{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VX4GQBI3C45JPCNCOC7UHE7QAK","short_pith_number":"pith:VX4GQBI3","schema_version":"1.0","canonical_sha256":"adf868051b173a9789a270bf4393f002b691bae85d150403a28848ddc47aacf1","source":{"kind":"arxiv","id":"2607.19711","version":1},"attestation_state":"computed","paper":{"title":"Point-Selection Fine-Tuning Framework for Robust Point Cloud Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Ma, Da Li, Dongfu Yin","submitted_at":"2026-07-22T03:27:18Z","abstract_excerpt":"Noisy and corrupted points can substantially degrade point cloud recognition performance, especially under challenging corruption settings. In particular, full fine-tuning of 3D pre-trained models may amplify the influence of outliers and overwrite robustness priors learned during pre-training, while naive parameter-efficient adaptation remains sensitive to corrupted tokens. To address this issue, we propose PSFT, a point-selection fine-tuning framework that improves robustness while remaining parameter-efficient. PSFT first estimates point-wise influence from pre-pooling features and adaptive"},"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":"2607.19711","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-22T03:27:18Z","cross_cats_sorted":[],"title_canon_sha256":"77d84aed8de22f626207757cfc57cd923b7d5503830066199b9a56d19d79033e","abstract_canon_sha256":"6b69797254d234af693396fcd4598ba9d81838682896d3812b3a99a4831195c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-23T00:24:05.011227Z","signature_b64":"ZCW97mY1NScLfxFWTSWnUhKH4ESGd+eM6NOWkTbq7nSGrX+ar/o/OWf+OO+SWgxJcF5HOj5a5F258Rnl4bEBDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"adf868051b173a9789a270bf4393f002b691bae85d150403a28848ddc47aacf1","last_reissued_at":"2026-07-23T00:24:05.010391Z","signature_status":"signed_v1","first_computed_at":"2026-07-23T00:24:05.010391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Point-Selection Fine-Tuning Framework for Robust Point Cloud Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Ma, Da Li, Dongfu Yin","submitted_at":"2026-07-22T03:27:18Z","abstract_excerpt":"Noisy and corrupted points can substantially degrade point cloud recognition performance, especially under challenging corruption settings. In particular, full fine-tuning of 3D pre-trained models may amplify the influence of outliers and overwrite robustness priors learned during pre-training, while naive parameter-efficient adaptation remains sensitive to corrupted tokens. To address this issue, we propose PSFT, a point-selection fine-tuning framework that improves robustness while remaining parameter-efficient. PSFT first estimates point-wise influence from pre-pooling features and adaptive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19711","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/2607.19711/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":"2607.19711","created_at":"2026-07-23T00:24:05.010835+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.19711v1","created_at":"2026-07-23T00:24:05.010835+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19711","created_at":"2026-07-23T00:24:05.010835+00:00"},{"alias_kind":"pith_short_12","alias_value":"VX4GQBI3C45J","created_at":"2026-07-23T00:24:05.010835+00:00"},{"alias_kind":"pith_short_16","alias_value":"VX4GQBI3C45JPCNC","created_at":"2026-07-23T00:24:05.010835+00:00"},{"alias_kind":"pith_short_8","alias_value":"VX4GQBI3","created_at":"2026-07-23T00:24:05.010835+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VX4GQBI3C45JPCNCOC7UHE7QAK","json":"https://pith.science/pith/VX4GQBI3C45JPCNCOC7UHE7QAK.json","graph_json":"https://pith.science/api/pith-number/VX4GQBI3C45JPCNCOC7UHE7QAK/graph.json","events_json":"https://pith.science/api/pith-number/VX4GQBI3C45JPCNCOC7UHE7QAK/events.json","paper":"https://pith.science/paper/VX4GQBI3"},"agent_actions":{"view_html":"https://pith.science/pith/VX4GQBI3C45JPCNCOC7UHE7QAK","download_json":"https://pith.science/pith/VX4GQBI3C45JPCNCOC7UHE7QAK.json","view_paper":"https://pith.science/paper/VX4GQBI3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.19711&json=true","fetch_graph":"https://pith.science/api/pith-number/VX4GQBI3C45JPCNCOC7UHE7QAK/graph.json","fetch_events":"https://pith.science/api/pith-number/VX4GQBI3C45JPCNCOC7UHE7QAK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VX4GQBI3C45JPCNCOC7UHE7QAK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VX4GQBI3C45JPCNCOC7UHE7QAK/action/storage_attestation","attest_author":"https://pith.science/pith/VX4GQBI3C45JPCNCOC7UHE7QAK/action/author_attestation","sign_citation":"https://pith.science/pith/VX4GQBI3C45JPCNCOC7UHE7QAK/action/citation_signature","submit_replication":"https://pith.science/pith/VX4GQBI3C45JPCNCOC7UHE7QAK/action/replication_record"}},"created_at":"2026-07-23T00:24:05.010835+00:00","updated_at":"2026-07-23T00:24:05.010835+00:00"}