{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:B2IGCX6UYH3SZXPDEZSLJQQ5QT","short_pith_number":"pith:B2IGCX6U","schema_version":"1.0","canonical_sha256":"0e90615fd4c1f72cdde32664b4c21d84f511315767233d4bff9993d0fb089ead","source":{"kind":"arxiv","id":"2505.20941","version":1},"attestation_state":"computed","paper":{"title":"PMA: Towards Parameter-Efficient Point Cloud Understanding via Point Mamba Adapter","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Chen, Hang Guo, Jinpeng Wang, Ke Chen, Shu-Tao Xia, Tao Dai, Xue Yuerong, Yanzi Wang, Yaohua Zha, Zhihao Ouyang","submitted_at":"2025-05-27T09:27:16Z","abstract_excerpt":"Applying pre-trained models to assist point cloud understanding has recently become a mainstream paradigm in 3D perception. However, existing application strategies are straightforward, utilizing only the final output of the pre-trained model for various task heads. It neglects the rich complementary information in the intermediate layer, thereby failing to fully unlock the potential of pre-trained models. To overcome this limitation, we propose an orthogonal solution: Point Mamba Adapter (PMA), which constructs an ordered feature sequence from all layers of the pre-trained model and leverages"},"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":"2505.20941","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T09:27:16Z","cross_cats_sorted":[],"title_canon_sha256":"c44c90a0a1467d108b6e13774f505d489fe6150038cc8cf0b17b70ecf6c048b8","abstract_canon_sha256":"08ff24a0dcb5e70fb8c847f56fd7d21178696ee8b267d6215b781d50fb3288cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:21.357964Z","signature_b64":"Jg4vIowP62QtgpzK40XkcGn8HLj34izRNp2vgtxKMlof47xLAEmIiX0J1ddSIzwPTnH5tE/XSqs32iRcYh8oCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e90615fd4c1f72cdde32664b4c21d84f511315767233d4bff9993d0fb089ead","last_reissued_at":"2026-07-05T11:10:21.357407Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:21.357407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PMA: Towards Parameter-Efficient Point Cloud Understanding via Point Mamba Adapter","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Chen, Hang Guo, Jinpeng Wang, Ke Chen, Shu-Tao Xia, Tao Dai, Xue Yuerong, Yanzi Wang, Yaohua Zha, Zhihao Ouyang","submitted_at":"2025-05-27T09:27:16Z","abstract_excerpt":"Applying pre-trained models to assist point cloud understanding has recently become a mainstream paradigm in 3D perception. However, existing application strategies are straightforward, utilizing only the final output of the pre-trained model for various task heads. It neglects the rich complementary information in the intermediate layer, thereby failing to fully unlock the potential of pre-trained models. To overcome this limitation, we propose an orthogonal solution: Point Mamba Adapter (PMA), which constructs an ordered feature sequence from all layers of the pre-trained model and leverages"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20941","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/2505.20941/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":"2505.20941","created_at":"2026-07-05T11:10:21.357465+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20941v1","created_at":"2026-07-05T11:10:21.357465+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20941","created_at":"2026-07-05T11:10:21.357465+00:00"},{"alias_kind":"pith_short_12","alias_value":"B2IGCX6UYH3S","created_at":"2026-07-05T11:10:21.357465+00:00"},{"alias_kind":"pith_short_16","alias_value":"B2IGCX6UYH3SZXPD","created_at":"2026-07-05T11:10:21.357465+00:00"},{"alias_kind":"pith_short_8","alias_value":"B2IGCX6U","created_at":"2026-07-05T11:10:21.357465+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/B2IGCX6UYH3SZXPDEZSLJQQ5QT","json":"https://pith.science/pith/B2IGCX6UYH3SZXPDEZSLJQQ5QT.json","graph_json":"https://pith.science/api/pith-number/B2IGCX6UYH3SZXPDEZSLJQQ5QT/graph.json","events_json":"https://pith.science/api/pith-number/B2IGCX6UYH3SZXPDEZSLJQQ5QT/events.json","paper":"https://pith.science/paper/B2IGCX6U"},"agent_actions":{"view_html":"https://pith.science/pith/B2IGCX6UYH3SZXPDEZSLJQQ5QT","download_json":"https://pith.science/pith/B2IGCX6UYH3SZXPDEZSLJQQ5QT.json","view_paper":"https://pith.science/paper/B2IGCX6U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20941&json=true","fetch_graph":"https://pith.science/api/pith-number/B2IGCX6UYH3SZXPDEZSLJQQ5QT/graph.json","fetch_events":"https://pith.science/api/pith-number/B2IGCX6UYH3SZXPDEZSLJQQ5QT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B2IGCX6UYH3SZXPDEZSLJQQ5QT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B2IGCX6UYH3SZXPDEZSLJQQ5QT/action/storage_attestation","attest_author":"https://pith.science/pith/B2IGCX6UYH3SZXPDEZSLJQQ5QT/action/author_attestation","sign_citation":"https://pith.science/pith/B2IGCX6UYH3SZXPDEZSLJQQ5QT/action/citation_signature","submit_replication":"https://pith.science/pith/B2IGCX6UYH3SZXPDEZSLJQQ5QT/action/replication_record"}},"created_at":"2026-07-05T11:10:21.357465+00:00","updated_at":"2026-07-05T11:10:21.357465+00:00"}