2GNTD7LXAG43M6Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OptMap: Geometric Map Distillation via Submodular Maximization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"OptMap distills large LiDAR streams into compact application-specific maps by maximizing a submodular reward function with polynomial-time near-optimal algorithms.","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Brett T. Lopez, Christa S. Robison, David Thorne, Nathan Chan, Philip R. Osteen","submitted_at":"2025-12-08T17:56:57Z","abstract_excerpt":"Autonomous robots rely on geometric maps to inform a diverse set of perception and decision-making algorithms. As autonomy requires reasoning and planning on multiple scales, each algorithm may require a different map for optimal performance. LiDAR sensors generate an abundance of geometric data (up to 50 MB per second) to satisfy these diverse requirements. However, the point-based operations required to process perception data are both memory and computationally expensive. Such operations can be bypassed via learned representations that encode similarity, but selecting informative, size-cons"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We present OptMap: a geometric map distillation algorithm which achieves online, application-specific map generation via multiple theoretical and algorithmic innovations. A central feature is the maximization of set functions that exhibit diminishing returns, i.e., submodularity, using polynomial-time algorithms with provably near-optimal solutions.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the proposed reward function is submodular (or sufficiently close) so that the polynomial-time greedy-style algorithms retain their near-optimality guarantees when applied to real LiDAR streams.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"OptMap generates compact, application-specific geometric maps from streaming LiDAR data using a novel submodular reward function and a dynamically reordered streaming maximization algorithm.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"OptMap distills large LiDAR streams into compact application-specific maps by maximizing a submodular reward function with polynomial-time near-optimal algorithms.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"48df3fec5ce2a5c4f418e8ef381fcf213bfbc6239b05faa38769107811ae5259"},"source":{"id":"2512.07775","kind":"arxiv","version":2},"verdict":{"id":"404297c2-02b8-4b5e-a72b-6da31eedf6be","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T00:29:11.063863Z","strongest_claim":"We present OptMap: a geometric map distillation algorithm which achieves online, application-specific map generation via multiple theoretical and algorithmic innovations. A central feature is the maximization of set functions that exhibit diminishing returns, i.e., submodularity, using polynomial-time algorithms with provably near-optimal solutions.","one_line_summary":"OptMap generates compact, application-specific geometric maps from streaming LiDAR data using a novel submodular reward function and a dynamically reordered streaming maximization algorithm.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the proposed reward function is submodular (or sufficiently close) so that the polynomial-time greedy-style algorithms retain their near-optimality guarantees when applied to real LiDAR streams.","pith_extraction_headline":"OptMap distills large LiDAR streams into compact application-specific maps by maximizing a submodular reward function with polynomial-time near-optimal algorithms."},"references":{"count":61,"sample":[{"doi":"","year":2022,"title":"Overlaptransformer: An efficient and yaw-angle-invariant transformer network for lidar-based place recognition,","work_id":"7e4603dc-620b-403c-850e-5bdbcbc6a155","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Overlapnet: A siamese network for computing lidar scan similarity with applications to loop closing and localization,","work_id":"48c69809-24cc-4589-a88e-05c9e3e82cc5","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Padloc: Lidar-based deep loop closure detection and registration using panoptic attention,","work_id":"3cb732ac-ac60-47a8-b63e-aa4e9ca3bbc8","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Minkloc3d: Point cloud based large-scale place recog- nition,","work_id":"523ff79a-c759-4954-8b49-d6cd0be4efc0","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Submodular optimization for keyframe selection & usage