{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EK5TKOCEBM2FGSK34CCLAV3IW5","short_pith_number":"pith:EK5TKOCE","schema_version":"1.0","canonical_sha256":"22bb3538440b3453495be084b05768b76b3ff6aa32ba55b46b138153ad19e6fb","source":{"kind":"arxiv","id":"2307.11342","version":3},"attestation_state":"computed","paper":{"title":"Tuning Pre-trained Model via Moment Probing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingbo Zhou, Mingze Gao, Pengfei Zhu, Qilong Wang, Qinghua Hu, Zhenyi Lin","submitted_at":"2023-07-21T04:15:02Z","abstract_excerpt":"Recently, efficient fine-tuning of large-scale pre-trained models has attracted increasing research interests, where linear probing (LP) as a fundamental module is involved in exploiting the final representations for task-dependent classification. However, most of the existing methods focus on how to effectively introduce a few of learnable parameters, and little work pays attention to the commonly used LP module. In this paper, we propose a novel Moment Probing (MP) method to further explore the potential of LP. Distinguished from LP which builds a linear classification head based on the mean"},"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":"2307.11342","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-21T04:15:02Z","cross_cats_sorted":[],"title_canon_sha256":"f9ac6a4170924d6b09a39aabd00b1c06c60314d884f1a7d702b990bc907993b1","abstract_canon_sha256":"b0c243480a51307fde4d7801c8eeb80e6342ff9e084e88c4dbbf706305b5726b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:56:22.005197Z","signature_b64":"C53nZ4jw6ojvbpAtdiVNrY39imwRtKUU6bfYXHqzsZArTjCeUwgYSdXVsbgEuiUmpnMxVPw1KPknDavWqhsSBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22bb3538440b3453495be084b05768b76b3ff6aa32ba55b46b138153ad19e6fb","last_reissued_at":"2026-07-05T06:56:22.004756Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:56:22.004756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tuning Pre-trained Model via Moment Probing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingbo Zhou, Mingze Gao, Pengfei Zhu, Qilong Wang, Qinghua Hu, Zhenyi Lin","submitted_at":"2023-07-21T04:15:02Z","abstract_excerpt":"Recently, efficient fine-tuning of large-scale pre-trained models has attracted increasing research interests, where linear probing (LP) as a fundamental module is involved in exploiting the final representations for task-dependent classification. However, most of the existing methods focus on how to effectively introduce a few of learnable parameters, and little work pays attention to the commonly used LP module. In this paper, we propose a novel Moment Probing (MP) method to further explore the potential of LP. Distinguished from LP which builds a linear classification head based on the mean"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.11342","kind":"arxiv","version":3},"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/2307.11342/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":"2307.11342","created_at":"2026-07-05T06:56:22.004817+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.11342v3","created_at":"2026-07-05T06:56:22.004817+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.11342","created_at":"2026-07-05T06:56:22.004817+00:00"},{"alias_kind":"pith_short_12","alias_value":"EK5TKOCEBM2F","created_at":"2026-07-05T06:56:22.004817+00:00"},{"alias_kind":"pith_short_16","alias_value":"EK5TKOCEBM2FGSK3","created_at":"2026-07-05T06:56:22.004817+00:00"},{"alias_kind":"pith_short_8","alias_value":"EK5TKOCE","created_at":"2026-07-05T06:56:22.004817+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/EK5TKOCEBM2FGSK34CCLAV3IW5","json":"https://pith.science/pith/EK5TKOCEBM2FGSK34CCLAV3IW5.json","graph_json":"https://pith.science/api/pith-number/EK5TKOCEBM2FGSK34CCLAV3IW5/graph.json","events_json":"https://pith.science/api/pith-number/EK5TKOCEBM2FGSK34CCLAV3IW5/events.json","paper":"https://pith.science/paper/EK5TKOCE"},"agent_actions":{"view_html":"https://pith.science/pith/EK5TKOCEBM2FGSK34CCLAV3IW5","download_json":"https://pith.science/pith/EK5TKOCEBM2FGSK34CCLAV3IW5.json","view_paper":"https://pith.science/paper/EK5TKOCE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.11342&json=true","fetch_graph":"https://pith.science/api/pith-number/EK5TKOCEBM2FGSK34CCLAV3IW5/graph.json","fetch_events":"https://pith.science/api/pith-number/EK5TKOCEBM2FGSK34CCLAV3IW5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EK5TKOCEBM2FGSK34CCLAV3IW5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EK5TKOCEBM2FGSK34CCLAV3IW5/action/storage_attestation","attest_author":"https://pith.science/pith/EK5TKOCEBM2FGSK34CCLAV3IW5/action/author_attestation","sign_citation":"https://pith.science/pith/EK5TKOCEBM2FGSK34CCLAV3IW5/action/citation_signature","submit_replication":"https://pith.science/pith/EK5TKOCEBM2FGSK34CCLAV3IW5/action/replication_record"}},"created_at":"2026-07-05T06:56:22.004817+00:00","updated_at":"2026-07-05T06:56:22.004817+00:00"}