{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VFUXEGCSSJVLJWR46BFQZGQ652","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4aca61925fc091a33c54b756735cf22e4ee548b8a1883790be76c659a5c6d6da","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-01T08:06:49Z","title_canon_sha256":"7661c869f22cdec3a7b993db99f95ff943ab58cb4688a5f1a9a51aeb6f3ba7fe"},"schema_version":"1.0","source":{"id":"2509.01221","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.01221","created_at":"2026-07-05T12:04:40Z"},{"alias_kind":"arxiv_version","alias_value":"2509.01221v2","created_at":"2026-07-05T12:04:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01221","created_at":"2026-07-05T12:04:40Z"},{"alias_kind":"pith_short_12","alias_value":"VFUXEGCSSJVL","created_at":"2026-07-05T12:04:40Z"},{"alias_kind":"pith_short_16","alias_value":"VFUXEGCSSJVLJWR4","created_at":"2026-07-05T12:04:40Z"},{"alias_kind":"pith_short_8","alias_value":"VFUXEGCS","created_at":"2026-07-05T12:04:40Z"}],"graph_snapshots":[{"event_id":"sha256:a0524a82950cb7dc684021f9ee60cfdabb43f5a451c9ed12d1f38496efb4063c","target":"graph","created_at":"2026-07-05T12:04:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2509.01221/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Huang Wei, Wei Huang, Yinggui Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-01T08:06:49Z","title":"DaMoC: Efficiently Selecting the Optimal Large Language Model for Fine-tuning Domain Tasks Based on Data and Model Compression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01221","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:24eec0ea6e038f53b99ccf5af70b3e1151bcc563ba447a36e83b551605637783","target":"record","created_at":"2026-07-05T12:04:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4aca61925fc091a33c54b756735cf22e4ee548b8a1883790be76c659a5c6d6da","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-01T08:06:49Z","title_canon_sha256":"7661c869f22cdec3a7b993db99f95ff943ab58cb4688a5f1a9a51aeb6f3ba7fe"},"schema_version":"1.0","source":{"id":"2509.01221","kind":"arxiv","version":2}},"canonical_sha256":"a969721852926ab4da3cf04b0c9a1eee8b4ac733aeb49fa0924e88b4e8713722","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a969721852926ab4da3cf04b0c9a1eee8b4ac733aeb49fa0924e88b4e8713722","first_computed_at":"2026-07-05T12:04:40.735472Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:04:40.735472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RG+xaXhMA492l1K80kW6Xq510i41Ohvlz6/1eyn/MvZENNiE8ZoALpauuA2XSdJNB+PWHwSeqZCZ8T9vRQn/BA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:04:40.736045Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.01221","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24eec0ea6e038f53b99ccf5af70b3e1151bcc563ba447a36e83b551605637783","sha256:a0524a82950cb7dc684021f9ee60cfdabb43f5a451c9ed12d1f38496efb4063c"],"state_sha256":"fe5949d85b69cd312acd84688a657f066345b8eef6812d47b492df8a77b94797"}