{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CRQSDZVNGLPJQNN2YGVJDVMGSU","short_pith_number":"pith:CRQSDZVN","schema_version":"1.0","canonical_sha256":"146121e6ad32de9835bac1aa91d5869508a67b6f23babcf605fe2c9081541dc4","source":{"kind":"arxiv","id":"2410.11303","version":3},"attestation_state":"computed","paper":{"title":"TSDS: Data Selection for Task-Specific Model Finetuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Amin Karbasi, Theodoros Rekatsinas, Zifan Liu","submitted_at":"2024-10-15T05:54:17Z","abstract_excerpt":"Finetuning foundation models for specific tasks is an emerging paradigm in modern machine learning. The efficacy of task-specific finetuning largely depends on the selection of appropriate training data. We present TSDS (Task-Specific Data Selection), a framework to select data for task-specific model finetuning, guided by a small but representative set of examples from the target task. To do so, we formulate data selection for task-specific finetuning as an optimization problem with a distribution alignment loss based on optimal transport to capture the discrepancy between the selected data a"},"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":"2410.11303","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T05:54:17Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"7628271d6afa73f4e114a0d6da3ead60ce6f2490b8169e756075c675c8acbddb","abstract_canon_sha256":"012bfb457cb336744933cbaa3e31f935ffac3da0bbbfbcb66aa48438fd53dda9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:05.036942Z","signature_b64":"kipJHA/A6uQoj7zd1NpiUm6kyceJOY8UduyHdZX2tDTuiRf6n9DDSUuQHQjJTFjTpO24EUOqOW776MRUWJ9nDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"146121e6ad32de9835bac1aa91d5869508a67b6f23babcf605fe2c9081541dc4","last_reissued_at":"2026-07-05T09:54:05.036446Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:05.036446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TSDS: Data Selection for Task-Specific Model Finetuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Amin Karbasi, Theodoros Rekatsinas, Zifan Liu","submitted_at":"2024-10-15T05:54:17Z","abstract_excerpt":"Finetuning foundation models for specific tasks is an emerging paradigm in modern machine learning. The efficacy of task-specific finetuning largely depends on the selection of appropriate training data. We present TSDS (Task-Specific Data Selection), a framework to select data for task-specific model finetuning, guided by a small but representative set of examples from the target task. To do so, we formulate data selection for task-specific finetuning as an optimization problem with a distribution alignment loss based on optimal transport to capture the discrepancy between the selected data a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11303","kind":"arxiv","version":3},"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/2410.11303/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":"2410.11303","created_at":"2026-07-05T09:54:05.036507+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.11303v3","created_at":"2026-07-05T09:54:05.036507+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11303","created_at":"2026-07-05T09:54:05.036507+00:00"},{"alias_kind":"pith_short_12","alias_value":"CRQSDZVNGLPJ","created_at":"2026-07-05T09:54:05.036507+00:00"},{"alias_kind":"pith_short_16","alias_value":"CRQSDZVNGLPJQNN2","created_at":"2026-07-05T09:54:05.036507+00:00"},{"alias_kind":"pith_short_8","alias_value":"CRQSDZVN","created_at":"2026-07-05T09:54:05.036507+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.18458","citing_title":"A Survey of LLM $\\times$ DATA","ref_index":269,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CRQSDZVNGLPJQNN2YGVJDVMGSU","json":"https://pith.science/pith/CRQSDZVNGLPJQNN2YGVJDVMGSU.json","graph_json":"https://pith.science/api/pith-number/CRQSDZVNGLPJQNN2YGVJDVMGSU/graph.json","events_json":"https://pith.science/api/pith-number/CRQSDZVNGLPJQNN2YGVJDVMGSU/events.json","paper":"https://pith.science/paper/CRQSDZVN"},"agent_actions":{"view_html":"https://pith.science/pith/CRQSDZVNGLPJQNN2YGVJDVMGSU","download_json":"https://pith.science/pith/CRQSDZVNGLPJQNN2YGVJDVMGSU.json","view_paper":"https://pith.science/paper/CRQSDZVN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.11303&json=true","fetch_graph":"https://pith.science/api/pith-number/CRQSDZVNGLPJQNN2YGVJDVMGSU/graph.json","fetch_events":"https://pith.science/api/pith-number/CRQSDZVNGLPJQNN2YGVJDVMGSU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CRQSDZVNGLPJQNN2YGVJDVMGSU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CRQSDZVNGLPJQNN2YGVJDVMGSU/action/storage_attestation","attest_author":"https://pith.science/pith/CRQSDZVNGLPJQNN2YGVJDVMGSU/action/author_attestation","sign_citation":"https://pith.science/pith/CRQSDZVNGLPJQNN2YGVJDVMGSU/action/citation_signature","submit_replication":"https://pith.science/pith/CRQSDZVNGLPJQNN2YGVJDVMGSU/action/replication_record"}},"created_at":"2026-07-05T09:54:05.036507+00:00","updated_at":"2026-07-05T09:54:05.036507+00:00"}