{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SLSBCYFWVSYWN57SRVZACWMZ5O","short_pith_number":"pith:SLSBCYFW","canonical_record":{"source":{"id":"2410.05639","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-08T02:42:56Z","cross_cats_sorted":[],"title_canon_sha256":"6f7c02e198cc03bc83f49cadfdbf4b57fefcf54fd1849c9a0984330788846186","abstract_canon_sha256":"554065756d1ee5224c9b7a17a7ba1a564122a3fbeabed1c7b6fff0d7f435091a"},"schema_version":"1.0"},"canonical_sha256":"92e41160b6acb166f7f28d72015999eba888fa9b18ba40aa7f24b75bd6c1865a","source":{"kind":"arxiv","id":"2410.05639","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.05639","created_at":"2026-07-05T09:18:31Z"},{"alias_kind":"arxiv_version","alias_value":"2410.05639v1","created_at":"2026-07-05T09:18:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05639","created_at":"2026-07-05T09:18:31Z"},{"alias_kind":"pith_short_12","alias_value":"SLSBCYFWVSYW","created_at":"2026-07-05T09:18:31Z"},{"alias_kind":"pith_short_16","alias_value":"SLSBCYFWVSYWN57S","created_at":"2026-07-05T09:18:31Z"},{"alias_kind":"pith_short_8","alias_value":"SLSBCYFW","created_at":"2026-07-05T09:18:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SLSBCYFWVSYWN57SRVZACWMZ5O","target":"record","payload":{"canonical_record":{"source":{"id":"2410.05639","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-08T02:42:56Z","cross_cats_sorted":[],"title_canon_sha256":"6f7c02e198cc03bc83f49cadfdbf4b57fefcf54fd1849c9a0984330788846186","abstract_canon_sha256":"554065756d1ee5224c9b7a17a7ba1a564122a3fbeabed1c7b6fff0d7f435091a"},"schema_version":"1.0"},"canonical_sha256":"92e41160b6acb166f7f28d72015999eba888fa9b18ba40aa7f24b75bd6c1865a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:31.281451Z","signature_b64":"WxybK7ROe7X90LFXvxSKfjcFvuRWHdpuIPwsGlMF+QWiGcZduC/cNNhbTARqsdnIJPuGWDXszcEiFRK9LujUBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92e41160b6acb166f7f28d72015999eba888fa9b18ba40aa7f24b75bd6c1865a","last_reissued_at":"2026-07-05T09:18:31.280976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:31.280976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.05639","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":"2026-07-05T09:18:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CdNo9aLwDAMe+4cIjCP+WvWB/NdjLpJqZ8MZWg7ndgKSBlA0bJRn3GvL9S00JM4HYKB+/5Op+JTKEbzLQB/5Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T08:34:57.818997Z"},"content_sha256":"defadd5b303e92ddf4c570d6e4329366e36b3e304b11bd52329caac0bd081297","schema_version":"1.0","event_id":"sha256:defadd5b303e92ddf4c570d6e4329366e36b3e304b11bd52329caac0bd081297"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SLSBCYFWVSYWN57SRVZACWMZ5O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DecorateLM: Data Engineering through Corpus Rating, Tagging, and Editing with Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jie Cai, Jie Zhou, Maosong Sun, Ranchi Zhao, Shengding Hu, Yifan Zhang, Yunqi Ba, Zhen Leng Thai, Zhiyuan Liu","submitted_at":"2024-10-08T02:42:56Z","abstract_excerpt":"The performance of Large Language Models (LLMs) is substantially influenced by the pretraining corpus, which consists of vast quantities of unsupervised data processed by the models. Despite its critical role in model performance, ensuring the quality of this data is challenging due to its sheer volume and the absence of sample-level quality annotations and enhancements. In this paper, we introduce DecorateLM, a data engineering method designed to refine the pretraining corpus through data rating, tagging and editing. Specifically, DecorateLM rates texts against quality criteria, tags texts wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05639","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/2410.05639/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":"2026-07-05T09:18:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bGcQa+pVFVaV9yBF7Toa9WMxoAJ5XuP4GND9zB0YTvFfxF5knlOsf/fNh18bqLl7c3pRjCWrk7yRdkDjAKakCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T08:34:57.819555Z"},"content_sha256":"e6c8c446129a5c3a6f8d8608225a68181d565b2f959ad7de7b9d6c664fde9189","schema_version":"1.0","event_id":"sha256:e6c8c446129a5c3a6f8d8608225a68181d565b2f959ad7de7b9d6c664fde9189"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SLSBCYFWVSYWN57SRVZACWMZ5O/bundle.json","state_url":"https://pith.science/pith/SLSBCYFWVSYWN57SRVZACWMZ5O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SLSBCYFWVSYWN57SRVZACWMZ5O/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":"2026-08-18T08:34:57Z","links":{"resolver":"https://pith.science/pith/SLSBCYFWVSYWN57SRVZACWMZ5O","bundle":"https://pith.science/pith/SLSBCYFWVSYWN57SRVZACWMZ5O/bundle.json","state":"https://pith.science/pith/SLSBCYFWVSYWN57SRVZACWMZ5O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SLSBCYFWVSYWN57SRVZACWMZ5O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SLSBCYFWVSYWN57SRVZACWMZ5O","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":"554065756d1ee5224c9b7a17a7ba1a564122a3fbeabed1c7b6fff0d7f435091a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-08T02:42:56Z","title_canon_sha256":"6f7c02e198cc03bc83f49cadfdbf4b57fefcf54fd1849c9a0984330788846186"},"schema_version":"1.0","source":{"id":"2410.05639","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.05639","created_at":"2026-07-05T09:18:31Z"},{"alias_kind":"arxiv_version","alias_value":"2410.05639v1","created_at":"2026-07-05T09:18:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05639","created_at":"2026-07-05T09:18:31Z"},{"alias_kind":"pith_short_12","alias_value":"SLSBCYFWVSYW","created_at":"2026-07-05T09:18:31Z"},{"alias_kind":"pith_short_16","alias_value":"SLSBCYFWVSYWN57S","created_at":"2026-07-05T09:18:31Z"},{"alias_kind":"pith_short_8","alias_value":"SLSBCYFW","created_at":"2026-07-05T09:18:31Z"}],"graph_snapshots":[{"event_id":"sha256:e6c8c446129a5c3a6f8d8608225a68181d565b2f959ad7de7b9d6c664fde9189","target":"graph","created_at":"2026-07-05T09:18:31Z","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/2410.05639/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The performance of Large Language Models (LLMs) is substantially influenced by the pretraining corpus, which consists of vast quantities of unsupervised data processed by the models. Despite its critical role in model performance, ensuring the quality of this data is challenging due to its sheer volume and the absence of sample-level quality annotations and enhancements. In this paper, we introduce DecorateLM, a data engineering method designed to refine the pretraining corpus through data rating, tagging and editing. Specifically, DecorateLM rates texts against quality criteria, tags texts wi","authors_text":"Jie Cai, Jie Zhou, Maosong Sun, Ranchi Zhao, Shengding Hu, Yifan Zhang, Yunqi Ba, Zhen Leng Thai, Zhiyuan Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-08T02:42:56Z","title":"DecorateLM: Data Engineering through Corpus Rating, Tagging, and Editing with Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05639","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:defadd5b303e92ddf4c570d6e4329366e36b3e304b11bd52329caac0bd081297","target":"record","created_at":"2026-07-05T09:18:31Z","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":"554065756d1ee5224c9b7a17a7ba1a564122a3fbeabed1c7b6fff0d7f435091a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-08T02:42:56Z","title_canon_sha256":"6f7c02e198cc03bc83f49cadfdbf4b57fefcf54fd1849c9a0984330788846186"},"schema_version":"1.0","source":{"id":"2410.05639","kind":"arxiv","version":1}},"canonical_sha256":"92e41160b6acb166f7f28d72015999eba888fa9b18ba40aa7f24b75bd6c1865a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92e41160b6acb166f7f28d72015999eba888fa9b18ba40aa7f24b75bd6c1865a","first_computed_at":"2026-07-05T09:18:31.280976Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:18:31.280976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WxybK7ROe7X90LFXvxSKfjcFvuRWHdpuIPwsGlMF+QWiGcZduC/cNNhbTARqsdnIJPuGWDXszcEiFRK9LujUBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:18:31.281451Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.05639","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:defadd5b303e92ddf4c570d6e4329366e36b3e304b11bd52329caac0bd081297","sha256:e6c8c446129a5c3a6f8d8608225a68181d565b2f959ad7de7b9d6c664fde9189"],"state_sha256":"f8bdf44d5596bc8f0b9caa81d1922620aacc8a15fb5cb548ce3de50637de2f86"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R6Xd1XXwAL0iMoqL3bm3j3YnxOhDiodTLxR2uwzMDwf2Z2JWMIj2+XW/NQfTdXxiFBsjeBx+nCOfR8sbDgXqBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T08:34:57.823500Z","bundle_sha256":"9289f6079449f9ca17be3294da643214a0ff7b7f90b3a546e912ede35e6522a5"}}