{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IEBVXZKRUNAJHBZWQ33VPV7TJD","short_pith_number":"pith:IEBVXZKR","canonical_record":{"source":{"id":"2605.02098","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-03T23:36:32Z","cross_cats_sorted":[],"title_canon_sha256":"beb3ea8bba97739889b7aa2f1b6c79bee32c6d061cbb517e83b22c68a8d2cd91","abstract_canon_sha256":"06102f4be5b0dfa9266f12dd31df574fa0607f3ee1c7659a973659417829e15c"},"schema_version":"1.0"},"canonical_sha256":"41035be551a34093873686f757d7f348dce083261debaac36d1919ef28fbc778","source":{"kind":"arxiv","id":"2605.02098","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.02098","created_at":"2026-05-22T01:04:04Z"},{"alias_kind":"arxiv_version","alias_value":"2605.02098v2","created_at":"2026-05-22T01:04:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.02098","created_at":"2026-05-22T01:04:04Z"},{"alias_kind":"pith_short_12","alias_value":"IEBVXZKRUNAJ","created_at":"2026-05-22T01:04:04Z"},{"alias_kind":"pith_short_16","alias_value":"IEBVXZKRUNAJHBZW","created_at":"2026-05-22T01:04:04Z"},{"alias_kind":"pith_short_8","alias_value":"IEBVXZKR","created_at":"2026-05-22T01:04:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IEBVXZKRUNAJHBZWQ33VPV7TJD","target":"record","payload":{"canonical_record":{"source":{"id":"2605.02098","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-03T23:36:32Z","cross_cats_sorted":[],"title_canon_sha256":"beb3ea8bba97739889b7aa2f1b6c79bee32c6d061cbb517e83b22c68a8d2cd91","abstract_canon_sha256":"06102f4be5b0dfa9266f12dd31df574fa0607f3ee1c7659a973659417829e15c"},"schema_version":"1.0"},"canonical_sha256":"41035be551a34093873686f757d7f348dce083261debaac36d1919ef28fbc778","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:04.090473Z","signature_b64":"JPntNVskHs1radDcU9dRnak+FlORlxLIYDY6XGNeI8S0lItc75t1KoAiXsPkGF7c/lD54TCa5ysbaO1DMUVkDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41035be551a34093873686f757d7f348dce083261debaac36d1919ef28fbc778","last_reissued_at":"2026-05-22T01:04:04.089740Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:04.089740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.02098","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":"2026-05-22T01:04:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NCSsrh9WVSwoR9dLk07Jd40W6LnvOasakBnu4ntOsIzKuteFyLg2dYVI4qf4lBrfbkjLlXEq0Uz7zJguJCUzCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T15:23:27.871373Z"},"content_sha256":"384d9ad835b27a16bd6a0da61b6d3ca1bd04fa4763d13dc8b205b4e19b8e232e","schema_version":"1.0","event_id":"sha256:384d9ad835b27a16bd6a0da61b6d3ca1bd04fa4763d13dc8b205b4e19b8e232e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IEBVXZKRUNAJHBZWQ33VPV7TJD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Spherical to Gaussian: A Comparative Analysis of Point Cloud Cropping Strategies in Large-Scale 3D Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Switching from spherical to Gaussian cropping improves 3D semantic segmentation on large outdoor point clouds.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Reiterer, Dominik Merkle, Maximilian Kellner, Michael Brunklaus","submitted_at":"2026-05-03T23:36:32Z","abstract_excerpt":"Large-scale 3D point clouds can consist of hundreds of millions of points. Even after downsampling, these point clouds are too large for modern 3D neural networks. In order to develop a semantic understanding of the scene, the point clouds are divided into smaller subclouds that can be processed. Typically, this division is done using spherical crops, resulting in a loss of surrounding geometric context. To address this issue, we propose alternative methods that produce subclouds with larger crop sizes while maintaining a similar number of points. Specifically, we compare exponential, Gaussian"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our results demonstrate that altering the cropping strategy can enhance model performance, especially for large-scale outdoor scenes, yielding new state-of-the-art results.