{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:W6ANLQHOQCFVMSK2I3OHIM3GON","short_pith_number":"pith:W6ANLQHO","canonical_record":{"source":{"id":"2307.05354","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-11T15:44:01Z","cross_cats_sorted":[],"title_canon_sha256":"8d5190fd47d5f0694a54b5bf60b268f52ca76e453a4af815bb879dca1af3bbb8","abstract_canon_sha256":"7c765e33b100c2d316acd6fc0a79efc38b6366d9b95e55d4de295a7a6efcbf44"},"schema_version":"1.0"},"canonical_sha256":"b780d5c0ee808b56495a46dc743366734709e09db6140d6f073c642115e44dd5","source":{"kind":"arxiv","id":"2307.05354","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.05354","created_at":"2026-07-05T06:29:56Z"},{"alias_kind":"arxiv_version","alias_value":"2307.05354v1","created_at":"2026-07-05T06:29:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.05354","created_at":"2026-07-05T06:29:56Z"},{"alias_kind":"pith_short_12","alias_value":"W6ANLQHOQCFV","created_at":"2026-07-05T06:29:56Z"},{"alias_kind":"pith_short_16","alias_value":"W6ANLQHOQCFVMSK2","created_at":"2026-07-05T06:29:56Z"},{"alias_kind":"pith_short_8","alias_value":"W6ANLQHO","created_at":"2026-07-05T06:29:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:W6ANLQHOQCFVMSK2I3OHIM3GON","target":"record","payload":{"canonical_record":{"source":{"id":"2307.05354","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-11T15:44:01Z","cross_cats_sorted":[],"title_canon_sha256":"8d5190fd47d5f0694a54b5bf60b268f52ca76e453a4af815bb879dca1af3bbb8","abstract_canon_sha256":"7c765e33b100c2d316acd6fc0a79efc38b6366d9b95e55d4de295a7a6efcbf44"},"schema_version":"1.0"},"canonical_sha256":"b780d5c0ee808b56495a46dc743366734709e09db6140d6f073c642115e44dd5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:29:56.375808Z","signature_b64":"aJ6fLkP6HM0MtiluOsH/MO9qQFElRVg16a+W/Qyik+0pM/AON6aLfZtRj1KHDngWUmXRJwpN3IILxzEGixEqAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b780d5c0ee808b56495a46dc743366734709e09db6140d6f073c642115e44dd5","last_reissued_at":"2026-07-05T06:29:56.375341Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:29:56.375341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.05354","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":"2026-07-05T06:29:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oIeZ+jXK6YwjAtM4Pc++1jk+PxWxsqR0/kgZ6EiHr8QF7EuObBGt5NmvVd2Jn58hLMw3jrJ6dPNmSlmHBcz7Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:56:10.070273Z"},"content_sha256":"4a32af48cc72ddfc1ae1c353b69fee8be17572923d14da275d3839370d4d9d99","schema_version":"1.0","event_id":"sha256:4a32af48cc72ddfc1ae1c353b69fee8be17572923d14da275d3839370d4d9d99"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:W6ANLQHOQCFVMSK2I3OHIM3GON","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GujiBERT and GujiGPT: Construction of Intelligent Information Processing Foundation Language Models for Ancient Texts","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin Li, Chang Liu, Dongbo Wang, Haotian Hu, Litao Lin, Liu Liu, Mengcheng Wu, Si Shen, Xiyu Wang, Xue Zhao, Zhixiao Zhao","submitted_at":"2023-07-11T15:44:01Z","abstract_excerpt":"In the context of the rapid development of large language models, we have meticulously trained and introduced the GujiBERT and GujiGPT language models, which are foundational models specifically designed for intelligent information processing of ancient texts. These models have been trained on an extensive dataset that encompasses both simplified and traditional Chinese characters, allowing them to effectively handle various natural language processing tasks related to ancient books, including but not limited to automatic sentence segmentation, punctuation, word segmentation, part-of-speech ta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.05354","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/2307.05354/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":"2026-07-05T06:29:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AmvBX1D7epeDxeEu5MtuDfB2KC6sPB9AbwmG3wqDDP5errbSHUCTlg/u7cqkT1KZaEOT/LxFlCwJ9OqSXnzNAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:56:10.070764Z"},"content_sha256":"d981ecb1dbab368b0b5bfe08e9e8cd1895a84784ba16cdb4e6561ce24bc45990","schema_version":"1.0","event_id":"sha256:d981ecb1dbab368b0b5bfe08e9e8cd1895a84784ba16cdb4e6561ce24bc45990"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W6ANLQHOQCFVMSK2I3OHIM3GON/bundle.json","state_url":"https://pith