{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6YAQWWVVYEILXDKOTQNYTXHCSJ","short_pith_number":"pith:6YAQWWVV","canonical_record":{"source":{"id":"2408.08003","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-15T08:12:52Z","cross_cats_sorted":[],"title_canon_sha256":"1642851bc1e98e51f017f69b8e3545964ebdd032dbc7e242051b05684ea192c6","abstract_canon_sha256":"c5af98f83c0b5da178b22400ad2e7ea09b441177283194024dc6e86831726f65"},"schema_version":"1.0"},"canonical_sha256":"f6010b5ab5c110bb8d4e9c1b89dce29246f867cdf69f4339e508874854810bf8","source":{"kind":"arxiv","id":"2408.08003","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.08003","created_at":"2026-07-05T08:55:43Z"},{"alias_kind":"arxiv_version","alias_value":"2408.08003v1","created_at":"2026-07-05T08:55:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08003","created_at":"2026-07-05T08:55:43Z"},{"alias_kind":"pith_short_12","alias_value":"6YAQWWVVYEIL","created_at":"2026-07-05T08:55:43Z"},{"alias_kind":"pith_short_16","alias_value":"6YAQWWVVYEILXDKO","created_at":"2026-07-05T08:55:43Z"},{"alias_kind":"pith_short_8","alias_value":"6YAQWWVV","created_at":"2026-07-05T08:55:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6YAQWWVVYEILXDKOTQNYTXHCSJ","target":"record","payload":{"canonical_record":{"source":{"id":"2408.08003","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-15T08:12:52Z","cross_cats_sorted":[],"title_canon_sha256":"1642851bc1e98e51f017f69b8e3545964ebdd032dbc7e242051b05684ea192c6","abstract_canon_sha256":"c5af98f83c0b5da178b22400ad2e7ea09b441177283194024dc6e86831726f65"},"schema_version":"1.0"},"canonical_sha256":"f6010b5ab5c110bb8d4e9c1b89dce29246f867cdf69f4339e508874854810bf8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:43.110769Z","signature_b64":"PzuLnexQJtnvo8dupo9wIw4vDDqT1pEdKt78xf51IsZiQMgybGB78cYw4cuIaAfK/4QShzchOd9p0XlE4HeNCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6010b5ab5c110bb8d4e9c1b89dce29246f867cdf69f4339e508874854810bf8","last_reissued_at":"2026-07-05T08:55:43.110427Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:43.110427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.08003","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":"2026-07-05T08:55:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4IpWFLH2oq9LN7+PVRPA9Sw+wFmwyInmI1gg3wqx003KSeYXELegGpIaBR9l5KO3YvkHELoRWeon4o7fF6lJBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:05:52.998520Z"},"content_sha256":"e587296dddf34a66c2599f04aa34b8ca35d02939d8af75977fce91555a141a0b","schema_version":"1.0","event_id":"sha256:e587296dddf34a66c2599f04aa34b8ca35d02939d8af75977fce91555a141a0b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6YAQWWVVYEILXDKOTQNYTXHCSJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Web-Crawled Data for High-Quality Fine-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenglin Jiang, Jing Zhou, Wei Shen, Xiaonan He, Xiao Zhou","submitted_at":"2024-08-15T08:12:52Z","abstract_excerpt":"Most large language models are fine-tuned using either expensive human-annotated data or GPT-4 generated data which cannot guarantee performance in certain domains. We argue that although the web-crawled data often has formatting errors causing semantic inaccuracies, it can still serve as a valuable source for high-quality supervised fine-tuning in specific domains without relying on advanced models like GPT-4. To this end, we create a paired training dataset automatically by aligning web-crawled data with a smaller set of high-quality data. By training a language model on this dataset, we can"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08003","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/2408.08003/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":"2026-07-05T08:55:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"64jQ0OHCi5gnqx5xpR8PImRu5E1xw7h0jBGa2Fu0lSv0wXok61zilUzYEjLizWIiWlo15R2lfVLZ7C7+uiSBBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:05:52.999645Z"},"content_sha256":"37c3d814dd1ccd07c348c10eee2c755f87e415d531374b1353da1a201f12b613","schema_version":"1.0","event_id":"sha256:37c3d814dd1ccd07c348c10eee2c755f87e415d531374b1353da1a201f12b613"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6YAQWWVVYEILXDKOTQNYTXHCSJ/bundle.json","state_url":"https://pith.science