{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:S5YS56JANCVUYKHPQTXX6LZJLF","short_pith_number":"pith:S5YS56JA","canonical_record":{"source":{"id":"2409.18412","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-27T03:00:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e03dd50328eb63c317a20541709576f139260d6cf4e60d9bb5079b8d683515e4","abstract_canon_sha256":"44d2e8b1c94e995054e40ca2c0f13640a092af268f8b3dd20f93c112c0f17fb6"},"schema_version":"1.0"},"canonical_sha256":"97712ef92068ab4c28ef84ef7f2f29595132c321f49704c786744884f0bd1370","source":{"kind":"arxiv","id":"2409.18412","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.18412","created_at":"2026-07-05T09:34:20Z"},{"alias_kind":"arxiv_version","alias_value":"2409.18412v3","created_at":"2026-07-05T09:34:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18412","created_at":"2026-07-05T09:34:20Z"},{"alias_kind":"pith_short_12","alias_value":"S5YS56JANCVU","created_at":"2026-07-05T09:34:20Z"},{"alias_kind":"pith_short_16","alias_value":"S5YS56JANCVUYKHP","created_at":"2026-07-05T09:34:20Z"},{"alias_kind":"pith_short_8","alias_value":"S5YS56JA","created_at":"2026-07-05T09:34:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:S5YS56JANCVUYKHPQTXX6LZJLF","target":"record","payload":{"canonical_record":{"source":{"id":"2409.18412","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-27T03:00:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e03dd50328eb63c317a20541709576f139260d6cf4e60d9bb5079b8d683515e4","abstract_canon_sha256":"44d2e8b1c94e995054e40ca2c0f13640a092af268f8b3dd20f93c112c0f17fb6"},"schema_version":"1.0"},"canonical_sha256":"97712ef92068ab4c28ef84ef7f2f29595132c321f49704c786744884f0bd1370","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:20.183257Z","signature_b64":"soyFvpf18UoDUP/ft/UJ9adnNA7nfZxbWmvtmsUUL63SYccC54NaCjmKj64q9SzOv8FN1hO4CxMHr8/nt06ZAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97712ef92068ab4c28ef84ef7f2f29595132c321f49704c786744884f0bd1370","last_reissued_at":"2026-07-05T09:34:20.182770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:20.182770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.18412","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:34:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xCBhlfLBvq09Qx3RnjAcXIN4vWvgwJ9rqWf8zLK3Pk5ClsGW4gNRKuemIhBjaJXkRUe0fGC7J3g99q6rCeCyAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T15:10:37.716887Z"},"content_sha256":"91c24bc225f0b71f050ab912e6ce422052b2b8e80b19aaaa8565909c9b67b2a8","schema_version":"1.0","event_id":"sha256:91c24bc225f0b71f050ab912e6ce422052b2b8e80b19aaaa8565909c9b67b2a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:S5YS56JANCVUYKHPQTXX6LZJLF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SciDFM: A Large Language Model with Mixture-of-Experts for Science","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Baocai Chen, Da Ma, Danyu Luo, Kai Yu, Liangtai Sun, Lu Chen, Su Zhu, Xin Chen, Zhennan Shen, Zihan Zhao","submitted_at":"2024-09-27T03:00:29Z","abstract_excerpt":"Recently, there has been a significant upsurge of interest in leveraging large language models (LLMs) to assist scientific discovery. However, most LLMs only focus on general science, while they lack domain-specific knowledge, such as chemical molecules and amino acid sequences. To bridge these gaps, we introduce SciDFM, a mixture-of-experts LLM, which is trained from scratch and is able to conduct college-level scientific reasoning and understand molecules and amino acid sequences. We collect a large-scale training corpus containing numerous scientific papers and books from different discipli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18412","kind":"arxiv","version":3},"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/2409.18412/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":"2026-07-05T09:34:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s2fLrRokY0vIStcFEhmnspv52sKljPcv2jpuesTBk/cT/qv1PIEZPN23rMFwsuypvoMarTBDcCNFB0QliNzXDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T15:10:37.717818Z"},"content_sha256":"2874610615656c9c8acdf5fc50b51aaa7b3290ff494a0a59d0a4f85ca8b961d6","schema_version":"1.0","event_id":"sha256:2874610615656c9c8acdf5fc50b51aaa7b3290ff494a0a59d0a4f85ca8b961d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S5YS56JANCVUYKHPQTXX6LZJLF/bundle.json","state_url":"https://pith.