{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EIBTIKLLQWLTA2AAWRDDXFCQW2","short_pith_number":"pith:EIBTIKLL","canonical_record":{"source":{"id":"2402.05123","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-04T13:32:01Z","cross_cats_sorted":[],"title_canon_sha256":"d4612abb780598e4168953484bfb50a97c32ac3ea1b4280ef29e1cc61786b95b","abstract_canon_sha256":"a2c0610f798f4327d2a696722ee8884b5999ca63965e11c74faf84d5f67a2ea6"},"schema_version":"1.0"},"canonical_sha256":"220334296b8597306800b4463b9450b6955de8c368752b9554c396e41563204f","source":{"kind":"arxiv","id":"2402.05123","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.05123","created_at":"2026-07-05T11:59:04Z"},{"alias_kind":"arxiv_version","alias_value":"2402.05123v3","created_at":"2026-07-05T11:59:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05123","created_at":"2026-07-05T11:59:04Z"},{"alias_kind":"pith_short_12","alias_value":"EIBTIKLLQWLT","created_at":"2026-07-05T11:59:04Z"},{"alias_kind":"pith_short_16","alias_value":"EIBTIKLLQWLTA2AA","created_at":"2026-07-05T11:59:04Z"},{"alias_kind":"pith_short_8","alias_value":"EIBTIKLL","created_at":"2026-07-05T11:59:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EIBTIKLLQWLTA2AAWRDDXFCQW2","target":"record","payload":{"canonical_record":{"source":{"id":"2402.05123","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-04T13:32:01Z","cross_cats_sorted":[],"title_canon_sha256":"d4612abb780598e4168953484bfb50a97c32ac3ea1b4280ef29e1cc61786b95b","abstract_canon_sha256":"a2c0610f798f4327d2a696722ee8884b5999ca63965e11c74faf84d5f67a2ea6"},"schema_version":"1.0"},"canonical_sha256":"220334296b8597306800b4463b9450b6955de8c368752b9554c396e41563204f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:04.670062Z","signature_b64":"bUNNxL9XTT+RHdAxd5ZzrngkSuSYL5Gc1uzr9pkz0LXUPoEJ8njUSry87QL5jcZOj3vvIx4+0quRPLFdnnQOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"220334296b8597306800b4463b9450b6955de8c368752b9554c396e41563204f","last_reissued_at":"2026-07-05T11:59:04.669594Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:04.669594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.05123","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:59:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"53WymMsX1qgg1SrnAj896w4uzHdw9+z8EeVlTGxuL9H+oF68zwyhuzbGD/fkMIP/a31cZ4H4bgsgyY8viKQICg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:03:06.184020Z"},"content_sha256":"54007953d6d4f3868662e076636684f05e260b3cbc9df3e31b0f1f07b66b0daf","schema_version":"1.0","event_id":"sha256:54007953d6d4f3868662e076636684f05e260b3cbc9df3e31b0f1f07b66b0daf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EIBTIKLLQWLTA2AAWRDDXFCQW2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey on Data Selection for LLM Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bolin Zhang, Dianhui Chu, Jiahao Wang, Jiajun Zhang, Qianlong Du, Zhiying Tu","submitted_at":"2024-02-04T13:32:01Z","abstract_excerpt":"Instruction tuning is a vital step of training large language models (LLMs), so how to enhance the effect of instruction tuning has received increased attention. Existing works indicate that the quality of the dataset is more crucial than the quantity during instruction tuning of LLMs. Therefore, recently a lot of studies focus on exploring the methods of selecting high-quality subset from instruction datasets, aiming to reduce training costs and enhance the instruction-following capabilities of LLMs. This paper presents a comprehensive survey on data selection for LLM instruction tuning. Firs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05123","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/2402.05123/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":"2026-07-05T11:59:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cWGfMSpLAGCPj1EaFNX0CPq4OEIx65FpEtH+zQt06duVDyMHskx5rDRuYWgq3M6AbpH2DKfLnTj5djnb/r3ZBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:03:06.184977Z"},"content_sha256":"dfe08b2225bc6a7f7456694bc45144e08ac5f0d4c985589ebca7ae4a945625c4","schema_version":"1.0","event_id":"sha256:dfe08b2225bc6a7f7456694bc45144e08ac5f0d4c985589ebca7ae4a945625c4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EIBTIKLLQWLTA2AAWRDDXFCQW2/bundle.json","state_url":"https://pith.science/pith/EIBTIKLLQWLTA