{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:K2NSINCV5NBY7EXCZT5N5GTRPX","short_pith_number":"pith:K2NSINCV","schema_version":"1.0","canonical_sha256":"569b243455eb438f92e2ccfade9a717dc42e79b6995780415230ceb6e6624631","source":{"kind":"arxiv","id":"2007.04525","version":1},"attestation_state":"computed","paper":{"title":"PointMask: Towards Interpretable and Bias-Resilient Point Cloud Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Amir Hosein Khasahmadi, Kaveh Hassani, Pradeep Kumar Jayaraman, Saeid Asgari Taghanaki, Tonya Custis","submitted_at":"2020-07-09T03:06:06Z","abstract_excerpt":"Deep classifiers tend to associate a few discriminative input variables with their objective function, which in turn, may hurt their generalization capabilities. To address this, one can design systematic experiments and/or inspect the models via interpretability methods. In this paper, we investigate both of these strategies on deep models operating on point clouds. We propose PointMask, a model-agnostic interpretable information-bottleneck approach for attribution in point cloud models. PointMask encourages exploring the majority of variation factors in the input space while gradually conver"},"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":"2007.04525","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-09T03:06:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9437b6a2f2b1d7e4c39c82e23d93397f5bc8e0454d3aaa184faa8ba4dcc30a80","abstract_canon_sha256":"143388cf40f4b4f9d9703f7b5e75574d5f66fa98b110f39ab439caa02964528c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:17:30.969203Z","signature_b64":"bkFYU2oziylFRm3xEmRjQSEvCjmal/6w1EnuWQYBF849a7u0lWJBtbHXwRdJ20jw7aDdGgM2G+pHEKpcb/D2CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"569b243455eb438f92e2ccfade9a717dc42e79b6995780415230ceb6e6624631","last_reissued_at":"2026-07-05T01:17:30.968841Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:17:30.968841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PointMask: Towards Interpretable and Bias-Resilient Point Cloud Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Amir Hosein Khasahmadi, Kaveh Hassani, Pradeep Kumar Jayaraman, Saeid Asgari Taghanaki, Tonya Custis","submitted_at":"2020-07-09T03:06:06Z","abstract_excerpt":"Deep classifiers tend to associate a few discriminative input variables with their objective function, which in turn, may hurt their generalization capabilities. To address this, one can design systematic experiments and/or inspect the models via interpretability methods. In this paper, we investigate both of these strategies on deep models operating on point clouds. We propose PointMask, a model-agnostic interpretable information-bottleneck approach for attribution in point cloud models. PointMask encourages exploring the majority of variation factors in the input space while gradually conver"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.04525","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2007.04525/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":"2007.04525","created_at":"2026-07-05T01:17:30.968896+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.04525v1","created_at":"2026-07-05T01:17:30.968896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.04525","created_at":"2026-07-05T01:17:30.968896+00:00"},{"alias_kind":"pith_short_12","alias_value":"K2NSINCV5NBY","created_at":"2026-07-05T01:17:30.968896+00:00"},{"alias_kind":"pith_short_16","alias_value":"K2NSINCV5NBY7EXC","created_at":"2026-07-05T01:17:30.968896+00:00"},{"alias_kind":"pith_short_8","alias_value":"K2NSINCV","created_at":"2026-07-05T01:17:30.968896+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":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K2NSINCV5NBY7EXCZT5N5GTRPX","json":"https://pith.science/pith/K2NSINCV5NBY7EXCZT5N5GTRPX.json","graph_json":"https://pith.science/api/pith-number/K2NSINCV5NBY7EXCZT5N5GTRPX/graph.json","events_json":"https://pith.science/api/pith-number/K2NSINCV5NBY7EXCZT5N5GTRPX/events.json","paper":"https://pith.science/paper/K2NSINCV"},"agent_actions":{"view_html":"https://pith.science/pith/K2NSINCV5NBY7EXCZT5N5GTRPX","download_json":"https://pith.science/pith/K2NSINCV5NBY7EXCZT5N5GTRPX.json","view_paper":"https://pith.science/paper/K2NSINCV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.04525&json=true","fetch_graph":"https://pith.science/api/pith-number/K2NSINCV5NBY7EXCZT5N5GTRPX/graph.json","fetch_events":"https://pith.science/api/pith-number/K2NSINCV5NBY7EXCZT5N5GTRPX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K2NSINCV5NBY7EXCZT5N5GTRPX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K2NSINCV5NBY7EXCZT5N5GTRPX/action/storage_attestation","attest_author":"https://pith.science/pith/K2NSINCV5NBY7EXCZT5N5GTRPX/action/author_attestation","sign_citation":"https://pith.science/pith/K2NSINCV5NBY7EXCZT5N5GTRPX/action/citation_signature","submit_replication":"https://pith.science/pith/K2NSINCV5NBY7EXCZT5N5GTRPX/action/replication_record"}},"created_at":"2026-07-05T01:17:30.968896+00:00","updated_at":"2026-07-05T01:17:30.968896+00:00"}