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that performance differences are caused by the cropping geometry itself rather than by unstated implementation details, hyper-parameter choices, or dataset-specific effects, since the abstract provides no quantitative numbers, error bars, or ablation controls.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Gaussian and linear cropping strategies for large point clouds improve 3D neural network performance over spherical crops, especially in outdoor scenes, and achieve new state-of-the-art results.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Switching from spherical to Gaussian cropping improves 3D semantic segmentation on large outdoor point clouds.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"cd458ac20be0352161feb7c969014ebc9dca981e65a79eb888d94ab65d128e07"},"source":{"id":"2605.02098","kind":"arxiv","version":2},"verdict":{"id":"cc43951e-96d2-45aa-bd2e-88f6a6eaf826","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T19:09:35.751395Z","strongest_claim":"Our results demonstrate that altering the cropping strategy can enhance model performance, especially for large-scale outdoor scenes, yielding new state-of-the-art results.","one_line_summary":"Gaussian and linear cropping strategies for large point clouds improve 3D neural network performance over spherical crops, especially in outdoor scenes, and achieve new state-of-the-art results.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that performance differences are caused by the cropping geometry itself rather than by unstated implementation details, hyper-parameter choices, or dataset-specific effects, since the abstract provides no quantitative numbers, error bars, or ablation controls.","pith_extraction_headline":"Switching from spherical to Gaussian cropping improves 3D semantic segmentation on large outdoor point clouds."},"integrity":{"clean":false,"summary":{"advisory":4,"critical":0,"by_detector":{"doi_compliance":{"total":4,"advisory":4,"critical":0,"informational":0}},"informational":0},"endpoint":"/pith/2605.02098/integrity.json","findings":[{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/ARXIV.2205.14135.URLhttps://arxiv.org/abs/2205.14135) was visible in the surrounding text but could not be confirmed against doi.org as printed.","detector":"doi_compliance","severity":"advisory","ref_index":67,"audited_at":"2026-05-19T16:40:33.038920Z","detected_doi":"10.48550/ARXIV.2205.14135.URLhttps://arxiv.org/abs/2205.14135","finding_type":"recoverable_identifier","verdict_class":"incontrovertible","detected_arxiv_id":null},{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/arXiv.1612.00593.URLhttp://arxiv.org/abs/1612.00593) was visible in the surrounding text but could not be confirmed against doi.org as printed.","detector":"doi_compliance","severity":"advisory","ref_index":1,"audited_at":"2026-05-19T16:40:33.038920Z","detected_doi":"10.48550/arXiv.1612.00593.URLhttp://arxiv.org/abs/1612.00593","finding_type":"recoverable_identifier","verdict_class":"incontrovertible","detected_arxiv_id":null},{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/arXiv.1710.07563.URLhttp://arxiv.org/abs/1710.07563) was visible in the surrounding text but could not be confirmed against doi.org as printed.","detector":"doi_compliance","severity":"advisory","ref_index":19,"audited_at":"2026-05-19T16:40:33.038920Z","detected_doi":"10.48550/arXiv.1710.07563.URLhttp://arxiv.org/abs/1710.07563","finding_type":"recoverable_identifier","verdict_class":"incontrovertible","detected_arxiv_id":null},{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/arXiv.2206.02099.URLhttp://arxiv.org/abs/2206.02099) was