{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:COTOANRF2M63HCW6THEPSA3R43","short_pith_number":"pith:COTOANRF","schema_version":"1.0","canonical_sha256":"13a6e03625d33db38ade99c8f90371e6d8528689908a706335f3f906c7fcfa4a","source":{"kind":"arxiv","id":"2606.10196","version":1},"attestation_state":"computed","paper":{"title":"Fisher-Guided Progressive Parameter Selection for Adaptive Fine-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ghodsiyeh Rostami, Mahdi S. Hosseini, Po-Han Chen","submitted_at":"2026-06-08T21:35:11Z","abstract_excerpt":"Parameter-efficient fine-tuning (PEFT) aims to adapt pretrained models with a small trainable parameter subset, however, most existing methods choose this subset from fixed architectural heuristics rather than using dynamic, task-aware criteria. We introduce \\textbf{FisherAdapTune}, a Fisher-guided Adaptive Fine-Tuning framework that progressively selects parameter groups by tracking the temporal drift of their Fisher geometry. Starting from a PAC-Bayesian view of fine-tuning, we decompose the generalization error bound into Fisher-weighted update costs and show that parameter groups whose cur"},"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":"2606.10196","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-08T21:35:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a0ccc56cb37c174ffe8164538aeee115bbd1e818800ed51bacf9963f9c54fd0e","abstract_canon_sha256":"40cd248d50a6a0cf188c24aa8821076179beadd2520964a5c8293e2f4c25159f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:08:59.021530Z","signature_b64":"WHjFkQ1D4CmVepoIXOccZmz931xzwznQaBqYa6Ed/+HUKPVG5H6eJFovYK4TuierX2EMdVArIZDgxowxZUmjDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13a6e03625d33db38ade99c8f90371e6d8528689908a706335f3f906c7fcfa4a","last_reissued_at":"2026-06-10T01:08:59.020648Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:08:59.020648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fisher-Guided Progressive Parameter Selection for Adaptive Fine-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ghodsiyeh Rostami, Mahdi S. Hosseini, Po-Han Chen","submitted_at":"2026-06-08T21:35:11Z","abstract_excerpt":"Parameter-efficient fine-tuning (PEFT) aims to adapt pretrained models with a small trainable parameter subset, however, most existing methods choose this subset from fixed architectural heuristics rather than using dynamic, task-aware criteria. We introduce \\textbf{FisherAdapTune}, a Fisher-guided Adaptive Fine-Tuning framework that progressively selects parameter groups by tracking the temporal drift of their Fisher geometry. Starting from a PAC-Bayesian view of fine-tuning, we decompose the generalization error bound into Fisher-weighted update costs and show that parameter groups whose cur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10196","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/2606.10196/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":"2606.10196","created_at":"2026-06-10T01:08:59.020793+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10196v1","created_at":"2026-06-10T01:08:59.020793+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10196","created_at":"2026-06-10T01:08:59.020793+00:00"},{"alias_kind":"pith_short_12","alias_value":"COTOANRF2M63","created_at":"2026-06-10T01:08:59.020793+00:00"},{"alias_kind":"pith_short_16","alias_value":"COTOANRF2M63HCW6","created_at":"2026-06-10T01:08:59.020793+00:00"},{"alias_kind":"pith_short_8","alias_value":"COTOANRF","created_at":"2026-06-10T01:08:59.020793+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/COTOANRF2M63HCW6THEPSA3R43","json":"https://pith.science/pith/COTOANRF2M63HCW6THEPSA3R43.json","graph_json":"https://pith.science/api/pith-number/COTOANRF2M63HCW6THEPSA3R43/graph.json","events_json":"https://pith.science/api/pith-number/COTOANRF2M63HCW6THEPSA3R43/events.json","paper":"https://pith.science/paper/COTOANRF"},"agent_actions":{"view_html":"https://pith.science/pith/COTOANRF2M63HCW6THEPSA3R43","download_json":"https://pith.science/pith/COTOANRF2M63HCW6THEPSA3R43.json","view_paper":"https://pith.science/paper/COTOANRF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10196&json=true","fetch_graph":"https://pith.science/api/pith-number/COTOANRF2M63HCW6THEPSA3R43/graph.json","fetch_events":"https://pith.science/api/pith-number/COTOANRF2M63HCW6THEPSA3R43/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/COTOANRF2M63HCW6THEPSA3R43/action/timestamp_anchor","attest_storage":"https://pith.science/pith/COTOANRF2M63HCW6THEPSA3R43/action/storage_attestation","attest_author":"https://pith.science/pith/COTOANRF2M63HCW6THEPSA3R43/action/author_attestation","sign_citation":"https://pith.science/pith/COTOANRF2M63HCW6THEPSA3R43/action/citation_signature","submit_replication":"https://pith.science/pith/COTOANRF2M63HCW6THEPSA3R43/action/replication_record"}},"created_at":"2026-06-10T01:08:59.020793+00:00","updated_at":"2026-06-10T01:08:59.020793+00:00"}