in slam,","work_id":"1f9dd0ce-7069-4671-9e2c-1879d9bfcac5","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":61,"snapshot_sha256":"fd2bac47905bb00aea4675fe0023d6996b0c24ba7586a4b68d09c3ff668e1cac","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"be25867fc8649f07a2a4d82ec2f714d297a271732d49b728c96c4c1258c1b237"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"404297c2-02b8-4b5e-a72b-6da31eedf6be"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:10:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VC5pbeAwlF9GPglUONMjax4KS4480/XD8aXuYzVIWaXF8jVnDPoV4a6O0XUw7Y0V9Hx3HAxi6+KdXppm2z+aDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T10:47:08.469594Z"},"content_sha256":"8c9efae82cd551ddb1ee8e135f60d6b16f64be18709f3ac398b29dd17e188af9","schema_version":"1.0","event_id":"sha256:8c9efae82cd551ddb1ee8e135f60d6b16f64be18709f3ac398b29dd17e188af9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5FFG5GLVC2H2GNTD7LXAG43M6Q/bundle.json","state_url":"https://pith.science/pith/5FFG5GLVC2H2GNTD7LXAG43M6Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5FFG5GLVC2H2GNTD7LXAG43M6Q/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":"2026-05-28T10:47:08Z","links":{"resolver":"https://pith.science/pith/5FFG5GLVC2H2GNTD7LXAG43M6Q","bundle":"https://pith.science/pith/5FFG5GLVC2H2GNTD7LXAG43M6Q/bundle.json","state":"https://pith.science/pith/5FFG5GLVC2H2GNTD7LXAG43M6Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5FFG5GLVC2H2GNTD7LXAG43M6Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5FFG5GLVC2H2GNTD7LXAG43M6Q","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":"f9ebe30c29aad80617b9b7baaab56fade7b9f9c8f186bff63110eee8802df2a8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-12-08T17:56:57Z","title_canon_sha256":"8ef638ebb2dc2419d19b780aaf6b607d4750b95bdb0b84382054a3578b47cc9b"},"schema_version":"1.0","source":{"id":"2512.07775","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.07775","created_at":"2026-05-18T03:10:11Z"},{"alias_kind":"arxiv_version","alias_value":"2512.07775v2","created_at":"2026-05-18T03:10:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.07775","created_at":"2026-05-18T03:10:11Z"},{"alias_kind":"pith_short_12","alias_value":"5FFG5GLVC2H2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"5FFG5GLVC2H2GNTD","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"5FFG5GLV","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:8c9efae82cd551ddb1ee8e135f60d6b16f64be18709f3ac398b29dd17e188af9","target":"graph","created_at":"2026-05-18T03:10:11Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We present OptMap: a geometric map distillation algorithm which achieves online, application-specific map generation via multiple theoretical and algorithmic innovations. A central feature is the maximization of set functions that exhibit diminishing returns, i.e., submodularity, using polynomial-time algorithms with provably near-optimal solutions."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the proposed reward function is submodular (or sufficiently close) so that the polynomial-time greedy-style algorithms retain their near-optimality guarantees when applied to real LiDAR streams."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"OptMap generates compact, application-specific geometric maps from streaming LiDAR data using a novel submodular reward function and a dynamically reordered streaming maximization algorithm."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"OptMap distills large LiDAR streams into compact application-specific maps by maximizing a submodular reward function with polynomial-time near-optimal algorithms."}],"snapshot_sha256":"48df3fec5ce2a5c4f418e8ef381fcf213bfbc6239b05faa38769107811ae5259"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"be25867fc8649f07a2a4d82ec2f714d297a271732d49b728c96c4c1258c1b237"},"paper":{"abstract_excerpt":"Autonomous robots rely on geometric maps to inform a diverse set of perception and decision-making algorithms. As autonomy requires reasoning and planning on multiple scales, each algorithm may require a different map for optimal performance. LiDAR sensors generate an abundance of geometric data (up to 50 MB per second) to satisfy these diverse requirements. However, the point-based operations required to process perception data are both memory and computationally expensive. Such operations can be bypassed via learned representations that encode similarity, but selecting informative, size-cons","authors_text":"Brett T. Lopez, Christa S. Robison, David Thorne, Nathan Chan, Philip R. Osteen","cross_cats":[],"headline":"OptMap distills large LiDAR streams into compact application-specific maps by maximizing a submodular reward function with polynomial-time near-optimal algorithms.