{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:F4SWDZF77MV6NPUJRDIVZHAZXL","short_pith_number":"pith:F4SWDZF7","canonical_record":{"source":{"id":"2406.14115","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-20T08:58:58Z","cross_cats_sorted":[],"title_canon_sha256":"033a85d6c670e4424eb01a44ddc5ee5b034c8b0a6a6a7dad7b2d798cc8f9ecc0","abstract_canon_sha256":"02527972a9653184e50f320f93f3115d19f5cb7472d48d96039f104fa4b78947"},"schema_version":"1.0"},"canonical_sha256":"2f2561e4bffb2be6be8988d15c9c19bafa276e496072c464ef4cc875bc769ffb","source":{"kind":"arxiv","id":"2406.14115","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.14115","created_at":"2026-07-05T10:18:38Z"},{"alias_kind":"arxiv_version","alias_value":"2406.14115v2","created_at":"2026-07-05T10:18:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14115","created_at":"2026-07-05T10:18:38Z"},{"alias_kind":"pith_short_12","alias_value":"F4SWDZF77MV6","created_at":"2026-07-05T10:18:38Z"},{"alias_kind":"pith_short_16","alias_value":"F4SWDZF77MV6NPUJ","created_at":"2026-07-05T10:18:38Z"},{"alias_kind":"pith_short_8","alias_value":"F4SWDZF7","created_at":"2026-07-05T10:18:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:F4SWDZF77MV6NPUJRDIVZHAZXL","target":"record","payload":{"canonical_record":{"source":{"id":"2406.14115","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-20T08:58:58Z","cross_cats_sorted":[],"title_canon_sha256":"033a85d6c670e4424eb01a44ddc5ee5b034c8b0a6a6a7dad7b2d798cc8f9ecc0","abstract_canon_sha256":"02527972a9653184e50f320f93f3115d19f5cb7472d48d96039f104fa4b78947"},"schema_version":"1.0"},"canonical_sha256":"2f2561e4bffb2be6be8988d15c9c19bafa276e496072c464ef4cc875bc769ffb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:38.420439Z","signature_b64":"4rFFZl9j1Mdn3KAd77uj86FjoYLnC+SwiCWwbVFx5sXW35JzsR4vFujUo/JCJ7kX7rnGAebP5k/hFEDB77i0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f2561e4bffb2be6be8988d15c9c19bafa276e496072c464ef4cc875bc769ffb","last_reissued_at":"2026-07-05T10:18:38.419938Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:38.419938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.14115","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:18:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"of13r2Q5DXXBMd3bufnUZ3mQcVy713ZRmDXPMblsrsSrO4NcCJ3WIzsfdXe6KhATgp8l/hTDxJI7a4SSp0VcCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T21:11:29.643203Z"},"content_sha256":"24625ebf93efc55963c81e7992755d854b5b43832dfcce56213169217e8af811","schema_version":"1.0","event_id":"sha256:24625ebf93efc55963c81e7992755d854b5b43832dfcce56213169217e8af811"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:F4SWDZF77MV6NPUJRDIVZHAZXL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Take the essence and discard the dross: A Rethinking on Data Selection for Fine-Tuning Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Feng Jiang, Haizhou Li, Rui Ke, Yajiao Liu, Ziche Liu","submitted_at":"2024-06-20T08:58:58Z","abstract_excerpt":"Data selection for fine-tuning large language models (LLMs) aims to choose a high-quality subset from existing datasets, allowing the trained model to outperform baselines trained on the full dataset. However, the expanding body of research lacks a clear, unified framework, and the variability in experimental settings complicates systematic comparisons. While existing surveys comprehensively overview the stages and methods of data selection, they often overlook an in-depth exploration of the fine-tuning phase. In this paper, we conduct a focused review of recent data selection techniques for f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14115","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/2406.14115/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:18:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6bxjvP9T0YCM5PeDFgtcMpiDmP8eUNbUNihyQrthVEpTJzOMIE7qmBBxlUSChGUK7Il3rfoF7biZ5NCskanVDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T21:11:29.643697Z"},"content_sha256":"435729e0a7986b711ac66efa180d7168755bcd3712d8be82ea2203f95dc42366","schema_version":"1.0","event_id":"sha256:435729e0a7986b711ac66efa180d7168755bcd3712d8be82ea2203f95dc42366"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F4SWDZF77MV6NPUJRDIVZHAZXL/bundle.json","state_url":"https://pith.science