/pith/6YAQWWVVYEILXDKOTQNYTXHCSJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6YAQWWVVYEILXDKOTQNYTXHCSJ/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":"2026-08-09T13:05:53Z","links":{"resolver":"https://pith.science/pith/6YAQWWVVYEILXDKOTQNYTXHCSJ","bundle":"https://pith.science/pith/6YAQWWVVYEILXDKOTQNYTXHCSJ/bundle.json","state":"https://pith.science/pith/6YAQWWVVYEILXDKOTQNYTXHCSJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6YAQWWVVYEILXDKOTQNYTXHCSJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6YAQWWVVYEILXDKOTQNYTXHCSJ","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":"c5af98f83c0b5da178b22400ad2e7ea09b441177283194024dc6e86831726f65","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-15T08:12:52Z","title_canon_sha256":"1642851bc1e98e51f017f69b8e3545964ebdd032dbc7e242051b05684ea192c6"},"schema_version":"1.0","source":{"id":"2408.08003","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.08003","created_at":"2026-07-05T08:55:43Z"},{"alias_kind":"arxiv_version","alias_value":"2408.08003v1","created_at":"2026-07-05T08:55:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08003","created_at":"2026-07-05T08:55:43Z"},{"alias_kind":"pith_short_12","alias_value":"6YAQWWVVYEIL","created_at":"2026-07-05T08:55:43Z"},{"alias_kind":"pith_short_16","alias_value":"6YAQWWVVYEILXDKO","created_at":"2026-07-05T08:55:43Z"},{"alias_kind":"pith_short_8","alias_value":"6YAQWWVV","created_at":"2026-07-05T08:55:43Z"}],"graph_snapshots":[{"event_id":"sha256:37c3d814dd1ccd07c348c10eee2c755f87e415d531374b1353da1a201f12b613","target":"graph","created_at":"2026-07-05T08:55:43Z","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/2408.08003/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most large language models are fine-tuned using either expensive human-annotated data or GPT-4 generated data which cannot guarantee performance in certain domains. We argue that although the web-crawled data often has formatting errors causing semantic inaccuracies, it can still serve as a valuable source for high-quality supervised fine-tuning in specific domains without relying on advanced models like GPT-4. To this end, we create a paired training dataset automatically by aligning web-crawled data with a smaller set of high-quality data. By training a language model on this dataset, we can","authors_text":"Chenglin Jiang, Jing Zhou, Wei Shen, Xiaonan He, Xiao Zhou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-15T08:12:52Z","title":"Leveraging Web-Crawled Data for High-Quality Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08003","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:e587296dddf34a66c2599f04aa34b8ca35d02939d8af75977fce91555a141a0b","target":"record","created_at":"2026-07-05T08:55:43Z","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":"c5af98f83c0b5da178b22400ad2e7ea09b441177283194024dc6e86831726f65","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-15T08:12:52Z","title_canon_sha256":"1642851bc1e98e51f017f69b8e3545964ebdd032dbc7e242051b05684ea192c6"},"schema_version":"1.0","source":{"id":"2408.08003","kind":"arxiv","version":1}},"canonical_sha256":"f6010b5ab5c110bb8d4e9c1b89dce29246f867cdf69f4339e508874854810bf8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f6010b5ab5c110bb8d4e9c1b89dce29246f867cdf69f4339e508874854810bf8","first_computed_at":"2026-07-05T08:55:43.110427Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:55:43.110427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PzuLnexQJtnvo8dupo9wIw4vDDqT1pEdKt78xf51IsZiQMgybGB78cYw4cuIaAfK/4QShzchOd9p0XlE4HeNCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:55:43.110769Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.08003","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e587296dddf34a66c2599f04aa34b8ca35d02939d8af75977fce91555a141a0b","sha256:37c3d814dd1ccd07c348c10eee2c755f87e415d531374b1353da1a201f12b613"],"state_sha256":"84233eb67cbaf9a34ccfd923974859021397f60daeaa00c4b56b84eabf2ca55f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cP1LF3lx2Me4bs8o6HTgNlTaN15kC5co6TuA8QX1LftoPLe4XefVnf+tNxRyA27uapqbZjX54C3V0VGVO+/aCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T13:05:53.026735Z","bundle_sha256":"af87baeeb1b833a4b0d0b8fcaa6e5a09236f84c74a15df9f30110761e379561b"}}