science/pith/S5YS56JANCVUYKHPQTXX6LZJLF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S5YS56JANCVUYKHPQTXX6LZJLF/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":"2026-08-20T15:10:37Z","links":{"resolver":"https://pith.science/pith/S5YS56JANCVUYKHPQTXX6LZJLF","bundle":"https://pith.science/pith/S5YS56JANCVUYKHPQTXX6LZJLF/bundle.json","state":"https://pith.science/pith/S5YS56JANCVUYKHPQTXX6LZJLF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S5YS56JANCVUYKHPQTXX6LZJLF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:S5YS56JANCVUYKHPQTXX6LZJLF","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":"44d2e8b1c94e995054e40ca2c0f13640a092af268f8b3dd20f93c112c0f17fb6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-27T03:00:29Z","title_canon_sha256":"e03dd50328eb63c317a20541709576f139260d6cf4e60d9bb5079b8d683515e4"},"schema_version":"1.0","source":{"id":"2409.18412","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.18412","created_at":"2026-07-05T09:34:20Z"},{"alias_kind":"arxiv_version","alias_value":"2409.18412v3","created_at":"2026-07-05T09:34:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18412","created_at":"2026-07-05T09:34:20Z"},{"alias_kind":"pith_short_12","alias_value":"S5YS56JANCVU","created_at":"2026-07-05T09:34:20Z"},{"alias_kind":"pith_short_16","alias_value":"S5YS56JANCVUYKHP","created_at":"2026-07-05T09:34:20Z"},{"alias_kind":"pith_short_8","alias_value":"S5YS56JA","created_at":"2026-07-05T09:34:20Z"}],"graph_snapshots":[{"event_id":"sha256:2874610615656c9c8acdf5fc50b51aaa7b3290ff494a0a59d0a4f85ca8b961d6","target":"graph","created_at":"2026-07-05T09:34:20Z","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/2409.18412/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, there has been a significant upsurge of interest in leveraging large language models (LLMs) to assist scientific discovery. However, most LLMs only focus on general science, while they lack domain-specific knowledge, such as chemical molecules and amino acid sequences. To bridge these gaps, we introduce SciDFM, a mixture-of-experts LLM, which is trained from scratch and is able to conduct college-level scientific reasoning and understand molecules and amino acid sequences. We collect a large-scale training corpus containing numerous scientific papers and books from different discipli","authors_text":"Baocai Chen, Da Ma, Danyu Luo, Kai Yu, Liangtai Sun, Lu Chen, Su Zhu, Xin Chen, Zhennan Shen, Zihan Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-27T03:00:29Z","title":"SciDFM: A Large Language Model with Mixture-of-Experts for Science"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18412","kind":"arxiv","version":3},"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":"sha256:91c24bc225f0b71f050ab912e6ce422052b2b8e80b19aaaa8565909c9b67b2a8","target":"record","created_at":"2026-07-05T09:34:20Z","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":"44d2e8b1c94e995054e40ca2c0f13640a092af268f8b3dd20f93c112c0f17fb6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-27T03:00:29Z","title_canon_sha256":"e03dd50328eb63c317a20541709576f139260d6cf4e60d9bb5079b8d683515e4"},"schema_version":"1.0","source":{"id":"2409.18412","kind":"arxiv","version":3}},"canonical_sha256":"97712ef92068ab4c28ef84ef7f2f29595132c321f49704c786744884f0bd1370","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97712ef92068ab4c28ef84ef7f2f29595132c321f49704c786744884f0bd1370","first_computed_at":"2026-07-05T09:34:20.182770Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:34:20.182770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"soyFvpf18UoDUP/ft/UJ9adnNA7nfZxbWmvtmsUUL63SYccC54NaCjmKj64q9SzOv8FN1hO4CxMHr8/nt06ZAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:34:20.183257Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.18412","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91c24bc225f0b71f050ab912e6ce422052b2b8e80b19aaaa8565909c9b67b2a8","sha256:2874610615656c9c8acdf5fc50b51aaa7b3290ff494a0a59d0a4f85ca8b961d6"],"state_sha256":"2c0f636366cc9c7b693e98a7497ad5a39af4dabc2595c0374877ec44e20572d9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zwvgQut1CNHMShLf6iWnLy69aAPiDpYM3xH8VmvWilWsi7JXzs2VEyxuxCiVvxz1LlnoK9DadF6hk6v2gWSWAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T15:10:37.723164Z","bundle_sha256":"c740f2c07b9de2e91ffe5347561a43dfb77d4bbce927c9df91fb8c9040be26b4"}}