{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3KFGN57KSHYAXHQWH3EPQ5Z5EQ","short_pith_number":"pith:3KFGN57K","schema_version":"1.0","canonical_sha256":"da8a66f7ea91f00b9e163ec8f8773d242a78688d25e1649ead3ea3348813b608","source":{"kind":"arxiv","id":"2402.15823","version":1},"attestation_state":"computed","paper":{"title":"Parameter-efficient Prompt Learning for 3D Point Cloud Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deying Li, Haoran Deng, Hongyu Sun, Wang Chen, Yongcai Wang","submitted_at":"2024-02-24T14:20:50Z","abstract_excerpt":"This paper presents a parameter-efficient prompt tuning method, named PPT, to adapt a large multi-modal model for 3D point cloud understanding. Existing strategies are quite expensive in computation and storage, and depend on time-consuming prompt engineering. We address the problems from three aspects. Firstly, a PromptLearner module is devised to replace hand-crafted prompts with learnable contexts to automate the prompt tuning process. Then, we lock the pre-trained backbone instead of adopting the full fine-tuning paradigm to substantially improve the parameter efficiency. Finally, a lightw"},"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":"2402.15823","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-24T14:20:50Z","cross_cats_sorted":[],"title_canon_sha256":"75f53c284f4f3a0adfc3669994c1be714da738f7c6609b414a7a21275879e622","abstract_canon_sha256":"224e441aeb0859fa5da493944ab36d10b375569a9a33a10292781d645a89cbde"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:58.465990Z","signature_b64":"FWMod2k6poiM0dexmhMAndV3gHKqZqkwrx8oG191QlL5DErdae1WFjZK/sfxKTvNUSzgiIEkO0wMi8zhUaEACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da8a66f7ea91f00b9e163ec8f8773d242a78688d25e1649ead3ea3348813b608","last_reissued_at":"2026-07-05T07:48:58.465386Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:58.465386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parameter-efficient Prompt Learning for 3D Point Cloud Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deying Li, Haoran Deng, Hongyu Sun, Wang Chen, Yongcai Wang","submitted_at":"2024-02-24T14:20:50Z","abstract_excerpt":"This paper presents a parameter-efficient prompt tuning method, named PPT, to adapt a large multi-modal model for 3D point cloud understanding. Existing strategies are quite expensive in computation and storage, and depend on time-consuming prompt engineering. We address the problems from three aspects. Firstly, a PromptLearner module is devised to replace hand-crafted prompts with learnable contexts to automate the prompt tuning process. Then, we lock the pre-trained backbone instead of adopting the full fine-tuning paradigm to substantially improve the parameter efficiency. Finally, a lightw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15823","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/2402.15823/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":"2402.15823","created_at":"2026-07-05T07:48:58.465450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.15823v1","created_at":"2026-07-05T07:48:58.465450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15823","created_at":"2026-07-05T07:48:58.465450+00:00"},{"alias_kind":"pith_short_12","alias_value":"3KFGN57KSHYA","created_at":"2026-07-05T07:48:58.465450+00:00"},{"alias_kind":"pith_short_16","alias_value":"3KFGN57KSHYAXHQW","created_at":"2026-07-05T07:48:58.465450+00:00"},{"alias_kind":"pith_short_8","alias_value":"3KFGN57K","created_at":"2026-07-05T07:48:58.465450+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20941","citing_title":"PMA: Towards Parameter-Efficient Point Cloud Understanding via Point Mamba Adapter","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3KFGN57KSHYAXHQWH3EPQ5Z5EQ","json":"https://pith.science/pith/3KFGN57KSHYAXHQWH3EPQ5Z5EQ.json","graph_json":"https://pith.science/api/pith-number/3KFGN57KSHYAXHQWH3EPQ5Z5EQ/graph.json","events_json":"https://pith.science/api/pith-number/3KFGN57KSHYAXHQWH3EPQ5Z5EQ/events.json","paper":"https://pith.science/paper/3KFGN57K"},"agent_actions":{"view_html":"https://pith.science/pith/3KFGN57KSHYAXHQWH3EPQ5Z5EQ","download_json":"https://pith.science/pith/3KFGN57KSHYAXHQWH3EPQ5Z5EQ.json","view_paper":"https://pith.science/paper/3KFGN57K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.15823&json=true","fetch_graph":"https://pith.science/api/pith-number/3KFGN57KSHYAXHQWH3EPQ5Z5EQ/graph.json","fetch_events":"https://pith.science/api/pith-number/3KFGN57KSHYAXHQWH3EPQ5Z5EQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3KFGN57KSHYAXHQWH3EPQ5Z5EQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3KFGN57KSHYAXHQWH3EPQ5Z5EQ/action/storage_attestation","attest_author":"https://pith.science/pith/3KFGN57KSHYAXHQWH3EPQ5Z5EQ/action/author_attestation","sign_citation":"https://pith.science/pith/3KFGN57KSHYAXHQWH3EPQ5Z5EQ/action/citation_signature","submit_replication":"https://pith.science/pith/3KFGN57KSHYAXHQWH3EPQ5Z5EQ/action/replication_record"}},"created_at":"2026-07-05T07:48:58.465450+00:00","updated_at":"2026-07-05T07:48:58.465450+00:00"}