{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:X4XJQWCGQCLJFNL6SNFNAY6ABT","short_pith_number":"pith:X4XJQWCG","canonical_record":{"source":{"id":"2309.13079","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-21T09:02:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"88e4b4f0fdd8135f63da29be3b16e2c91e06e0ebb2f994f0aa60629eaa321a02","abstract_canon_sha256":"6c291eb12a729080774540c6e8168b6295c878bbc4aa4ab08948b71f038f70ef"},"schema_version":"1.0"},"canonical_sha256":"bf2e985846809692b57e934ad063c00cc844477636c3909f2c6657ad27005ec5","source":{"kind":"arxiv","id":"2309.13079","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.13079","created_at":"2026-07-05T06:54:23Z"},{"alias_kind":"arxiv_version","alias_value":"2309.13079v2","created_at":"2026-07-05T06:54:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13079","created_at":"2026-07-05T06:54:23Z"},{"alias_kind":"pith_short_12","alias_value":"X4XJQWCGQCLJ","created_at":"2026-07-05T06:54:23Z"},{"alias_kind":"pith_short_16","alias_value":"X4XJQWCGQCLJFNL6","created_at":"2026-07-05T06:54:23Z"},{"alias_kind":"pith_short_8","alias_value":"X4XJQWCG","created_at":"2026-07-05T06:54:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:X4XJQWCGQCLJFNL6SNFNAY6ABT","target":"record","payload":{"canonical_record":{"source":{"id":"2309.13079","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-21T09:02:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"88e4b4f0fdd8135f63da29be3b16e2c91e06e0ebb2f994f0aa60629eaa321a02","abstract_canon_sha256":"6c291eb12a729080774540c6e8168b6295c878bbc4aa4ab08948b71f038f70ef"},"schema_version":"1.0"},"canonical_sha256":"bf2e985846809692b57e934ad063c00cc844477636c3909f2c6657ad27005ec5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:23.712913Z","signature_b64":"c+QyL17B9nq/lBfIMjLROtyA7jcxXOv47P54cEMetzZJ7PhKRd7yoZwQIEc07PROB8TjZxr0Yb5wOMCPxeRSCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf2e985846809692b57e934ad063c00cc844477636c3909f2c6657ad27005ec5","last_reissued_at":"2026-07-05T06:54:23.712501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:23.712501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.13079","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:54:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3MnWkMcpxIkVV6ZVwgJHuP5R+FSoZz7uH2qZhePUC17XCMwrTJvYciMVghJrBE9btMgT0efbL916igt7xGM7AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T03:29:14.869486Z"},"content_sha256":"1c65395a30d66814670e5bf920d49f979beb0dd1afd2d9446649e09033042197","schema_version":"1.0","event_id":"sha256:1c65395a30d66814670e5bf920d49f979beb0dd1afd2d9446649e09033042197"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:X4XJQWCGQCLJFNL6SNFNAY6ABT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MiChao-HuaFen 1.0: A Specialized Pre-trained Corpus Dataset for Domain-specific Large Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Conghui He, Fang Wang, Fukai Shang, Jun Wang, Rui Xu, Wei Li, Yao Li, Yidong Liu","submitted_at":"2023-09-21T09:02:28Z","abstract_excerpt":"With the advancement of deep learning technologies, general-purpose large models such as GPT-4 have demonstrated exceptional capabilities across various domains. Nevertheless, there remains a demand for high-quality, domain-specific outputs in areas like healthcare, law, and finance. This paper first evaluates the existing large models for specialized domains and discusses their limitations. To cater to the specific needs of certain domains, we introduce the ``MiChao-HuaFen 1.0'' pre-trained corpus dataset, tailored for the news and governmental sectors. The dataset, sourced from publicly avai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13079","kind":"arxiv","version":2},"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/2309.13079/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":"2026-07-05T06:54:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"grcusWj5/bGEJFnaoRQNM0TcNDvn24VIsMI4yL5jaSWLtY9dLIW9j1qx3dzJJCIChO0WiE3Fmdaq+XchpmJhDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T03:29:14.869990Z"},"content_sha256":"b8034da71e4b8451a47fd9595f10c731e012f9b8856ceeec625dbc47f1173641","schema_version":"1.0","event_id":"sha256:b8034da71e4b8451a47fd9595f10c731e012f9b8856ceeec625dbc47f1173641"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X4XJQWCGQCLJFNL6SNFNAY6ABT/bundle.json","state_url":"https://pith.science