{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IVEX35M6PIWKF4UZMXRGDMBPTA","short_pith_number":"pith:IVEX35M6","schema_version":"1.0","canonical_sha256":"45497df59e7a2ca2f29965e261b02f98351ce5c903e59498c1451818440a805c","source":{"kind":"arxiv","id":"2402.02561","version":2},"attestation_state":"computed","paper":{"title":"Foundation Model Makes Clustering A Better Initialization For Cold-Start Active Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chuan Hong, Han Yuan","submitted_at":"2024-02-04T16:27:37Z","abstract_excerpt":"Active learning selects the most informative samples from the unlabelled dataset to annotate in the context of a limited annotation budget. While numerous methods have been proposed for subsequent sample selection based on an initialized model, scant attention has been paid to the indispensable phase of active learning: selecting samples for model cold-start initialization. Most of the previous studies resort to random sampling or naive clustering. However, random sampling is prone to fluctuation, and naive clustering suffers from convergence speed, particularly when dealing with high-dimensio"},"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":"2402.02561","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-04T16:27:37Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"54ed1ff3d6491a1dcab72f2629e934b9e795f7c4cf8dd54c1db474913a68fcca","abstract_canon_sha256":"6f34045979422e4a7b392d74960f7f2293db9bc45269a170aa5c4eb7f81dfdde"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:01.496655Z","signature_b64":"NJNqSxhxlFLrO9k1waj5d0clLFRdDOXYz16zvjNgL7lIv75vGkEZKnNmYx+wddbWYCvYSngfe4okwsdLjyGZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45497df59e7a2ca2f29965e261b02f98351ce5c903e59498c1451818440a805c","last_reissued_at":"2026-07-05T08:01:01.496168Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:01.496168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Foundation Model Makes Clustering A Better Initialization For Cold-Start Active Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chuan Hong, Han Yuan","submitted_at":"2024-02-04T16:27:37Z","abstract_excerpt":"Active learning selects the most informative samples from the unlabelled dataset to annotate in the context of a limited annotation budget. While numerous methods have been proposed for subsequent sample selection based on an initialized model, scant attention has been paid to the indispensable phase of active learning: selecting samples for model cold-start initialization. Most of the previous studies resort to random sampling or naive clustering. However, random sampling is prone to fluctuation, and naive clustering suffers from convergence speed, particularly when dealing with high-dimensio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02561","kind":"arxiv","version":2},"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/2402.02561/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":"2402.02561","created_at":"2026-07-05T08:01:01.496228+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.02561v2","created_at":"2026-07-05T08:01:01.496228+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02561","created_at":"2026-07-05T08:01:01.496228+00:00"},{"alias_kind":"pith_short_12","alias_value":"IVEX35M6PIWK","created_at":"2026-07-05T08:01:01.496228+00:00"},{"alias_kind":"pith_short_16","alias_value":"IVEX35M6PIWKF4UZ","created_at":"2026-07-05T08:01:01.496228+00:00"},{"alias_kind":"pith_short_8","alias_value":"IVEX35M6","created_at":"2026-07-05T08:01:01.496228+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20765","citing_title":"Dataset-Aware Cold-Start Active Learning for Annotation-Efficient 3D Medical Image Segmentation","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IVEX35M6PIWKF4UZMXRGDMBPTA","json":"https://pith.science/pith/IVEX35M6PIWKF4UZMXRGDMBPTA.json","graph_json":"https://pith.science/api/pith-number/IVEX35M6PIWKF4UZMXRGDMBPTA/graph.json","events_json":"https://pith.science/api/pith-number/IVEX35M6PIWKF4UZMXRGDMBPTA/events.json","paper":"https://pith.science/paper/IVEX35M6"},"agent_actions":{"view_html":"https://pith.science/pith/IVEX35M6PIWKF4UZMXRGDMBPTA","download_json":"https://pith.science/pith/IVEX35M6PIWKF4UZMXRGDMBPTA.json","view_paper":"https://pith.science/paper/IVEX35M6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.02561&json=true","fetch_graph":"https://pith.science/api/pith-number/IVEX35M6PIWKF4UZMXRGDMBPTA/graph.json","fetch_events":"https://pith.science/api/pith-number/IVEX35M6PIWKF4UZMXRGDMBPTA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IVEX35M6PIWKF4UZMXRGDMBPTA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IVEX35M6PIWKF4UZMXRGDMBPTA/action/storage_attestation","attest_author":"https://pith.science/pith/IVEX35M6PIWKF4UZMXRGDMBPTA/action/author_attestation","sign_citation":"https://pith.science/pith/IVEX35M6PIWKF4UZMXRGDMBPTA/action/citation_signature","submit_replication":"https://pith.science/pith/IVEX35M6PIWKF4UZMXRGDMBPTA/action/replication_record"}},"created_at":"2026-07-05T08:01:01.496228+00:00","updated_at":"2026-07-05T08:01:01.496228+00:00"}