{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H7WWLXUPWPUWV5GBZOKNOU3BED","short_pith_number":"pith:H7WWLXUP","schema_version":"1.0","canonical_sha256":"3fed65de8fb3e96af4c1cb94d7536120f85b505416b5070ce902cda7e3a3bc7b","source":{"kind":"arxiv","id":"2412.19085","version":2},"attestation_state":"computed","paper":{"title":"Assessing Pre-Trained Models for Transfer Learning Through Distribution of Spectral Components","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bin Yang, Chenjuan Guo, Tengxue Zhang, Xinyang Chen, Yang Shu, Yifei Long","submitted_at":"2024-12-26T06:54:22Z","abstract_excerpt":"Pre-trained model assessment for transfer learning aims to identify the optimal candidate for the downstream tasks from a model hub, without the need of time-consuming fine-tuning. Existing advanced works mainly focus on analyzing the intrinsic characteristics of the entire features extracted by each pre-trained model or how well such features fit the target labels. This paper proposes a novel perspective for pre-trained model assessment through the Distribution of Spectral Components (DISCO). Through singular value decomposition of features extracted from pre-trained models, we investigate di"},"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":"2412.19085","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-26T06:54:22Z","cross_cats_sorted":[],"title_canon_sha256":"fcababa34bc627653cd5847cacc3258619d65b5fb6c922a2bb432fe3b1ea54e2","abstract_canon_sha256":"750230335a787c5433cdd1883ec4fd95d129d02554704a3851a878eb7aa60a51"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:15.788769Z","signature_b64":"/bJKxx85aKiRy54CcW4Vm5UuIf1Kn1AVn2cMqQnytKYLEaZFe7w0VFhHfAhUPh2ripJQTH+JgMcXaB0resPJCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fed65de8fb3e96af4c1cb94d7536120f85b505416b5070ce902cda7e3a3bc7b","last_reissued_at":"2026-07-05T10:25:15.788248Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:15.788248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assessing Pre-Trained Models for Transfer Learning Through Distribution of Spectral Components","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bin Yang, Chenjuan Guo, Tengxue Zhang, Xinyang Chen, Yang Shu, Yifei Long","submitted_at":"2024-12-26T06:54:22Z","abstract_excerpt":"Pre-trained model assessment for transfer learning aims to identify the optimal candidate for the downstream tasks from a model hub, without the need of time-consuming fine-tuning. Existing advanced works mainly focus on analyzing the intrinsic characteristics of the entire features extracted by each pre-trained model or how well such features fit the target labels. This paper proposes a novel perspective for pre-trained model assessment through the Distribution of Spectral Components (DISCO). Through singular value decomposition of features extracted from pre-trained models, we investigate di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19085","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/2412.19085/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":"2412.19085","created_at":"2026-07-05T10:25:15.788297+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.19085v2","created_at":"2026-07-05T10:25:15.788297+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19085","created_at":"2026-07-05T10:25:15.788297+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7WWLXUPWPUW","created_at":"2026-07-05T10:25:15.788297+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7WWLXUPWPUWV5GB","created_at":"2026-07-05T10:25:15.788297+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7WWLXUP","created_at":"2026-07-05T10:25:15.788297+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/H7WWLXUPWPUWV5GBZOKNOU3BED","json":"https://pith.science/pith/H7WWLXUPWPUWV5GBZOKNOU3BED.json","graph_json":"https://pith.science/api/pith-number/H7WWLXUPWPUWV5GBZOKNOU3BED/graph.json","events_json":"https://pith.science/api/pith-number/H7WWLXUPWPUWV5GBZOKNOU3BED/events.json","paper":"https://pith.science/paper/H7WWLXUP"},"agent_actions":{"view_html":"https://pith.science/pith/H7WWLXUPWPUWV5GBZOKNOU3BED","download_json":"https://pith.science/pith/H7WWLXUPWPUWV5GBZOKNOU3BED.json","view_paper":"https://pith.science/paper/H7WWLXUP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.19085&json=true","fetch_graph":"https://pith.science/api/pith-number/H7WWLXUPWPUWV5GBZOKNOU3BED/graph.json","fetch_events":"https://pith.science/api/pith-number/H7WWLXUPWPUWV5GBZOKNOU3BED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7WWLXUPWPUWV5GBZOKNOU3BED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7WWLXUPWPUWV5GBZOKNOU3BED/action/storage_attestation","attest_author":"https://pith.science/pith/H7WWLXUPWPUWV5GBZOKNOU3BED/action/author_attestation","sign_citation":"https://pith.science/pith/H7WWLXUPWPUWV5GBZOKNOU3BED/action/citation_signature","submit_replication":"https://pith.science/pith/H7WWLXUPWPUWV5GBZOKNOU3BED/action/replication_record"}},"created_at":"2026-07-05T10:25:15.788297+00:00","updated_at":"2026-07-05T10:25:15.788297+00:00"}