visible in the surrounding text but could not be confirmed against doi.org as printed.","detector":"doi_compliance","severity":"advisory","ref_index":43,"audited_at":"2026-05-19T16:40:33.038920Z","detected_doi":"10.48550/arXiv.2206.02099.URLhttp://arxiv.org/abs/2206.02099","finding_type":"recoverable_identifier","verdict_class":"incontrovertible","detected_arxiv_id":null}],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T16:37:52.876924Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-20T04:01:22.719134Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T16:40:33.038920Z","status":"completed","version":"1.0.0","findings_count":4}],"snapshot_sha256":"d7915dc502b27e54399f3d424b4125c2fb1ae08282b5b845f91ca3f0e7577762"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"67b0d271374b761b8cfcf2dc51cb6baea9836a529b8a8e8b221e9ca6bb660996"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"cc43951e-96d2-45aa-bd2e-88f6a6eaf826"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T01:04:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CWy69wYzl+pojHUazrnZt4B44IzduHU/i06/kFDjK9QhXuMBB1QPl9ZWdlF6O3Gh7qjsXxXbGjFcCYiTR4T7Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T15:23:27.872002Z"},"content_sha256":"097974553b21b32b482efe29c917ed8e5476bd843bdc59257831394b553e47d7","schema_version":"1.0","event_id":"sha256:097974553b21b32b482efe29c917ed8e5476bd843bdc59257831394b553e47d7"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:IEBVXZKRUNAJHBZWQ33VPV7TJD","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/ARXIV.2205.14135.URLhttps://arxiv.org/abs/2205.14135) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"T. Dao, D. Y. Fu, S. Ermon, A. Rudra, C. Ré, FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness, version Number: 2 (2022).doi:10.48550/ARXIV. 2205.14135. URLhttps://arxiv.org/abs/2205.14135","arxiv_id":"2605.02098","detector":"doi_compliance","evidence":{"ref_index":67,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"T. Dao, D. Y. Fu, S. Ermon, A. Rudra, C. Ré, FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness, version Number: 2 (2022).doi:10.48550/ARXIV. 2205.14135. URLhttps://arxiv.org/abs/2205.14135","reconstructed_doi":"10.48550/ARXIV.2205.14135.URLhttps://arxiv.org/abs/2205.14135"},"severity":"advisory","ref_index":67,"audited_at":"2026-05-19T16:40:33.038920Z","event_type":"pith.integrity.v1","detected_doi":"10.48550/ARXIV.2205.14135.URLhttps://arxiv.org/abs/2205.14135","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"e66e753031a31882fd8eeeece04eb3f3b825553c4e7fa8a95e4c050ecc249cb6","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":2096,"payload_sha256":"0c40fef8ae45f34bdb84de7c51f68b8d4e0b169c04d75f60c605c0a8fd317a51","signature_b64":"jJOSQ+AauZW54eIQ6luOd8V7VCdWxQ1MdRfL3wDCXdLG3b31LDhAcbPHpbX7M3Xr0ZxnANPf46CMIz+bZ3VsDg==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-19T16:42:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pCLc02b7dYKqc++3OOEaeJkokX6TjwRcGrNePSDDyAmZ4AIZkEWLSTdP4mbgqUMtA/mj6QA8T+ezR+Ng1kQmCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T15:23:27.873209Z"},"content_sha256":"ca39b1cde3409410bd02dd81c10937492286a136911cd7c7a32ee0519db0b3ff","schema_version":"1.0","event_id":"sha256:ca39b1cde3409410bd02dd81c10937492286a136911cd7c7a32ee0519db0b3ff"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:IEBVXZKRUNAJHBZWQ33VPV7TJD","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/arXiv.2206.02099.URLhttp://arxiv.org/abs/2206.02099) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Y.Hou, X.Zhu, Y.Ma, C.C.Loy, Y.Li, Point- to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation, arXiv:2206.02099 [cs] (Jun. 2022).doi:10.48550/arXiv.2206. 