.science/pith/W6ANLQHOQCFVMSK2I3OHIM3GON/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W6ANLQHOQCFVMSK2I3OHIM3GON/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":"2026-08-08T20:56:10Z","links":{"resolver":"https://pith.science/pith/W6ANLQHOQCFVMSK2I3OHIM3GON","bundle":"https://pith.science/pith/W6ANLQHOQCFVMSK2I3OHIM3GON/bundle.json","state":"https://pith.science/pith/W6ANLQHOQCFVMSK2I3OHIM3GON/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W6ANLQHOQCFVMSK2I3OHIM3GON/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:W6ANLQHOQCFVMSK2I3OHIM3GON","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":"7c765e33b100c2d316acd6fc0a79efc38b6366d9b95e55d4de295a7a6efcbf44","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-11T15:44:01Z","title_canon_sha256":"8d5190fd47d5f0694a54b5bf60b268f52ca76e453a4af815bb879dca1af3bbb8"},"schema_version":"1.0","source":{"id":"2307.05354","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.05354","created_at":"2026-07-05T06:29:56Z"},{"alias_kind":"arxiv_version","alias_value":"2307.05354v1","created_at":"2026-07-05T06:29:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.05354","created_at":"2026-07-05T06:29:56Z"},{"alias_kind":"pith_short_12","alias_value":"W6ANLQHOQCFV","created_at":"2026-07-05T06:29:56Z"},{"alias_kind":"pith_short_16","alias_value":"W6ANLQHOQCFVMSK2","created_at":"2026-07-05T06:29:56Z"},{"alias_kind":"pith_short_8","alias_value":"W6ANLQHO","created_at":"2026-07-05T06:29:56Z"}],"graph_snapshots":[{"event_id":"sha256:d981ecb1dbab368b0b5bfe08e9e8cd1895a84784ba16cdb4e6561ce24bc45990","target":"graph","created_at":"2026-07-05T06:29:56Z","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/2307.05354/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the context of the rapid development of large language models, we have meticulously trained and introduced the GujiBERT and GujiGPT language models, which are foundational models specifically designed for intelligent information processing of ancient texts. These models have been trained on an extensive dataset that encompasses both simplified and traditional Chinese characters, allowing them to effectively handle various natural language processing tasks related to ancient books, including but not limited to automatic sentence segmentation, punctuation, word segmentation, part-of-speech ta","authors_text":"Bin Li, Chang Liu, Dongbo Wang, Haotian Hu, Litao Lin, Liu Liu, Mengcheng Wu, Si Shen, Xiyu Wang, Xue Zhao, Zhixiao Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-11T15:44:01Z","title":"GujiBERT and GujiGPT: Construction of Intelligent Information Processing Foundation Language Models for Ancient Texts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.05354","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":"sha256:4a32af48cc72ddfc1ae1c353b69fee8be17572923d14da275d3839370d4d9d99","target":"record","created_at":"2026-07-05T06:29:56Z","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":"7c765e33b100c2d316acd6fc0a79efc38b6366d9b95e55d4de295a7a6efcbf44","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-11T15:44:01Z","title_canon_sha256":"8d5190fd47d5f0694a54b5bf60b268f52ca76e453a4af815bb879dca1af3bbb8"},"schema_version":"1.0","source":{"id":"2307.05354","kind":"arxiv","version":1}},"canonical_sha256":"b780d5c0ee808b56495a46dc743366734709e09db6140d6f073c642115e44dd5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b780d5c0ee808b56495a46dc743366734709e09db6140d6f073c642115e44dd5","first_computed_at":"2026-07-05T06:29:56.375341Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:29:56.375341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aJ6fLkP6HM0MtiluOsH/MO9qQFElRVg16a+W/Qyik+0pM/AON6aLfZtRj1KHDngWUmXRJwpN3IILxzEGixEqAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:29:56.375808Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.05354","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a32af48cc72ddfc1ae1c353b69fee8be17572923d14da275d3839370d4d9d99","sha256:d981ecb1dbab368b0b5bfe08e9e8cd1895a84784ba16cdb4e6561ce24bc45990"],"state_sha256":"2aca398f47785d9220acf455e2e5388129e3492dd16014febdc7a30b3006c6db"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4uDs6+QobNa8LEEfGC5KBL5LpYo44HOdpR+g2EhRN4eyDId+fYBpVmD1qpGJfpHq+VMBsUTVWC7pXvhKN8hwDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:56:10.074133Z","bundle_sha256":"b0326db434e3ae1d922cdc0d61b449d9f5aab8954da94f3d9a4e258fd4383849"}}