{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZP4Q5JOSFJ7TJECXG3K4MIUVP6","short_pith_number":"pith:ZP4Q5JOS","schema_version":"1.0","canonical_sha256":"cbf90ea5d22a7f34905736d5c622957fa96775c6c2c4b919c23b54d03c34e514","source":{"kind":"arxiv","id":"2505.19546","version":1},"attestation_state":"computed","paper":{"title":"SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Clouds","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Bahri, Christian Desrosiers, David Osowiechi, Farzad Beizaee, Gustavo Adolfo Vargas Hakim, Ismail Ben Ayed, Mehrdad Noori, Moslem Yazdanpanah, Sahar Dastani","submitted_at":"2025-05-26T06:11:02Z","abstract_excerpt":"Test-Time Training (TTT) has emerged as a promising solution to address distribution shifts in 3D point cloud classification. However, existing methods often rely on computationally expensive backpropagation during adaptation, limiting their applicability in real-world, time-sensitive scenarios. In this paper, we introduce SMART-PC, a skeleton-based framework that enhances resilience to corruptions by leveraging the geometric structure of 3D point clouds. During pre-training, our method predicts skeletal representations, enabling the model to extract robust and meaningful geometric features th"},"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":"2505.19546","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T06:11:02Z","cross_cats_sorted":[],"title_canon_sha256":"da6ec38f995c03d50252d07923ee8c36ed55c9121960b734048179450bf5415c","abstract_canon_sha256":"fe8c744fb28f661d133ebf1863b57b8fc19f6d34416497d5ea4bd6c36e6536bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:32.239684Z","signature_b64":"an74y/LGEAVbxvLiVC1Y1ekYEG7O69uBT7B2SWqByCP2X1UnApAlXQFxGzRGHO8G7FT9O4qWUdEP2Yb87V1iCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbf90ea5d22a7f34905736d5c622957fa96775c6c2c4b919c23b54d03c34e514","last_reissued_at":"2026-07-05T11:09:32.239203Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:32.239203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Clouds","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Bahri, Christian Desrosiers, David Osowiechi, Farzad Beizaee, Gustavo Adolfo Vargas Hakim, Ismail Ben Ayed, Mehrdad Noori, Moslem Yazdanpanah, Sahar Dastani","submitted_at":"2025-05-26T06:11:02Z","abstract_excerpt":"Test-Time Training (TTT) has emerged as a promising solution to address distribution shifts in 3D point cloud classification. However, existing methods often rely on computationally expensive backpropagation during adaptation, limiting their applicability in real-world, time-sensitive scenarios. In this paper, we introduce SMART-PC, a skeleton-based framework that enhances resilience to corruptions by leveraging the geometric structure of 3D point clouds. During pre-training, our method predicts skeletal representations, enabling the model to extract robust and meaningful geometric features th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19546","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/2505.19546/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":"2505.19546","created_at":"2026-07-05T11:09:32.239264+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19546v1","created_at":"2026-07-05T11:09:32.239264+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19546","created_at":"2026-07-05T11:09:32.239264+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZP4Q5JOSFJ7T","created_at":"2026-07-05T11:09:32.239264+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZP4Q5JOSFJ7TJECX","created_at":"2026-07-05T11:09:32.239264+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZP4Q5JOS","created_at":"2026-07-05T11:09:32.239264+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12939","citing_title":"MAMVI: 3D Test-Time Adaptation via Masked Multi-View Point Clouds","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22813","citing_title":"TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZP4Q5JOSFJ7TJECXG3K4MIUVP6","json":"https://pith.science/pith/ZP4Q5JOSFJ7TJECXG3K4MIUVP6.json","graph_json":"https://pith.science/api/pith-number/ZP4Q5JOSFJ7TJECXG3K4MIUVP6/graph.json","events_json":"https://pith.science/api/pith-number/ZP4Q5JOSFJ7TJECXG3K4MIUVP6/events.json","paper":"https://pith.science/paper/ZP4Q5JOS"},"agent_actions":{"view_html":"https://pith.science/pith/ZP4Q5JOSFJ7TJECXG3K4MIUVP6","download_json":"https://pith.science/pith/ZP4Q5JOSFJ7TJECXG3K4MIUVP6.json","view_paper":"https://pith.science/paper/ZP4Q5JOS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19546&json=true","fetch_graph":"https://pith.science/api/pith-number/ZP4Q5JOSFJ7TJECXG3K4MIUVP6/graph.json","fetch_events":"https://pith.science/api/pith-number/ZP4Q5JOSFJ7TJECXG3K4MIUVP6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZP4Q5JOSFJ7TJECXG3K4MIUVP6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZP4Q5JOSFJ7TJECXG3K4MIUVP6/action/storage_attestation","attest_author":"https://pith.science/pith/ZP4Q5JOSFJ7TJECXG3K4MIUVP6/action/author_attestation","sign_citation":"https://pith.science/pith/ZP4Q5JOSFJ7TJECXG3K4MIUVP6/action/citation_signature","submit_replication":"https://pith.science/pith/ZP4Q5JOSFJ7TJECXG3K4MIUVP6/action/replication_record"}},"created_at":"2026-07-05T11:09:32.239264+00:00","updated_at":"2026-07-05T11:09:32.239264+00:00"}