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-12-08T17:56:57Z","title":"OptMap: Geometric Map Distillation via Submodular Maximization"},"references":{"count":61,"internal_anchors":0,"resolved_work":61,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Overlaptransformer: An efficient and yaw-angle-invariant transformer network for lidar-based place recognition,","work_id":"7e4603dc-620b-403c-850e-5bdbcbc6a155","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Overlapnet: A siamese network for computing lidar scan similarity with applications to loop closing and localization,","work_id":"48c69809-24cc-4589-a88e-05c9e3e82cc5","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Padloc: Lidar-based deep loop closure detection and registration using panoptic attention,","work_id":"3cb732ac-ac60-47a8-b63e-aa4e9ca3bbc8","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Minkloc3d: Point cloud based large-scale place recog- nition,","work_id":"523ff79a-c759-4954-8b49-d6cd0be4efc0","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Submodular optimization for keyframe selection & usage in slam,","work_id":"1f9dd0ce-7069-4671-9e2c-1879d9bfcac5","year":2025}],"snapshot_sha256":"fd2bac47905bb00aea4675fe0023d6996b0c24ba7586a4b68d09c3ff668e1cac"},"source":{"id":"2512.07775","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-17T00:29:11.063863Z","id":"404297c2-02b8-4b5e-a72b-6da31eedf6be","model_set":{"reader":"grok-4.3"},"one_line_summary":"OptMap generates compact, application-specific geometric maps from streaming LiDAR data using a novel submodular reward function and a dynamically reordered streaming maximization algorithm.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"OptMap distills large LiDAR streams into compact application-specific maps by maximizing a submodular reward function with polynomial-time near-optimal algorithms.","strongest_claim":"We present OptMap: a geometric map distillation algorithm which achieves online, application-specific map generation via multiple theoretical and algorithmic innovations. A central feature is the maximization of set functions that exhibit diminishing returns, i.e., submodularity, using polynomial-time algorithms with provably near-optimal solutions.","weakest_assumption":"That the proposed reward function is submodular (or sufficiently close) so that the polynomial-time greedy-style algorithms retain their near-optimality guarantees when applied to real LiDAR streams."}},"verdict_id":"404297c2-02b8-4b5e-a72b-6da31eedf6be"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:613eb11d25285c0a6161b3e290e403df6c09028ba5c28cc16b5a24b043d4c8f2","target":"record","created_at":"2026-05-18T03:10:11Z","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":"f9ebe30c29aad80617b9b7baaab56fade7b9f9c8f186bff63110eee8802df2a8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-12-08T17:56:57Z","title_canon_sha256":"8ef638ebb2dc2419d19b780aaf6b607d4750b95bdb0b84382054a3578b47cc9b"},"schema_version":"1.0","source":{"id":"2512.07775","kind":"arxiv","version":2}},"canonical_sha256":"e94a6e9975168fa33663faee03736cf4103a7974d33e162124c3617e838abaea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e94a6e9975168fa33663faee03736cf4103a7974d33e162124c3617e838abaea","first_computed_at":"2026-05-18T03:10:11.630696Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:10:11.630696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gkuU26DaG7Ia9WbClbWxL2ZFil2wYM4cXAiGBRnE90etOfgsoAYuHIrGrAM0EaKqlqOofYBIdjVzsZIyBPdHDg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:10:11.631376Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.07775","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:613eb11d25285c0a6161b3e290e403df6c09028ba5c28cc16b5a24b043d4c8f2","sha256:8c9efae82cd551ddb1ee8e135f60d6b16f64be18709f3ac398b29dd17e188af9"],"state_sha256":"3d95032779113ac2044bf5af84a5905fb1c5f3e7ae21d666506752ee193d560a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KdaQunoGY3aOZlI7tJT6O2SxIp3UtcetzfgrimSWZyl931QIi1TAC++2Rh0CBDYrWN226Gj/TpwBG1enctarDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T10:47:08.472282Z","bundle_sha256":"22fdcd8f76ca6b023b04c0317e5e2949a0fc8aa5aadd9af8b76659d50d430156"}}