{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NJPUXRYRF65RGE236L6G7YLY2G","short_pith_number":"pith:NJPUXRYR","canonical_record":{"source":{"id":"2407.13906","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T21:36:00Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"902076e8b79ba57fd8457588baa84cd3bd64699d47b883426e9d426057b2bbb1","abstract_canon_sha256":"b2b091433ca5315bdf940b7c025d8d988301582400259a0d93748f6367547baa"},"schema_version":"1.0"},"canonical_sha256":"6a5f4bc7112fbb13135bf2fc6fe178d1bf9590398d188a6fc6485743dfbfe540","source":{"kind":"arxiv","id":"2407.13906","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.13906","created_at":"2026-07-05T08:45:55Z"},{"alias_kind":"arxiv_version","alias_value":"2407.13906v1","created_at":"2026-07-05T08:45:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13906","created_at":"2026-07-05T08:45:55Z"},{"alias_kind":"pith_short_12","alias_value":"NJPUXRYRF65R","created_at":"2026-07-05T08:45:55Z"},{"alias_kind":"pith_short_16","alias_value":"NJPUXRYRF65RGE23","created_at":"2026-07-05T08:45:55Z"},{"alias_kind":"pith_short_8","alias_value":"NJPUXRYR","created_at":"2026-07-05T08:45:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NJPUXRYRF65RGE236L6G7YLY2G","target":"record","payload":{"canonical_record":{"source":{"id":"2407.13906","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T21:36:00Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"902076e8b79ba57fd8457588baa84cd3bd64699d47b883426e9d426057b2bbb1","abstract_canon_sha256":"b2b091433ca5315bdf940b7c025d8d988301582400259a0d93748f6367547baa"},"schema_version":"1.0"},"canonical_sha256":"6a5f4bc7112fbb13135bf2fc6fe178d1bf9590398d188a6fc6485743dfbfe540","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:55.313339Z","signature_b64":"dTv3JWkEmOTKyfTLNon4+KOSB0TgcPGb8YfMc5thYX59+r3yyv1ksj48bKU35OD3aPcxDqr7lerOOb9SwuFaCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a5f4bc7112fbb13135bf2fc6fe178d1bf9590398d188a6fc6485743dfbfe540","last_reissued_at":"2026-07-05T08:45:55.312841Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:55.312841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.13906","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:45:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lYHnAY52txkkNdDu5L0az8i7ruTWvVi+dz0jAPRdBcAhJGZwjap3lUQw1gU8o4zYeiwqz+bOIoisEoRnYWiPAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:32:07.132763Z"},"content_sha256":"af6f10397bcc8da77736f1b6a235a812e478d7554db4d6514d74aeeba018ff16","schema_version":"1.0","event_id":"sha256:af6f10397bcc8da77736f1b6a235a812e478d7554db4d6514d74aeeba018ff16"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NJPUXRYRF65RGE236L6G7YLY2G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Crafting Efficient Fine-Tuning Strategies for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Guan Wang, Michael Oliver","submitted_at":"2024-07-18T21:36:00Z","abstract_excerpt":"This paper addresses the challenges of efficiently fine-tuning large language models (LLMs) by exploring data efficiency and hyperparameter optimization. We investigate the minimum data required for effective fine-tuning and propose a novel hyperparameter optimization method that leverages early-stage model performance. Our experiments demonstrate that fine-tuning with as few as 200 samples can improve model accuracy from 70\\% to 88\\% in a product attribute extraction task. We identify a saturation point of approximately 6,500 samples, beyond which additional data yields diminishing returns. O"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13906","kind":"arxiv","version":1},"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/2407.13906/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":"2026-07-05T08:45:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L9Te0sJDmBjs973MFhDCUcnijvldPuOYxVCXDWr54N9MW1skZkcixDBgwFx5Jq8vFEa+b/bgMY9jXWaaLWf7Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:32:07.133270Z"},"content_sha256":"346dadcdd8a367db6d642c7da6bb69be0d9f03bb823ea5678d569c4bc9a7fb25","schema_version":"1.0","event_id":"sha256:346dadcdd8a367db6d642c7da6bb69be0d9f03bb823ea5678d569c4bc9a7fb25"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NJPUXRYRF65RGE236L6G7YLY2G/bundle.json","state_url":"https://pith.science/pith/NJPUXRYRF65RGE236L6G7YLY2G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NJPUXRYRF65RGE236L6G7YLY2G/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":"2026-08-09T04:32:07Z","links":{"resolver":"https://pith.science/pith/NJPUXRYRF65RGE236L6G7YLY2G","bundle":"https://pith.science/pith/NJPUXRYRF65RGE236L6G7YLY2G/bundle.json","state":"https://pith.science/pith/NJPUXRYRF65RGE236L6G7YLY2G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NJPUXRYRF65RGE236L6G7YLY2G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NJPUXRYRF65RGE236L6G7YLY2G","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":"b2b091433ca5315bdf940b7c025d8d988301582400259a0d93748f6367547baa","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T21:36:00Z","title_canon_sha256":"902076e8b79ba57fd8457588baa84cd3bd64699d47b883426e9d426057b2bbb1"},"schema_version":"1.0","source":{"id":"2407.13906","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.13906","created_at":"2026-07-05T08:45:55Z"},{"alias_kind":"arxiv_version","alias_value":"2407.13906v1","created_at":"2026-07-05T08:45:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13906","created_at":"2026-07-05T08:45:55Z"},{"alias_kind":"pith_short_12","alias_value":"NJPUXRYRF65R","created_at":"2026-07-05T08:45:55Z"},{"alias_kind":"pith_short_16","alias_value":"NJPUXRYRF65RGE23","created_at":"2026-07-05T08:45:55Z"},{"alias_kind":"pith_short_8","alias_value":"NJPUXRYR","created_at":"2026-07-05T08:45:55Z"}],"graph_snapshots":[{"event_id":"sha256:346dadcdd8a367db6d642c7da6bb69be0d9f03bb823ea5678d569c4bc9a7fb25","target":"graph","created_at":"2026-07-05T08:45:55Z","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/2407.13906/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper addresses the challenges of efficiently fine-tuning large language models (LLMs) by exploring data efficiency and hyperparameter optimization. We investigate the minimum data required for effective fine-tuning and propose a novel hyperparameter optimization method that leverages early-stage model performance. Our experiments demonstrate that fine-tuning with as few as 200 samples can improve model accuracy from 70\\% to 88\\% in a product attribute extraction task. We identify a saturation point of approximately 6,500 samples, beyond which additional data yields diminishing returns. O","authors_text":"Guan Wang, Michael Oliver","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T21:36:00Z","title":"Crafting Efficient Fine-Tuning Strategies for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13906","kind":"arxiv","version":1},"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:af6f10397bcc8da77736f1b6a235a812e478d7554db4d6514d74aeeba018ff16","target":"record","created_at":"2026-07-05T08:45:55Z","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":"b2b091433ca5315bdf940b7c025d8d988301582400259a0d93748f6367547baa","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T21:36:00Z","title_canon_sha256":"902076e8b79ba57fd8457588baa84cd3bd64699d47b883426e9d426057b2bbb1"},"schema_version":"1.0","source":{"id":"2407.13906","kind":"arxiv","version":1}},"canonical_sha256":"6a5f4bc7112fbb13135bf2fc6fe178d1bf9590398d188a6fc6485743dfbfe540","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a5f4bc7112fbb13135bf2fc6fe178d1bf9590398d188a6fc6485743dfbfe540","first_computed_at":"2026-07-05T08:45:55.312841Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:55.312841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dTv3JWkEmOTKyfTLNon4+KOSB0TgcPGb8YfMc5thYX59+r3yyv1ksj48bKU35OD3aPcxDqr7lerOOb9SwuFaCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:55.313339Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.13906","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af6f10397bcc8da77736f1b6a235a812e478d7554db4d6514d74aeeba018ff16","sha256:346dadcdd8a367db6d642c7da6bb69be0d9f03bb823ea5678d569c4bc9a7fb25"],"state_sha256":"eb07f0bf1d151f2ae200ede30c0fe652522e5276fa5f7b25b238bc34cfb0c785"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dFkI93LDMfw5Ea70+pJR4/8j4Usj7tE/I5EAO00Z0XSXdQ+ZUDiXZiCKc0IFquegkibgRP3/WRvc1OdY9oR1Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:32:07.138814Z","bundle_sha256":"3ac6e4864289bd0d092585c635dca8a70b853c7f9c79a901be1ad59d5dc32819"}}