{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SVXHQJTP434HUPHECUWJEO5M5F","short_pith_number":"pith:SVXHQJTP","canonical_record":{"source":{"id":"2308.12032","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-23T09:45:29Z","cross_cats_sorted":[],"title_canon_sha256":"1dba7979ed42b6cddc3135b0ebe0b7893b96bb39ccbae9c80e86f767749b66f1","abstract_canon_sha256":"047395a3d3647f754811dcccaa9d1e964ed3ffd0e429210fbf0b1af396282971"},"schema_version":"1.0"},"canonical_sha256":"956e78266fe6f87a3ce4152c923bace950b81d258545f4e8d99b40952c65b963","source":{"kind":"arxiv","id":"2308.12032","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.12032","created_at":"2026-07-05T08:05:01Z"},{"alias_kind":"arxiv_version","alias_value":"2308.12032v5","created_at":"2026-07-05T08:05:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12032","created_at":"2026-07-05T08:05:01Z"},{"alias_kind":"pith_short_12","alias_value":"SVXHQJTP434H","created_at":"2026-07-05T08:05:01Z"},{"alias_kind":"pith_short_16","alias_value":"SVXHQJTP434HUPHE","created_at":"2026-07-05T08:05:01Z"},{"alias_kind":"pith_short_8","alias_value":"SVXHQJTP","created_at":"2026-07-05T08:05:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SVXHQJTP434HUPHECUWJEO5M5F","target":"record","payload":{"canonical_record":{"source":{"id":"2308.12032","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-23T09:45:29Z","cross_cats_sorted":[],"title_canon_sha256":"1dba7979ed42b6cddc3135b0ebe0b7893b96bb39ccbae9c80e86f767749b66f1","abstract_canon_sha256":"047395a3d3647f754811dcccaa9d1e964ed3ffd0e429210fbf0b1af396282971"},"schema_version":"1.0"},"canonical_sha256":"956e78266fe6f87a3ce4152c923bace950b81d258545f4e8d99b40952c65b963","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:01.294580Z","signature_b64":"fIrYsWlteE6TFiyed0vx/zYk8xXOqBgvsceWe2bqSdJ/sKuTa9HtC2WoEH2+3+oEL3/Vso4JfwNpwZ3FTvTFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"956e78266fe6f87a3ce4152c923bace950b81d258545f4e8d99b40952c65b963","last_reissued_at":"2026-07-05T08:05:01.294065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:01.294065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.12032","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:05:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3C/tBMAA1V8Co428gc2P6Urg1uSsLfWAL/s/iu1TnFS5v1Wt6K3ilw6s9mhWI8AZVP19t8gvesTLjlmeTZrgBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:35:54.852625Z"},"content_sha256":"47c7658e531a852e8dea30936df4a6259940daa93fb669ef631af46ea91182b2","schema_version":"1.0","event_id":"sha256:47c7658e531a852e8dea30936df4a6259940daa93fb669ef631af46ea91182b2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SVXHQJTP434HUPHECUWJEO5M5F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jianzong Wang, Jing Xiao, Jiuhai Chen, Lichang Chen, Ming Li, Ning Cheng, Tianyi Zhou, Yong Zhang, Zhitao Li","submitted_at":"2023-08-23T09:45:29Z","abstract_excerpt":"In the realm of Large Language Models (LLMs), the balance between instruction data quality and quantity is a focal point. Recognizing this, we introduce a self-guided methodology for LLMs to autonomously discern and select cherry samples from open-source datasets, effectively minimizing manual curation and potential cost for instruction tuning an LLM. Our key innovation, the Instruction-Following Difficulty (IFD) metric, emerges as a pivotal metric to identify discrepancies between a model's expected responses and its intrinsic generation capability. Through the application of IFD, cherry samp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12032","kind":"arxiv","version":5},"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/2308.12032/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":"2026-07-05T08:05:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Av9b2/DujSKtYF0I+UPbdqa4SAD0lco698Lp3njnkSu3F0VdSQdrWP02+cdy0fDp/KitW+1H0FTIIhfXoGqtAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:35:54.853145Z"},"content_sha256":"2aeb4bed6b6b6420b8bbfcbfeafbf0fa972a8a30747daafae7fca3bb71af2ada","schema_version":"1.0","event_id":"sha256:2aeb4bed6b6b6420b8bbfcbfeafbf0fa972a8a30747daafae7fca3bb71af2ada"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SVXHQJTP434HUPHECUWJEO5M5F/bundle.json","state_url":"https://pith.science/pith/SVXHQJTP434HUPHECUWJEO5M5F