{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JTPXM5RNKNPPPJ2POT6EK54COR","short_pith_number":"pith:JTPXM5RN","canonical_record":{"source":{"id":"2312.03360","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-06T08:55:55Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"506178855dd50c07b61c27aca2d7e759af27abd0e926ff6ae13654a9d89c44e4","abstract_canon_sha256":"1ac28e6da96be0336728e826d6bfd3c2a478c691c11d0ed910af624523494899"},"schema_version":"1.0"},"canonical_sha256":"4cdf76762d535ef7a74f74fc45778274498c93f2d2469139174f4073593d7061","source":{"kind":"arxiv","id":"2312.03360","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.03360","created_at":"2026-07-05T07:24:57Z"},{"alias_kind":"arxiv_version","alias_value":"2312.03360v2","created_at":"2026-07-05T07:24:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03360","created_at":"2026-07-05T07:24:57Z"},{"alias_kind":"pith_short_12","alias_value":"JTPXM5RNKNPP","created_at":"2026-07-05T07:24:57Z"},{"alias_kind":"pith_short_16","alias_value":"JTPXM5RNKNPPPJ2P","created_at":"2026-07-05T07:24:57Z"},{"alias_kind":"pith_short_8","alias_value":"JTPXM5RN","created_at":"2026-07-05T07:24:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JTPXM5RNKNPPPJ2POT6EK54COR","target":"record","payload":{"canonical_record":{"source":{"id":"2312.03360","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-06T08:55:55Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"506178855dd50c07b61c27aca2d7e759af27abd0e926ff6ae13654a9d89c44e4","abstract_canon_sha256":"1ac28e6da96be0336728e826d6bfd3c2a478c691c11d0ed910af624523494899"},"schema_version":"1.0"},"canonical_sha256":"4cdf76762d535ef7a74f74fc45778274498c93f2d2469139174f4073593d7061","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:57.406529Z","signature_b64":"N8jk0ASCIPThHfDJWZdfSgNEGBVDHNEUHwQQLYOHYk/2EPD8ZVAUgqv6f0yxWXkCPOYqrGacmBTLwGYXCJtqCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cdf76762d535ef7a74f74fc45778274498c93f2d2469139174f4073593d7061","last_reissued_at":"2026-07-05T07:24:57.406109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:57.406109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.03360","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":"2026-07-05T07:24:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"itQA/yE29KuMnNYC+duomt5BJJ7jMipU/QYjXOCdvonbuXV/MasNdZlQOajwc/jzQhM3o5HaRTpvxjK2xRHlCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T05:19:05.011163Z"},"content_sha256":"e7d85c2a6e4046ed5131b1f5d0d0a9b90d5fd43b8daed80692c1c0b590c266a3","schema_version":"1.0","event_id":"sha256:e7d85c2a6e4046ed5131b1f5d0d0a9b90d5fd43b8daed80692c1c0b590c266a3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JTPXM5RNKNPPPJ2POT6EK54COR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Teaching Specific Scientific Knowledge into Large Language Models through Additional Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Kan Hatakeyama-Sato, Shun Katakami, Teruaki Hayakawa, Yasuhiko Igarashi, Yuta Nabae","submitted_at":"2023-12-06T08:55:55Z","abstract_excerpt":"Through additional training, we explore embedding specialized scientific knowledge into the Llama 2 Large Language Model (LLM). Key findings reveal that effective knowledge integration requires reading texts from multiple perspectives, especially in instructional formats. We utilize text augmentation to tackle the scarcity of specialized texts, including style conversions and translations. Hyperparameter optimization proves crucial, with different size models (7b, 13b, and 70b) reasonably undergoing additional training. Validating our methods, we construct a dataset of 65,000 scientific papers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03360","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/2312.03360/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":"2026-07-05T07:24:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"26mJgrNy0ri53WktFx6ATtIol+smunTtb/AuHbo0Qd4nQ9OH3L6u8ShQAR5Apejrgt70nHtQc8syf+M0VlgzDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T05:19:05.011560Z"},"content_sha256":"b96ed412d2ca506f98e986acc538e09306ba9238344fa8275ed4cb5e4262b3b9","schema_version":"1.0","event_id":"sha256:b96ed412d2ca506f98e986acc538e09306ba9238344fa8275ed4cb5e4262b3b9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JTPXM5RNKNPPPJ2POT6EK54COR/bundle.json","state_url":"https://pith.science/pith/JTPXM5RNKNPPPJ2POT6EK54COR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JTPXM5RNKNPPPJ2POT6EK54COR/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":"2026-07-18T05:19:05Z","links":{"resolver":"https://pith.science/pith/JTPXM5RNKNPPPJ2POT6EK54COR","bundle":"https://pith.science/pith/JTPXM5RNKNPPPJ2POT6EK54COR/bundle.json","state":"https://pith.science/pith/JTPXM5RNKNPPPJ2POT6EK54COR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JTPXM5RNKNPPPJ2POT6EK54COR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JTPXM5RNKNPPPJ2POT6EK54COR","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":"1ac28e6da96be0336728e826d6bfd3c2a478c691c11d0ed910af624523494899","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-06T08:55:55Z","title_canon_sha256":"506178855dd50c07b61c27aca2d7e759af27abd0e926ff6ae13654a9d89c44e4"},"schema_version":"1.0","source":{"id":"2312.03360","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.03360","created_at":"2026-07-05T07:24:57Z"},{"alias_kind":"arxiv_version","alias_value":"2312.03360v2","created_at":"2026-07-05T07:24:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03360","created_at":"2026-07-05T07:24:57Z"},{"alias_kind":"pith_short_12","alias_value":"JTPXM5RNKNPP","created_at":"2026-07-05T07:24:57Z"},{"alias_kind":"pith_short_16","alias_value":"JTPXM5RNKNPPPJ2P","created_at":"2026-07-05T07:24:57Z"},{"alias_kind":"pith_short_8","alias_value":"JTPXM5RN","created_at":"2026-07-05T07:24:57Z"}],"graph_snapshots":[{"event_id":"sha256:b96ed412d2ca506f98e986acc538e09306ba9238344fa8275ed4cb5e4262b3b9","target":"graph","created_at":"2026-07-05T07:24:57Z","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/2312.03360/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Through additional training, we explore embedding specialized scientific knowledge into the Llama 2 Large Language Model (LLM). Key findings reveal that effective knowledge integration requires reading texts from multiple perspectives, especially in instructional formats. We utilize text augmentation to tackle the scarcity of specialized texts, including style conversions and translations. Hyperparameter optimization proves crucial, with different size models (7b, 13b, and 70b) reasonably undergoing additional training. Validating our methods, we construct a dataset of 65,000 scientific papers","authors_text":"Kan Hatakeyama-Sato, Shun Katakami, Teruaki Hayakawa, Yasuhiko Igarashi, Yuta Nabae","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-06T08:55:55Z","title":"Teaching Specific Scientific Knowledge into Large Language Models through Additional Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03360","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:e7d85c2a6e4046ed5131b1f5d0d0a9b90d5fd43b8daed80692c1c0b590c266a3","target":"record","created_at":"2026-07-05T07:24:57Z","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":"1ac28e6da96be0336728e826d6bfd3c2a478c691c11d0ed910af624523494899","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-06T08:55:55Z","title_canon_sha256":"506178855dd50c07b61c27aca2d7e759af27abd0e926ff6ae13654a9d89c44e4"},"schema_version":"1.0","source":{"id":"2312.03360","kind":"arxiv","version":2}},"canonical_sha256":"4cdf76762d535ef7a74f74fc45778274498c93f2d2469139174f4073593d7061","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4cdf76762d535ef7a74f74fc45778274498c93f2d2469139174f4073593d7061","first_computed_at":"2026-07-05T07:24:57.406109Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:24:57.406109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N8jk0ASCIPThHfDJWZdfSgNEGBVDHNEUHwQQLYOHYk/2EPD8ZVAUgqv6f0yxWXkCPOYqrGacmBTLwGYXCJtqCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:24:57.406529Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.03360","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7d85c2a6e4046ed5131b1f5d0d0a9b90d5fd43b8daed80692c1c0b590c266a3","sha256:b96ed412d2ca506f98e986acc538e09306ba9238344fa8275ed4cb5e4262b3b9"],"state_sha256":"92bb00d882b33c5852aa03aecbcb9a4c71bc5f5ef2dc316e3cc20fa6a83ca760"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eIqc7Rc739WijUvzEV2NPjEG5PYPd5Fybi4POXmcKpjcge4UoZnjf+Lhhx+NM3UeJycQDO4vfCdYb15f8W1vCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-18T05:19:05.014364Z","bundle_sha256":"69ac2988c82fa3899a9fae05ccdde82bd3a4d1778f10c8b1ef8cdc413b5e3b68"}}