02099. URLhttp://arxiv.org/abs/2206.02099","arxiv_id":"2605.02098","detector":"doi_compliance","evidence":{"ref_index":43,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"Y.Hou, X.Zhu, Y.Ma, C.C.Loy, Y.Li, Point- to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation, arXiv:2206.02099 [cs] (Jun. 2022).doi:10.48550/arXiv.2206. 02099. URLhttp://arxiv.org/abs/2206.02099","reconstructed_doi":"10.48550/arXiv.2206.02099.URLhttp://arxiv.org/abs/2206.02099"},"severity":"advisory","ref_index":43,"audited_at":"2026-05-19T16:40:33.038920Z","event_type":"pith.integrity.v1","detected_doi":"10.48550/arXiv.2206.02099.URLhttp://arxiv.org/abs/2206.02099","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"853616de84c595e8e6ba035c164565a0994b4a47595558bd55e1c22e8ab1d65e","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":2095,"payload_sha256":"d275ecd1eedf994f4044d87f0962abfb5ecb24bb2899de72d2a08b91b6127fb0","signature_b64":"KQiNFiIdEGiUQ9JfKLcFe9BOIq89AFf8wdqw/hsym3nSLjwyv5ReVcr0FGRQzMOgYVooz9xPc6N5jr2ExfpTDg==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-19T16:42:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hhz+wLAV5N9ebpu1BYyIR43vlsshQBrv15QzRxhkUECtQSU6VVlfGl+aE2DBFRMGmptvulmYL4d77g092MppBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T15:23:27.873513Z"},"content_sha256":"e443aa8244c18d3d91d2dbaf4ade0b7560a4ef71604fa5b84a301e0018b4ffd2","schema_version":"1.0","event_id":"sha256:e443aa8244c18d3d91d2dbaf4ade0b7560a4ef71604fa5b84a301e0018b4ffd2"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:IEBVXZKRUNAJHBZWQ33VPV7TJD","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/arXiv.1710.07563.URLhttp://arxiv.org/abs/1710.07563) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"L.P.Tchapmi, C.B.Choy, I.Armeni, J.Gwak, S. Savarese, SEGCloud: Semantic Segmen- tation of 3D Point Clouds, arXiv:1710.07563 [cs] (Oct. 2017).doi:10.48550/arXiv.1710. 07563. URLhttp://arxiv.org/abs/1710.07563","arxiv_id":"2605.02098","detector":"doi_compliance","evidence":{"ref_index":19,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"L.P.Tchapmi, C.B.Choy, I.Armeni, J.Gwak, S. Savarese, SEGCloud: Semantic Segmen- tation of 3D Point Clouds, arXiv:1710.07563 [cs] (Oct. 2017).doi:10.48550/arXiv.1710. 07563. URLhttp://arxiv.org/abs/1710.07563","reconstructed_doi":"10.48550/arXiv.1710.07563.URLhttp://arxiv.org/abs/1710.07563"},"severity":"advisory","ref_index":19,"audited_at":"2026-05-19T16:40:33.038920Z","event_type":"pith.integrity.v1","detected_doi":"10.48550/arXiv.1710.07563.URLhttp://arxiv.org/abs/1710.07563","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"d997d78a52d41a875578668b127836002c4432e7ad69fdb2334525de2c639954","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":2094,"payload_sha256":"d111dd991c0e8189139a13da66b373ced8f578984b94fbbb7ac61e177fb23104","signature_b64":"8HgyegEGD0DvG7CDxL/x5IJHkTgiMsuaSy01A2uEj8X6v4Mspg/5/dHsJeZoGMwAbOfEY747/ijERHRsSmlBDA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-19T16:42:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wh7yldpF5wz/LsevwUlCZoPUpxaT/xdP9LcR3fpsKc6ikv2CT5m9UypEvKNvZa4xCeZsPDSomgSRjxGE5aedCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T15:23:27.873783Z"},"content_sha256":"a8f68206735c36c5d33b8da36b41014335544724ec57d499d49d54062b84727d","schema_version":"1.0","event_id":"sha256:a8f68206735c36c5d33b8da36b41014335544724ec57d499d49d54062b84727d"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:IEBVXZKRUNAJHBZWQ33VPV7TJD","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/arXiv.1612.00593.URLhttp://arxiv.org/abs/1612.00593) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"C. R. Qi, H. Su, K. Mo, L. J. Guibas, Point- Net: Deep Learning on Point Sets for 3D Clas- sification and Segmentation, arXiv:1612.00593 [cs] (Feb. 2016).doi:10.48550/arXiv.1612. 