{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:MCMNXD4BU7KQA6HUBBNJC4REMC","short_pith_number":"pith:MCMNXD4B","schema_version":"1.0","canonical_sha256":"6098db8f81a7d50078f4085a91722460839ce5f0c622d05a4e17c29d4eb3ea86","source":{"kind":"arxiv","id":"1812.01687","version":6},"attestation_state":"computed","paper":{"title":"PointCloud Saliency Maps","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Li, Changyou Chen, Junsong Yuan, Kui Ren, Tianhang Zheng","submitted_at":"2018-11-28T21:50:49Z","abstract_excerpt":"3D point-cloud recognition with PointNet and its variants has received remarkable progress. A missing ingredient, however, is the ability to automatically evaluate point-wise importance w.r.t.\\! classification performance, which is usually reflected by a saliency map. A saliency map is an important tool as it allows one to perform further processes on point-cloud data. In this paper, we propose a novel way of characterizing critical points and segments to build point-cloud saliency maps. Our method assigns each point a score reflecting its contribution to the model-recognition loss. The salien"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1812.01687","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-28T21:50:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"28083f92842ff46143f5f6c47eaaa4be82a3bd5bea7fe7d476ab637d491d8393","abstract_canon_sha256":"b666d0f078da84bb4380622324f0d75c1d8b98ac07078d8ed102be0563193153"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:04:26.621905Z","signature_b64":"B4u/yGwyZJmejhxfKl+F1l3n+pLpTw5hpaQvLp+BCL+AT7AIUhmYZLg1mpQtAg6eOTU5mBP8BttNlTop5XdHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6098db8f81a7d50078f4085a91722460839ce5f0c622d05a4e17c29d4eb3ea86","last_reissued_at":"2026-07-05T00:04:26.621411Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:04:26.621411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PointCloud Saliency Maps","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Li, Changyou Chen, Junsong Yuan, Kui Ren, Tianhang Zheng","submitted_at":"2018-11-28T21:50:49Z","abstract_excerpt":"3D point-cloud recognition with PointNet and its variants has received remarkable progress. A missing ingredient, however, is the ability to automatically evaluate point-wise importance w.r.t.\\! classification performance, which is usually reflected by a saliency map. A saliency map is an important tool as it allows one to perform further processes on point-cloud data. In this paper, we propose a novel way of characterizing critical points and segments to build point-cloud saliency maps. Our method assigns each point a score reflecting its contribution to the model-recognition loss. The salien"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.01687","kind":"arxiv","version":6},"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/1812.01687/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1812.01687","created_at":"2026-07-05T00:04:26.621476+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.01687v6","created_at":"2026-07-05T00:04:26.621476+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.01687","created_at":"2026-07-05T00:04:26.621476+00:00"},{"alias_kind":"pith_short_12","alias_value":"MCMNXD4BU7KQ","created_at":"2026-07-05T00:04:26.621476+00:00"},{"alias_kind":"pith_short_16","alias_value":"MCMNXD4BU7KQA6HU","created_at":"2026-07-05T00:04:26.621476+00:00"},{"alias_kind":"pith_short_8","alias_value":"MCMNXD4B","created_at":"2026-07-05T00:04:26.621476+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22020","citing_title":"XAI for Point Cloud Data using Perturbations based on Meaningful Segmentation","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MCMNXD4BU7KQA6HUBBNJC4REMC","json":"https://pith.science/pith/MCMNXD4BU7KQA6HUBBNJC4REMC.json","graph_json":"https://pith.science/api/pith-number/MCMNXD4BU7KQA6HUBBNJC4REMC/graph.json","events_json":"https://pith.science/api/pith-number/MCMNXD4BU7KQA6HUBBNJC4REMC/events.json","paper":"https://pith.science/paper/MCMNXD4B"},"agent_actions":{"view_html":"https://pith.science/pith/MCMNXD4BU7KQA6HUBBNJC4REMC","download_json":"https://pith.science/pith/MCMNXD4BU7KQA6HUBBNJC4REMC.json","view_paper":"https://pith.science/paper/MCMNXD4B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.01687&json=true","fetch_graph":"https://pith.science/api/pith-number/MCMNXD4BU7KQA6HUBBNJC4REMC/graph.json","fetch_events":"https://pith.science/api/pith-number/MCMNXD4BU7KQA6HUBBNJC4REMC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MCMNXD4BU7KQA6HUBBNJC4REMC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MCMNXD4BU7KQA6HUBBNJC4REMC/action/storage_attestation","attest_author":"https://pith.science/pith/MCMNXD4BU7KQA6HUBBNJC4REMC/action/author_attestation","sign_citation":"https://pith.science/pith/MCMNXD4BU7KQA6HUBBNJC4REMC/action/citation_signature","submit_replication":"https://pith.science/pith/MCMNXD4BU7KQA6HUBBNJC4REMC/action/replication_record"}},"created_at":"2026-07-05T00:04:26.621476+00:00","updated_at":"2026-07-05T00:04:26.621476+00:00"}