/pith/F4SWDZF77MV6NPUJRDIVZHAZXL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F4SWDZF77MV6NPUJRDIVZHAZXL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T21:11:29Z","links":{"resolver":"https://pith.science/pith/F4SWDZF77MV6NPUJRDIVZHAZXL","bundle":"https://pith.science/pith/F4SWDZF77MV6NPUJRDIVZHAZXL/bundle.json","state":"https://pith.science/pith/F4SWDZF77MV6NPUJRDIVZHAZXL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F4SWDZF77MV6NPUJRDIVZHAZXL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F4SWDZF77MV6NPUJRDIVZHAZXL","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":"02527972a9653184e50f320f93f3115d19f5cb7472d48d96039f104fa4b78947","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-20T08:58:58Z","title_canon_sha256":"033a85d6c670e4424eb01a44ddc5ee5b034c8b0a6a6a7dad7b2d798cc8f9ecc0"},"schema_version":"1.0","source":{"id":"2406.14115","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.14115","created_at":"2026-07-05T10:18:38Z"},{"alias_kind":"arxiv_version","alias_value":"2406.14115v2","created_at":"2026-07-05T10:18:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14115","created_at":"2026-07-05T10:18:38Z"},{"alias_kind":"pith_short_12","alias_value":"F4SWDZF77MV6","created_at":"2026-07-05T10:18:38Z"},{"alias_kind":"pith_short_16","alias_value":"F4SWDZF77MV6NPUJ","created_at":"2026-07-05T10:18:38Z"},{"alias_kind":"pith_short_8","alias_value":"F4SWDZF7","created_at":"2026-07-05T10:18:38Z"}],"graph_snapshots":[{"event_id":"sha256:435729e0a7986b711ac66efa180d7168755bcd3712d8be82ea2203f95dc42366","target":"graph","created_at":"2026-07-05T10:18:38Z","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/2406.14115/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data selection for fine-tuning large language models (LLMs) aims to choose a high-quality subset from existing datasets, allowing the trained model to outperform baselines trained on the full dataset. However, the expanding body of research lacks a clear, unified framework, and the variability in experimental settings complicates systematic comparisons. While existing surveys comprehensively overview the stages and methods of data selection, they often overlook an in-depth exploration of the fine-tuning phase. In this paper, we conduct a focused review of recent data selection techniques for f","authors_text":"Feng Jiang, Haizhou Li, Rui Ke, Yajiao Liu, Ziche Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-20T08:58:58Z","title":"Take the essence and discard the dross: A Rethinking on Data Selection for Fine-Tuning Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14115","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":"sha256:24625ebf93efc55963c81e7992755d854b5b43832dfcce56213169217e8af811","target":"record","created_at":"2026-07-05T10:18:38Z","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":"02527972a9653184e50f320f93f3115d19f5cb7472d48d96039f104fa4b78947","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-20T08:58:58Z","title_canon_sha256":"033a85d6c670e4424eb01a44ddc5ee5b034c8b0a6a6a7dad7b2d798cc8f9ecc0"},"schema_version":"1.0","source":{"id":"2406.14115","kind":"arxiv","version":2}},"canonical_sha256":"2f2561e4bffb2be6be8988d15c9c19bafa276e496072c464ef4cc875bc769ffb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f2561e4bffb2be6be8988d15c9c19bafa276e496072c464ef4cc875bc769ffb","first_computed_at":"2026-07-05T10:18:38.419938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:38.419938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4rFFZl9j1Mdn3KAd77uj86FjoYLnC+SwiCWwbVFx5sXW35JzsR4vFujUo/JCJ7kX7rnGAebP5k/hFEDB77i0Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:38.420439Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.14115","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24625ebf93efc55963c81e7992755d854b5b43832dfcce56213169217e8af811","sha256:435729e0a7986b711ac66efa180d7168755bcd3712d8be82ea2203f95dc42366"],"state_sha256":"d0831e076535542ddd8089131f72af80a22fe208111e32cc79454dd02c4a4a6b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6qGxPP8eEc2bJklncV/3MulCrAd4AOJoG0ap9jaJ2egicphG6KuJPK3HSEiQ2mggLorA5CPkyUsum+rWM2LNCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T21:11:29.649314Z","bundle_sha256":"b86376289ee64afd12201fc93d8b8fc7b404a94ceda4cd5189076fd000c22977"}}