{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:W7LSUOHMIBHLANSPPQBZSZ55KY","short_pith_number":"pith:W7LSUOHM","schema_version":"1.0","canonical_sha256":"b7d72a38ec404eb0364f7c039967bd5623cfec2bfbc3896b04f2481939387fd2","source":{"kind":"arxiv","id":"2507.22872","version":1},"attestation_state":"computed","paper":{"title":"TR-PTS: Task-Relevant Parameter and Token Selection for Efficient Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangtao Zhai, Guangyang Wu, Haoran Yang, Mingyang Yi, Siqi Luo, Xiaohong Liu, Yi Xin","submitted_at":"2025-07-30T17:47:13Z","abstract_excerpt":"Large pre-trained models achieve remarkable performance in vision tasks but are impractical for fine-tuning due to high computational and storage costs. Parameter-Efficient Fine-Tuning (PEFT) methods mitigate this issue by updating only a subset of parameters; however, most existing approaches are task-agnostic, failing to fully exploit task-specific adaptations, which leads to suboptimal efficiency and performance. To address this limitation, we propose Task-Relevant Parameter and Token Selection (TR-PTS), a task-driven framework that enhances both computational efficiency and accuracy. Speci"},"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":"2507.22872","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-30T17:47:13Z","cross_cats_sorted":[],"title_canon_sha256":"aa92026f7603d430853acc63f7e81050132abad8c98f84026205cbf8be0eecde","abstract_canon_sha256":"b90cd513974dbd443c9bdcfb81edeb9c0d5a3f1e5951ed8d0ba177788a88e88e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:50.732272Z","signature_b64":"07ZMNgdvVtVlCl/mPfTsIttRyjnbMOjMi91I87nMNLr/WsJHxMGzI2fktJOMDYifAHlXdJu0iebgcZJGDOjKDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7d72a38ec404eb0364f7c039967bd5623cfec2bfbc3896b04f2481939387fd2","last_reissued_at":"2026-07-05T11:45:50.731775Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:50.731775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TR-PTS: Task-Relevant Parameter and Token Selection for Efficient Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangtao Zhai, Guangyang Wu, Haoran Yang, Mingyang Yi, Siqi Luo, Xiaohong Liu, Yi Xin","submitted_at":"2025-07-30T17:47:13Z","abstract_excerpt":"Large pre-trained models achieve remarkable performance in vision tasks but are impractical for fine-tuning due to high computational and storage costs. Parameter-Efficient Fine-Tuning (PEFT) methods mitigate this issue by updating only a subset of parameters; however, most existing approaches are task-agnostic, failing to fully exploit task-specific adaptations, which leads to suboptimal efficiency and performance. To address this limitation, we propose Task-Relevant Parameter and Token Selection (TR-PTS), a task-driven framework that enhances both computational efficiency and accuracy. Speci"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22872","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/2507.22872/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":"2507.22872","created_at":"2026-07-05T11:45:50.731833+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.22872v1","created_at":"2026-07-05T11:45:50.731833+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22872","created_at":"2026-07-05T11:45:50.731833+00:00"},{"alias_kind":"pith_short_12","alias_value":"W7LSUOHMIBHL","created_at":"2026-07-05T11:45:50.731833+00:00"},{"alias_kind":"pith_short_16","alias_value":"W7LSUOHMIBHLANSP","created_at":"2026-07-05T11:45:50.731833+00:00"},{"alias_kind":"pith_short_8","alias_value":"W7LSUOHM","created_at":"2026-07-05T11:45:50.731833+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/W7LSUOHMIBHLANSPPQBZSZ55KY","json":"https://pith.science/pith/W7LSUOHMIBHLANSPPQBZSZ55KY.json","graph_json":"https://pith.science/api/pith-number/W7LSUOHMIBHLANSPPQBZSZ55KY/graph.json","events_json":"https://pith.science/api/pith-number/W7LSUOHMIBHLANSPPQBZSZ55KY/events.json","paper":"https://pith.science/paper/W7LSUOHM"},"agent_actions":{"view_html":"https://pith.science/pith/W7LSUOHMIBHLANSPPQBZSZ55KY","download_json":"https://pith.science/pith/W7LSUOHMIBHLANSPPQBZSZ55KY.json","view_paper":"https://pith.science/paper/W7LSUOHM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.22872&json=true","fetch_graph":"https://pith.science/api/pith-number/W7LSUOHMIBHLANSPPQBZSZ55KY/graph.json","fetch_events":"https://pith.science/api/pith-number/W7LSUOHMIBHLANSPPQBZSZ55KY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W7LSUOHMIBHLANSPPQBZSZ55KY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W7LSUOHMIBHLANSPPQBZSZ55KY/action/storage_attestation","attest_author":"https://pith.science/pith/W7LSUOHMIBHLANSPPQBZSZ55KY/action/author_attestation","sign_citation":"https://pith.science/pith/W7LSUOHMIBHLANSPPQBZSZ55KY/action/citation_signature","submit_replication":"https://pith.science/pith/W7LSUOHMIBHLANSPPQBZSZ55KY/action/replication_record"}},"created_at":"2026-07-05T11:45:50.731833+00:00","updated_at":"2026-07-05T11:45:50.731833+00:00"}