/pith/X4XJQWCGQCLJFNL6SNFNAY6ABT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X4XJQWCGQCLJFNL6SNFNAY6ABT/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":"2026-08-21T03:29:14Z","links":{"resolver":"https://pith.science/pith/X4XJQWCGQCLJFNL6SNFNAY6ABT","bundle":"https://pith.science/pith/X4XJQWCGQCLJFNL6SNFNAY6ABT/bundle.json","state":"https://pith.science/pith/X4XJQWCGQCLJFNL6SNFNAY6ABT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X4XJQWCGQCLJFNL6SNFNAY6ABT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:X4XJQWCGQCLJFNL6SNFNAY6ABT","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":"6c291eb12a729080774540c6e8168b6295c878bbc4aa4ab08948b71f038f70ef","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-21T09:02:28Z","title_canon_sha256":"88e4b4f0fdd8135f63da29be3b16e2c91e06e0ebb2f994f0aa60629eaa321a02"},"schema_version":"1.0","source":{"id":"2309.13079","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.13079","created_at":"2026-07-05T06:54:23Z"},{"alias_kind":"arxiv_version","alias_value":"2309.13079v2","created_at":"2026-07-05T06:54:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13079","created_at":"2026-07-05T06:54:23Z"},{"alias_kind":"pith_short_12","alias_value":"X4XJQWCGQCLJ","created_at":"2026-07-05T06:54:23Z"},{"alias_kind":"pith_short_16","alias_value":"X4XJQWCGQCLJFNL6","created_at":"2026-07-05T06:54:23Z"},{"alias_kind":"pith_short_8","alias_value":"X4XJQWCG","created_at":"2026-07-05T06:54:23Z"}],"graph_snapshots":[{"event_id":"sha256:b8034da71e4b8451a47fd9595f10c731e012f9b8856ceeec625dbc47f1173641","target":"graph","created_at":"2026-07-05T06:54:23Z","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/2309.13079/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the advancement of deep learning technologies, general-purpose large models such as GPT-4 have demonstrated exceptional capabilities across various domains. Nevertheless, there remains a demand for high-quality, domain-specific outputs in areas like healthcare, law, and finance. This paper first evaluates the existing large models for specialized domains and discusses their limitations. To cater to the specific needs of certain domains, we introduce the ``MiChao-HuaFen 1.0'' pre-trained corpus dataset, tailored for the news and governmental sectors. The dataset, sourced from publicly avai","authors_text":"Conghui He, Fang Wang, Fukai Shang, Jun Wang, Rui Xu, Wei Li, Yao Li, Yidong Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-21T09:02:28Z","title":"MiChao-HuaFen 1.0: A Specialized Pre-trained Corpus Dataset for Domain-specific Large Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13079","kind":"arxiv","version":2},"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":"sha256:1c65395a30d66814670e5bf920d49f979beb0dd1afd2d9446649e09033042197","target":"record","created_at":"2026-07-05T06:54:23Z","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":"6c291eb12a729080774540c6e8168b6295c878bbc4aa4ab08948b71f038f70ef","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-21T09:02:28Z","title_canon_sha256":"88e4b4f0fdd8135f63da29be3b16e2c91e06e0ebb2f994f0aa60629eaa321a02"},"schema_version":"1.0","source":{"id":"2309.13079","kind":"arxiv","version":2}},"canonical_sha256":"bf2e985846809692b57e934ad063c00cc844477636c3909f2c6657ad27005ec5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf2e985846809692b57e934ad063c00cc844477636c3909f2c6657ad27005ec5","first_computed_at":"2026-07-05T06:54:23.712501Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:54:23.712501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c+QyL17B9nq/lBfIMjLROtyA7jcxXOv47P54cEMetzZJ7PhKRd7yoZwQIEc07PROB8TjZxr0Yb5wOMCPxeRSCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:54:23.712913Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.13079","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c65395a30d66814670e5bf920d49f979beb0dd1afd2d9446649e09033042197","sha256:b8034da71e4b8451a47fd9595f10c731e012f9b8856ceeec625dbc47f1173641"],"state_sha256":"9e8da37614d6287e5c127586eb32d922ef1c3d203b768b458db04ddcabb3d500"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TRZtkVaYFzd1DMcnHDNBb3Nzr/WoKQhXkLynKjH9UQC4SiLlbm96cREwdRCS7lvpkzwI5MgucsXqHa3eSMZeCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T03:29:14.874944Z","bundle_sha256":"f31fb279c8c70b2fe05c36794db3356fdf96e89d053f4d0f576fc0d3b355160a"}}