2AAWRDDXFCQW2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EIBTIKLLQWLTA2AAWRDDXFCQW2/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":"2026-08-04T15:03:06Z","links":{"resolver":"https://pith.science/pith/EIBTIKLLQWLTA2AAWRDDXFCQW2","bundle":"https://pith.science/pith/EIBTIKLLQWLTA2AAWRDDXFCQW2/bundle.json","state":"https://pith.science/pith/EIBTIKLLQWLTA2AAWRDDXFCQW2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EIBTIKLLQWLTA2AAWRDDXFCQW2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EIBTIKLLQWLTA2AAWRDDXFCQW2","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":"a2c0610f798f4327d2a696722ee8884b5999ca63965e11c74faf84d5f67a2ea6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-04T13:32:01Z","title_canon_sha256":"d4612abb780598e4168953484bfb50a97c32ac3ea1b4280ef29e1cc61786b95b"},"schema_version":"1.0","source":{"id":"2402.05123","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.05123","created_at":"2026-07-05T11:59:04Z"},{"alias_kind":"arxiv_version","alias_value":"2402.05123v3","created_at":"2026-07-05T11:59:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05123","created_at":"2026-07-05T11:59:04Z"},{"alias_kind":"pith_short_12","alias_value":"EIBTIKLLQWLT","created_at":"2026-07-05T11:59:04Z"},{"alias_kind":"pith_short_16","alias_value":"EIBTIKLLQWLTA2AA","created_at":"2026-07-05T11:59:04Z"},{"alias_kind":"pith_short_8","alias_value":"EIBTIKLL","created_at":"2026-07-05T11:59:04Z"}],"graph_snapshots":[{"event_id":"sha256:dfe08b2225bc6a7f7456694bc45144e08ac5f0d4c985589ebca7ae4a945625c4","target":"graph","created_at":"2026-07-05T11:59:04Z","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/2402.05123/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction tuning is a vital step of training large language models (LLMs), so how to enhance the effect of instruction tuning has received increased attention. Existing works indicate that the quality of the dataset is more crucial than the quantity during instruction tuning of LLMs. Therefore, recently a lot of studies focus on exploring the methods of selecting high-quality subset from instruction datasets, aiming to reduce training costs and enhance the instruction-following capabilities of LLMs. This paper presents a comprehensive survey on data selection for LLM instruction tuning. Firs","authors_text":"Bolin Zhang, Dianhui Chu, Jiahao Wang, Jiajun Zhang, Qianlong Du, Zhiying Tu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-04T13:32:01Z","title":"A Survey on Data Selection for LLM Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05123","kind":"arxiv","version":3},"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":"sha256:54007953d6d4f3868662e076636684f05e260b3cbc9df3e31b0f1f07b66b0daf","target":"record","created_at":"2026-07-05T11:59:04Z","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":"a2c0610f798f4327d2a696722ee8884b5999ca63965e11c74faf84d5f67a2ea6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-04T13:32:01Z","title_canon_sha256":"d4612abb780598e4168953484bfb50a97c32ac3ea1b4280ef29e1cc61786b95b"},"schema_version":"1.0","source":{"id":"2402.05123","kind":"arxiv","version":3}},"canonical_sha256":"220334296b8597306800b4463b9450b6955de8c368752b9554c396e41563204f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"220334296b8597306800b4463b9450b6955de8c368752b9554c396e41563204f","first_computed_at":"2026-07-05T11:59:04.669594Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:59:04.669594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bUNNxL9XTT+RHdAxd5ZzrngkSuSYL5Gc1uzr9pkz0LXUPoEJ8njUSry87QL5jcZOj3vvIx4+0quRPLFdnnQOCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:59:04.670062Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.05123","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54007953d6d4f3868662e076636684f05e260b3cbc9df3e31b0f1f07b66b0daf","sha256:dfe08b2225bc6a7f7456694bc45144e08ac5f0d4c985589ebca7ae4a945625c4"],"state_sha256":"1ff8894b8a56f83de6a1f8664f44a962cbbcf860a995b41c350abfd30960115e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z1wyg80lluLRmYUY5suolA5yKlQpCcNqoFP7WSdqRi3B7eg1eIYvfOxafLsOlgnWAhIRFJ6DCdjcpW3Vn7vgAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T15:03:06.190283Z","bundle_sha256":"765011664f04fbcb2606cbf52039e7d36ba02fe9c2c3f2ff191ecd5a1c6a1324"}}