{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CPQGYZJUWKNBY5WVA5J6E6C2CX","short_pith_number":"pith:CPQGYZJU","schema_version":"1.0","canonical_sha256":"13e06c6534b29a1c76d50753e2785a15eb279f5a8f17b7f5d29b0fb4a4149180","source":{"kind":"arxiv","id":"2507.14559","version":1},"attestation_state":"computed","paper":{"title":"LEAD: Exploring Logit Space Evolution for Model Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jun Liu, Ling-Yu Duan, Shixiang Tang, Xiaotong Li, Yichun Hu, Zixuan Hu","submitted_at":"2025-07-19T09:45:17Z","abstract_excerpt":"The remarkable success of pretrain-then-finetune paradigm has led to a proliferation of available pre-trained models for vision tasks. This surge presents a significant challenge in efficiently choosing the most suitable pre-trained models for downstream tasks. The critical aspect of this challenge lies in effectively predicting the model transferability by considering the underlying fine-tuning dynamics. Existing methods often model fine-tuning dynamics in feature space with linear transformations, which do not precisely align with the fine-tuning objective and fail to grasp the essential non"},"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":"2507.14559","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-19T09:45:17Z","cross_cats_sorted":[],"title_canon_sha256":"2dabfb5b18117a22d4aa09dbd5014b24dc012cdb92b44b55b8da57bc34919226","abstract_canon_sha256":"b86a7f10d9ee5d8bb925e37b6eddcdb14df16d4d1abc9d14932fb06d41942264"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:09.503910Z","signature_b64":"tLdf9rBAMkH1t2Xe1nHMuhRQ2RnSmjG4rIRRpeGExUoBpsQTjLQgRWhabdJdvsrdoNYIb2T4NR1pXRf10TJpCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13e06c6534b29a1c76d50753e2785a15eb279f5a8f17b7f5d29b0fb4a4149180","last_reissued_at":"2026-07-05T11:40:09.503456Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:09.503456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LEAD: Exploring Logit Space Evolution for Model Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jun Liu, Ling-Yu Duan, Shixiang Tang, Xiaotong Li, Yichun Hu, Zixuan Hu","submitted_at":"2025-07-19T09:45:17Z","abstract_excerpt":"The remarkable success of pretrain-then-finetune paradigm has led to a proliferation of available pre-trained models for vision tasks. This surge presents a significant challenge in efficiently choosing the most suitable pre-trained models for downstream tasks. The critical aspect of this challenge lies in effectively predicting the model transferability by considering the underlying fine-tuning dynamics. Existing methods often model fine-tuning dynamics in feature space with linear transformations, which do not precisely align with the fine-tuning objective and fail to grasp the essential non"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14559","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/2507.14559/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":"2507.14559","created_at":"2026-07-05T11:40:09.503514+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.14559v1","created_at":"2026-07-05T11:40:09.503514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14559","created_at":"2026-07-05T11:40:09.503514+00:00"},{"alias_kind":"pith_short_12","alias_value":"CPQGYZJUWKNB","created_at":"2026-07-05T11:40:09.503514+00:00"},{"alias_kind":"pith_short_16","alias_value":"CPQGYZJUWKNBY5WV","created_at":"2026-07-05T11:40:09.503514+00:00"},{"alias_kind":"pith_short_8","alias_value":"CPQGYZJU","created_at":"2026-07-05T11:40:09.503514+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/CPQGYZJUWKNBY5WVA5J6E6C2CX","json":"https://pith.science/pith/CPQGYZJUWKNBY5WVA5J6E6C2CX.json","graph_json":"https://pith.science/api/pith-number/CPQGYZJUWKNBY5WVA5J6E6C2CX/graph.json","events_json":"https://pith.science/api/pith-number/CPQGYZJUWKNBY5WVA5J6E6C2CX/events.json","paper":"https://pith.science/paper/CPQGYZJU"},"agent_actions":{"view_html":"https://pith.science/pith/CPQGYZJUWKNBY5WVA5J6E6C2CX","download_json":"https://pith.science/pith/CPQGYZJUWKNBY5WVA5J6E6C2CX.json","view_paper":"https://pith.science/paper/CPQGYZJU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.14559&json=true","fetch_graph":"https://pith.science/api/pith-number/CPQGYZJUWKNBY5WVA5J6E6C2CX/graph.json","fetch_events":"https://pith.science/api/pith-number/CPQGYZJUWKNBY5WVA5J6E6C2CX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CPQGYZJUWKNBY5WVA5J6E6C2CX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CPQGYZJUWKNBY5WVA5J6E6C2CX/action/storage_attestation","attest_author":"https://pith.science/pith/CPQGYZJUWKNBY5WVA5J6E6C2CX/action/author_attestation","sign_citation":"https://pith.science/pith/CPQGYZJUWKNBY5WVA5J6E6C2CX/action/citation_signature","submit_replication":"https://pith.science/pith/CPQGYZJUWKNBY5WVA5J6E6C2CX/action/replication_record"}},"created_at":"2026-07-05T11:40:09.503514+00:00","updated_at":"2026-07-05T11:40:09.503514+00:00"}