{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VFUXEGCSSJVLJWR46BFQZGQ652","short_pith_number":"pith:VFUXEGCS","schema_version":"1.0","canonical_sha256":"a969721852926ab4da3cf04b0c9a1eee8b4ac733aeb49fa0924e88b4e8713722","source":{"kind":"arxiv","id":"2509.01221","version":2},"attestation_state":"computed","paper":{"title":"DaMoC: Efficiently Selecting the Optimal Large Language Model for Fine-tuning Domain Tasks Based on Data and Model Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Huang Wei, Wei Huang, Yinggui Wang","submitted_at":"2025-09-01T08:06:49Z","abstract_excerpt":"Large language models (LLMs) excel in general tasks but struggle with domain-specific ones, requiring fine-tuning with specific data. With many open-source LLMs available, selecting the best model for fine-tuning downstream tasks is challenging, primarily focusing on how to quickly identify the optimal LLM. We introduce a Data and Model Compression Framework (DaMoC) that addresses this challenge by: 1) Data Level: A systematic categorization of data filtering methodologies for LLMs is first established, classifying them into three distinct paradigms: (1) distribution-aware methods, (2) quality"},"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":"2509.01221","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-01T08:06:49Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"7661c869f22cdec3a7b993db99f95ff943ab58cb4688a5f1a9a51aeb6f3ba7fe","abstract_canon_sha256":"4aca61925fc091a33c54b756735cf22e4ee548b8a1883790be76c659a5c6d6da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:40.736045Z","signature_b64":"RG+xaXhMA492l1K80kW6Xq510i41Ohvlz6/1eyn/MvZENNiE8ZoALpauuA2XSdJNB+PWHwSeqZCZ8T9vRQn/BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a969721852926ab4da3cf04b0c9a1eee8b4ac733aeb49fa0924e88b4e8713722","last_reissued_at":"2026-07-05T12:04:40.735472Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:40.735472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DaMoC: Efficiently Selecting the Optimal Large Language Model for Fine-tuning Domain Tasks Based on Data and Model Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Huang Wei, Wei Huang, Yinggui Wang","submitted_at":"2025-09-01T08:06:49Z","abstract_excerpt":"Large language models (LLMs) excel in general tasks but struggle with domain-specific ones, requiring fine-tuning with specific data. With many open-source LLMs available, selecting the best model for fine-tuning downstream tasks is challenging, primarily focusing on how to quickly identify the optimal LLM. We introduce a Data and Model Compression Framework (DaMoC) that addresses this challenge by: 1) Data Level: A systematic categorization of data filtering methodologies for LLMs is first established, classifying them into three distinct paradigms: (1) distribution-aware methods, (2) quality"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01221","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/2509.01221/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":"2509.01221","created_at":"2026-07-05T12:04:40.735527+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.01221v2","created_at":"2026-07-05T12:04:40.735527+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01221","created_at":"2026-07-05T12:04:40.735527+00:00"},{"alias_kind":"pith_short_12","alias_value":"VFUXEGCSSJVL","created_at":"2026-07-05T12:04:40.735527+00:00"},{"alias_kind":"pith_short_16","alias_value":"VFUXEGCSSJVLJWR4","created_at":"2026-07-05T12:04:40.735527+00:00"},{"alias_kind":"pith_short_8","alias_value":"VFUXEGCS","created_at":"2026-07-05T12:04:40.735527+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/VFUXEGCSSJVLJWR46BFQZGQ652","json":"https://pith.science/pith/VFUXEGCSSJVLJWR46BFQZGQ652.json","graph_json":"https://pith.science/api/pith-number/VFUXEGCSSJVLJWR46BFQZGQ652/graph.json","events_json":"https://pith.science/api/pith-number/VFUXEGCSSJVLJWR46BFQZGQ652/events.json","paper":"https://pith.science/paper/VFUXEGCS"},"agent_actions":{"view_html":"https://pith.science/pith/VFUXEGCSSJVLJWR46BFQZGQ652","download_json":"https://pith.science/pith/VFUXEGCSSJVLJWR46BFQZGQ652.json","view_paper":"https://pith.science/paper/VFUXEGCS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.01221&json=true","fetch_graph":"https://pith.science/api/pith-number/VFUXEGCSSJVLJWR46BFQZGQ652/graph.json","fetch_events":"https://pith.science/api/pith-number/VFUXEGCSSJVLJWR46BFQZGQ652/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VFUXEGCSSJVLJWR46BFQZGQ652/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VFUXEGCSSJVLJWR46BFQZGQ652/action/storage_attestation","attest_author":"https://pith.science/pith/VFUXEGCSSJVLJWR46BFQZGQ652/action/author_attestation","sign_citation":"https://pith.science/pith/VFUXEGCSSJVLJWR46BFQZGQ652/action/citation_signature","submit_replication":"https://pith.science/pith/VFUXEGCSSJVLJWR46BFQZGQ652/action/replication_record"}},"created_at":"2026-07-05T12:04:40.735527+00:00","updated_at":"2026-07-05T12:04:40.735527+00:00"}