{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LJTLIZYTDT3P2W7CSSFSTDJVST","short_pith_number":"pith:LJTLIZYT","schema_version":"1.0","canonical_sha256":"5a66b467131cf6fd5be2948b298d3594d40230926b87be5adff3cbaffc81028d","source":{"kind":"arxiv","id":"2111.03549","version":1},"attestation_state":"computed","paper":{"title":"Interpreting Representation Quality of DNNs for 3D Point Cloud Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dongrui Liu, Qihan Ren, Quanshi Zhang, Wen Shen","submitted_at":"2021-11-05T15:14:34Z","abstract_excerpt":"In this paper, we evaluate the quality of knowledge representations encoded in deep neural networks (DNNs) for 3D point cloud processing. We propose a method to disentangle the overall model vulnerability into the sensitivity to the rotation, the translation, the scale, and local 3D structures. Besides, we also propose metrics to evaluate the spatial smoothness of encoding 3D structures, and the representation complexity of the DNN. Based on such analysis, experiments expose representation problems with classic DNNs, and explain the utility of the adversarial training."},"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":"2111.03549","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-05T15:14:34Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d9c183741bf31a6f6c21ff87bdc5d671088ba51b9018ad1fe4a85fd1d9644c73","abstract_canon_sha256":"e83b2300eb2638d906cd8f7b0f7646d853f0d01c1ccd821f8fcdebecde566033"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:29:25.734866Z","signature_b64":"QPtNxbZLeQZlQ3ZvQ/mvhaK4ZHYTWPvQMc/LhdN1VINOrImyGy2MALsntviJmmOSHs4dmA4Ls5gMgNzm6hqaDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a66b467131cf6fd5be2948b298d3594d40230926b87be5adff3cbaffc81028d","last_reissued_at":"2026-07-05T03:29:25.734396Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:29:25.734396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpreting Representation Quality of DNNs for 3D Point Cloud Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dongrui Liu, Qihan Ren, Quanshi Zhang, Wen Shen","submitted_at":"2021-11-05T15:14:34Z","abstract_excerpt":"In this paper, we evaluate the quality of knowledge representations encoded in deep neural networks (DNNs) for 3D point cloud processing. We propose a method to disentangle the overall model vulnerability into the sensitivity to the rotation, the translation, the scale, and local 3D structures. Besides, we also propose metrics to evaluate the spatial smoothness of encoding 3D structures, and the representation complexity of the DNN. Based on such analysis, experiments expose representation problems with classic DNNs, and explain the utility of the adversarial training."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.03549","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/2111.03549/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":"2111.03549","created_at":"2026-07-05T03:29:25.734454+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.03549v1","created_at":"2026-07-05T03:29:25.734454+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.03549","created_at":"2026-07-05T03:29:25.734454+00:00"},{"alias_kind":"pith_short_12","alias_value":"LJTLIZYTDT3P","created_at":"2026-07-05T03:29:25.734454+00:00"},{"alias_kind":"pith_short_16","alias_value":"LJTLIZYTDT3P2W7C","created_at":"2026-07-05T03:29:25.734454+00:00"},{"alias_kind":"pith_short_8","alias_value":"LJTLIZYT","created_at":"2026-07-05T03:29:25.734454+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":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LJTLIZYTDT3P2W7CSSFSTDJVST","json":"https://pith.science/pith/LJTLIZYTDT3P2W7CSSFSTDJVST.json","graph_json":"https://pith.science/api/pith-number/LJTLIZYTDT3P2W7CSSFSTDJVST/graph.json","events_json":"https://pith.science/api/pith-number/LJTLIZYTDT3P2W7CSSFSTDJVST/events.json","paper":"https://pith.science/paper/LJTLIZYT"},"agent_actions":{"view_html":"https://pith.science/pith/LJTLIZYTDT3P2W7CSSFSTDJVST","download_json":"https://pith.science/pith/LJTLIZYTDT3P2W7CSSFSTDJVST.json","view_paper":"https://pith.science/paper/LJTLIZYT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.03549&json=true","fetch_graph":"https://pith.science/api/pith-number/LJTLIZYTDT3P2W7CSSFSTDJVST/graph.json","fetch_events":"https://pith.science/api/pith-number/LJTLIZYTDT3P2W7CSSFSTDJVST/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LJTLIZYTDT3P2W7CSSFSTDJVST/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LJTLIZYTDT3P2W7CSSFSTDJVST/action/storage_attestation","attest_author":"https://pith.science/pith/LJTLIZYTDT3P2W7CSSFSTDJVST/action/author_attestation","sign_citation":"https://pith.science/pith/LJTLIZYTDT3P2W7CSSFSTDJVST/action/citation_signature","submit_replication":"https://pith.science/pith/LJTLIZYTDT3P2W7CSSFSTDJVST/action/replication_record"}},"created_at":"2026-07-05T03:29:25.734454+00:00","updated_at":"2026-07-05T03:29:25.734454+00:00"}