00593. URLhttp://arxiv.org/abs/1612.00593","arxiv_id":"2605.02098","detector":"doi_compliance","evidence":{"ref_index":1,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"C. R. Qi, H. Su, K. Mo, L. J. Guibas, Point- Net: Deep Learning on Point Sets for 3D Clas- sification and Segmentation, arXiv:1612.00593 [cs] (Feb. 2016).doi:10.48550/arXiv.1612. 00593. URLhttp://arxiv.org/abs/1612.00593","reconstructed_doi":"10.48550/arXiv.1612.00593.URLhttp://arxiv.org/abs/1612.00593"},"severity":"advisory","ref_index":1,"audited_at":"2026-05-19T16:40:33.038920Z","event_type":"pith.integrity.v1","detected_doi":"10.48550/arXiv.1612.00593.URLhttp://arxiv.org/abs/1612.00593","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"1b6ba7956d4214b1756bca945b14446810426d6de2ccb46ae42d02039fb171a3","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":2093,"payload_sha256":"8a55f937c18a33ed0861acd6ceb73786d997fcd29d53a0e085fd37e0c62b9d1d","signature_b64":"52yUBl62jx5BvTiJuobXVpE4qvth9r+8mfY5j+ijbywMq78DbmGDBmXnI2eGA+WsiEbw8oEWC1pNU12cTAhbDA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-19T16:42:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FG0KAa7fNAznVkRlbgqm1JMrie4PpK4yHg+7L24nF2kiNVPWvnVoAj5YMyw80EhD5gCZoEss4/44C659dEKhBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T15:23:27.874054Z"},"content_sha256":"e3579481d1070142d9fe780d2a745ec4267ab82de7f61775b39086e1d518df42","schema_version":"1.0","event_id":"sha256:e3579481d1070142d9fe780d2a745ec4267ab82de7f61775b39086e1d518df42"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IEBVXZKRUNAJHBZWQ33VPV7TJD/bundle.json","state_url":"https://pith.science/pith/IEBVXZKRUNAJHBZWQ33VPV7TJD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IEBVXZKRUNAJHBZWQ33VPV7TJD/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":"2026-05-29T15:23:27Z","links":{"resolver":"https://pith.science/pith/IEBVXZKRUNAJHBZWQ33VPV7TJD","bundle":"https://pith.science/pith/IEBVXZKRUNAJHBZWQ33VPV7TJD/bundle.json","state":"https://pith.science/pith/IEBVXZKRUNAJHBZWQ33VPV7TJD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IEBVXZKRUNAJHBZWQ33VPV7TJD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IEBVXZKRUNAJHBZWQ33VPV7TJD","merge_version":"pith-open-graph-merge-v1","event_count":6,"valid_event_count":6,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"06102f4be5b0dfa9266f12dd31df574fa0607f3ee1c7659a973659417829e15c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-03T23:36:32Z","title_canon_sha256":"beb3ea8bba97739889b7aa2f1b6c79bee32c6d061cbb517e83b22c68a8d2cd91"},"schema_version":"1.0","source":{"id":"2605.02098","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.02098","created_at":"2026-05-22T01:04:04Z"},{"alias_kind":"arxiv_version","alias_value":"2605.02098v2","created_at":"2026-05-22T01:04:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.02098","created_at":"2026-05-22T01:04:04Z"},{"alias_kind":"pith_short_12","alias_value":"IEBVXZKRUNAJ","created_at":"2026-05-22T01:04:04Z"},{"alias_kind":"pith_short_16","alias_value":"IEBVXZKRUNAJHBZW","created_at":"2026-05-22T01:04:04Z"},{"alias_kind":"pith_short_8","alias_value":"IEBVXZKR","created_at":"2026-05-22T01:04:04Z"}],"graph_snapshots":[{"event_id":"sha256:097974553b21b32b482efe29c917ed8e5476bd843bdc59257831394b553e47d7","target":"graph","created_at":"2026-05-22T01:04:04Z","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":"Our results demonstrate that altering the cropping strategy can enhance model performance, especially for large-scale outdoor scenes, yielding new state-of-the-art results."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that performance differences are caused by the cropping geometry itself rather than by unstated implementation details, hyper-parameter choices, or dataset-specific effects, since the abstract provides no quantitative numbers, error bars, or ablation controls."