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SVXHQJTP434HUPHECUWJEO5M5F/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":"2026-08-05T10:35:54Z","links":{"resolver":"https://pith.science/pith/SVXHQJTP434HUPHECUWJEO5M5F","bundle":"https://pith.science/pith/SVXHQJTP434HUPHECUWJEO5M5F/bundle.json","state":"https://pith.science/pith/SVXHQJTP434HUPHECUWJEO5M5F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SVXHQJTP434HUPHECUWJEO5M5F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SVXHQJTP434HUPHECUWJEO5M5F","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":"047395a3d3647f754811dcccaa9d1e964ed3ffd0e429210fbf0b1af396282971","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-23T09:45:29Z","title_canon_sha256":"1dba7979ed42b6cddc3135b0ebe0b7893b96bb39ccbae9c80e86f767749b66f1"},"schema_version":"1.0","source":{"id":"2308.12032","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.12032","created_at":"2026-07-05T08:05:01Z"},{"alias_kind":"arxiv_version","alias_value":"2308.12032v5","created_at":"2026-07-05T08:05:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12032","created_at":"2026-07-05T08:05:01Z"},{"alias_kind":"pith_short_12","alias_value":"SVXHQJTP434H","created_at":"2026-07-05T08:05:01Z"},{"alias_kind":"pith_short_16","alias_value":"SVXHQJTP434HUPHE","created_at":"2026-07-05T08:05:01Z"},{"alias_kind":"pith_short_8","alias_value":"SVXHQJTP","created_at":"2026-07-05T08:05:01Z"}],"graph_snapshots":[{"event_id":"sha256:2aeb4bed6b6b6420b8bbfcbfeafbf0fa972a8a30747daafae7fca3bb71af2ada","target":"graph","created_at":"2026-07-05T08:05:01Z","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/2308.12032/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the realm of Large Language Models (LLMs), the balance between instruction data quality and quantity is a focal point. Recognizing this, we introduce a self-guided methodology for LLMs to autonomously discern and select cherry samples from open-source datasets, effectively minimizing manual curation and potential cost for instruction tuning an LLM. Our key innovation, the Instruction-Following Difficulty (IFD) metric, emerges as a pivotal metric to identify discrepancies between a model's expected responses and its intrinsic generation capability. Through the application of IFD, cherry samp","authors_text":"Jianzong Wang, Jing Xiao, Jiuhai Chen, Lichang Chen, Ming Li, Ning Cheng, Tianyi Zhou, Yong Zhang, Zhitao Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-23T09:45:29Z","title":"From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12032","kind":"arxiv","version":5},"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":"sha256:47c7658e531a852e8dea30936df4a6259940daa93fb669ef631af46ea91182b2","target":"record","created_at":"2026-07-05T08:05:01Z","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":"047395a3d3647f754811dcccaa9d1e964ed3ffd0e429210fbf0b1af396282971","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-23T09:45:29Z","title_canon_sha256":"1dba7979ed42b6cddc3135b0ebe0b7893b96bb39ccbae9c80e86f767749b66f1"},"schema_version":"1.0","source":{"id":"2308.12032","kind":"arxiv","version":5}},"canonical_sha256":"956e78266fe6f87a3ce4152c923bace950b81d258545f4e8d99b40952c65b963","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"956e78266fe6f87a3ce4152c923bace950b81d258545f4e8d99b40952c65b963","first_computed_at":"2026-07-05T08:05:01.294065Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:05:01.294065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fIrYsWlteE6TFiyed0vx/zYk8xXOqBgvsceWe2bqSdJ/sKuTa9HtC2WoEH2+3+oEL3/Vso4JfwNpwZ3FTvTFBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:05:01.294580Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.12032","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47c7658e531a852e8dea30936df4a6259940daa93fb669ef631af46ea91182b2","sha256:2aeb4bed6b6b6420b8bbfcbfeafbf0fa972a8a30747daafae7fca3bb71af2ada"],"state_sha256":"2d154bd6faf15ebf89a44af5579dfd88bdaa03d307becb5854b0a50f4b5295a1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pUJ7Y3ZoNID7Z7fr5AzO9DDpu3416BvRMH/LyU6ZiNEU8X3CdIYJ4xdRFmRf0z8bA5rYFLwgpdrysJ2tlizdDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T10:35:54.858640Z","bundle_sha256":"f7c0166003c0510460eb6596fc8307a52395a426224565bcd47b9fc833e4f066"}}