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Gaussian and linear cropping strategies for large point clouds improve 3D neural network performance over spherical crops, especially in outdoor scenes, and achieve new state-of-the-art results."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Switching from spherical to Gaussian cropping improves 3D semantic segmentation on large outdoor point clouds."}],"snapshot_sha256":"cd458ac20be0352161feb7c969014ebc9dca981e65a79eb888d94ab65d128e07"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"67b0d271374b761b8cfcf2dc51cb6baea9836a529b8a8e8b221e9ca6bb660996"},"integrity":{"available":true,"clean":false,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T16:37:52.876924Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-20T04:01:22.719134Z","status":"completed","version":"1.0.0"},{"findings_count":4,"name":"doi_compliance","ran_at":"2026-05-19T16:40:33.038920Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.02098/integrity.json","findings":[{"audited_at":"2026-05-19T16:40:33.038920Z","detected_arxiv_id":null,"detected_doi":"10.48550/ARXIV.2205.14135.URLhttps://arxiv.org/abs/2205.14135","detector":"doi_compliance","finding_type":"recoverable_identifier","note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/ARXIV.2205.14135.URLhttps://arxiv.org/abs/2205.14135) was visible in the surrounding text but could not be confirmed against doi.org as printed.","ref_index":67,"severity":"advisory","verdict_class":"incontrovertible"},{"audited_at":"2026-05-19T16:40:33.038920Z","detected_arxiv_id":null,"detected_doi":"10.48550/arXiv.1612.00593.URLhttp://arxiv.org/abs/1612.00593","detector":"doi_compliance","finding_type":"recoverable_identifier","note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/arXiv.1612.00593.URLhttp://arxiv.org/abs/1612.00593) was visible in the surrounding text but could not be confirmed against doi.org as printed.","ref_index":1,"severity":"advisory","verdict_class":"incontrovertible"},{"audited_at":"2026-05-19T16:40:33.038920Z","detected_arxiv_id":null,"detected_doi":"10.48550/arXiv.1710.07563.URLhttp://arxiv.org/abs/1710.07563","detector":"doi_compliance","finding_type":"recoverable_identifier","note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/arXiv.1710.07563.URLhttp://arxiv.org/abs/1710.07563) was visible in the surrounding text but could not be confirmed against doi.org as printed.","ref_index":19,"severity":"advisory","verdict_class":"incontrovertible"},{"audited_at":"2026-05-19T16:40:33.038920Z","detected_arxiv_id":null,"detected_doi":"10.48550/arXiv.2206.02099.URLhttp://arxiv.org/abs/2206.02099","detector":"doi_compliance","finding_type":"recoverable_identifier","note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/arXiv.2206.02099.URLhttp://arxiv.org/abs/2206.02099) was visible in the surrounding text but could not be confirmed against doi.org as printed.","ref_index":43,"severity":"advisory","verdict_class":"incontrovertible"}],"snapshot_sha256":"d7915dc502b27e54399f3d424b4125c2fb1ae08282b5b845f91ca3f0e7577762","summary":{"advisory":4,"by_detector":{"doi_compliance":{"advisory":4,"critical":0,"informational":0,"total":4}},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale 3D point clouds can consist of hundreds of millions of points. Even after downsampling, these point clouds are too large for modern 3D neural networks. In order to develop a semantic understanding of the scene, the point clouds are divided into smaller subclouds that can be processed. Typically, this division is done using spherical crops, resulting in a loss of surrounding geometric context. To address this issue, we propose alternative methods that produce subclouds with larger crop sizes while maintaining a similar number of points. Specifically, we compare exponential, Gaussian","authors_text":"Alexander Reiterer, Dominik Merkle, Maximilian Kellner, Michael Brunklaus","cross_cats":[],"headline":"Switching from spherical to Gaussian cropping improves 3D semantic segmentation on large outdoor point clouds.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-03T23:36:32Z","title":"From Spherical to Gaussian: A Comparative Analysis of Point Cloud Cropping Strategies in Large-Scale 3D Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.02098","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-08T19:09:35.751395Z","id":"cc43951e-96d2-45aa-bd2e-88f6a6eaf826","model_set":{"reader":"grok-4.3"},"one_line_summary":"Gaussian and linear cropping strategies for large point clouds improve 3D neural network performance over spherical crops, especially in outdoor scenes, and achieve new state-of-the-art results.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Switching from spherical to Gaussian cropping improves 3D semantic segmentation on large outdoor point clouds.","strongest_claim":"Our results demonstrate that altering the cropping strategy can enhance model performance, especially for large-scale outdoor scenes, yielding new state-of-the-art results.","weakest_assumption":"The assumption that performance differences are caused by the cropping geometry itself rather than by unstated implementation details, hyper-parameter choices, or dataset-specific effects, since the abstract provides no quantitative numbers, error bars, or ablation controls."}},"verdict_id":"cc43951e-96d2-45aa-bd2e-88f6a6eaf826"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:384d9ad835b27a16bd6a0da61b6d3ca1bd04fa4763d13dc8b205b4e19b8e232e","target":"record","created_at":"2026-05-22T01:04:04Z","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":"06102f4be5b0dfa9266f12dd31df574fa0607f3ee1c7659a973659417829e15c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-03T23:36:32Z","title_canon_sha256":"beb3ea8bba97739889b7aa2f1b6c79bee32c6d061cbb517e83b22c68a8d2cd91"},"schema_version":"1.0","source":{"id":"2605.02098","kind":"arxiv","version":2}},"canonical_sha256":"41035be551a34093873686f757d7f348dce083261debaac36d1919ef28fbc778","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41035be551a34093873686f757d7f348dce083261debaac36d1919ef28fbc778","first_computed_at":"2026-05-22T01:04:04.089740Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:04:04.089740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JPntNVskHs1radDcU9dRnak+FlORlxLIYDY6XGNeI8S0lItc75t1KoAiXsPkGF7c/lD54TCa5ysbaO1DMUVkDw==","signature_status":"signed_v1","signed_at":"2026-05-22T01:04:04.090473Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.02098","source_kind":"arxiv","source_version":2}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:a8f68206735c36c5d33b8da36b41014335544724ec57d499d49d54062b84727d","sha256:ca39b1cde3409410bd02dd81c10937492286a136911cd7c7a32ee0519db0b3ff","sha256:e3579481d1070142d9fe780d2a745ec4267ab82de7f61775b39086e1d518df42","sha256:e443aa8244c18d3d91d2dbaf4ade0b7560a4ef71604fa5b84a301e0018b4ffd2"]}],"invalid_events":[],"applied_event_ids":["sha256:384d9ad835b27a16bd6a0da61b6d3ca1bd04fa4763d13dc8b205b4e19b8e232e","sha256:097974553b21b32b482efe29c917ed8e5476bd843bdc59257831394b553e47d7"],"state_sha256":"8869b78c6f3614eea490dda1446fe32d6b3020fbb67e3ce84f61e8691bd5273b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0sW2ngekwoDnwCxBU1iW0I9NkAq2zXntBRE+bAsN+X82uu0chwCBuPrYZXHwWejJFd7lxIhMfrRm66iC2CX8AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T15:23:27.877630Z","bundle_sha256":"bbbcd945314a029a16fa90feb061be9161e09d4484c7c1114a8a225fbfbc5151"}}