{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HRY3L6OFY3LCIULXGKMRR6FDI7","short_pith_number":"pith:HRY3L6OF","canonical_record":{"source":{"id":"2412.19994","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.chem-ph","submitted_at":"2024-12-28T03:40:25Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"74e216168789202a52830ac9cf774a44ebc9e346f6d5987a775cb073d432dbee","abstract_canon_sha256":"139816554703f4266f3f4889aa35aa5b5e4d5d2737368fc2e0308baedeae931a"},"schema_version":"1.0"},"canonical_sha256":"3c71b5f9c5c6d6245177329918f8a347f6cec908f319ac90e79e9ccd90539bae","source":{"kind":"arxiv","id":"2412.19994","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19994","created_at":"2026-07-05T09:54:52Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19994v1","created_at":"2026-07-05T09:54:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19994","created_at":"2026-07-05T09:54:52Z"},{"alias_kind":"pith_short_12","alias_value":"HRY3L6OFY3LC","created_at":"2026-07-05T09:54:52Z"},{"alias_kind":"pith_short_16","alias_value":"HRY3L6OFY3LCIULX","created_at":"2026-07-05T09:54:52Z"},{"alias_kind":"pith_short_8","alias_value":"HRY3L6OF","created_at":"2026-07-05T09:54:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HRY3L6OFY3LCIULXGKMRR6FDI7","target":"record","payload":{"canonical_record":{"source":{"id":"2412.19994","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.chem-ph","submitted_at":"2024-12-28T03:40:25Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"74e216168789202a52830ac9cf774a44ebc9e346f6d5987a775cb073d432dbee","abstract_canon_sha256":"139816554703f4266f3f4889aa35aa5b5e4d5d2737368fc2e0308baedeae931a"},"schema_version":"1.0"},"canonical_sha256":"3c71b5f9c5c6d6245177329918f8a347f6cec908f319ac90e79e9ccd90539bae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:52.944599Z","signature_b64":"w2US7mwYTd3LK68iLmRfkg0pcq5v+LQtGrfj1D9leHT62Prcii/QUdTFXIEG7GCex9M7momCfcEaRy5BTQ5WCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c71b5f9c5c6d6245177329918f8a347f6cec908f319ac90e79e9ccd90539bae","last_reissued_at":"2026-07-05T09:54:52.944144Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:52.944144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.19994","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":"2026-07-05T09:54:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uuTUHH2Gxyc/hqCIat3Rj2fOlJ9g6SwWpysj82cLp7dweNfrqr9ARoKVAu2DqrT6swcwzVE2gHWsx8lkdaDgCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:25:03.551400Z"},"content_sha256":"4e1a1507959a6d947f1b351032e1c97cf166f1c1cdd7197e31a2d93f59db40e2","schema_version":"1.0","event_id":"sha256:4e1a1507959a6d947f1b351032e1c97cf166f1c1cdd7197e31a2d93f59db40e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HRY3L6OFY3LCIULXGKMRR6FDI7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Generalist to Specialist: A Survey of Large Language Models for Chemistry","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"physics.chem-ph","authors_text":"Kai Yu, Lu Chen, Xin Chen, Yang Han, Ziping Wan","submitted_at":"2024-12-28T03:40:25Z","abstract_excerpt":"Large Language Models (LLMs) have significantly transformed our daily life and established a new paradigm in natural language processing (NLP). However, the predominant pretraining of LLMs on extensive web-based texts remains insufficient for advanced scientific discovery, particularly in chemistry. The scarcity of specialized chemistry data, coupled with the complexity of multi-modal data such as 2D graph, 3D structure and spectrum, present distinct challenges. Although several studies have reviewed Pretrained Language Models (PLMs) in chemistry, there is a conspicuous absence of a systematic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19994","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/2412.19994/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":"2026-07-05T09:54:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EQDzIOOzPt8/187xuu72tuvI2Y3zTmH7zln83NXifcZr7TgyqvDAQU8OVhbH8lrstHyRyvcWXiRTABQHc8HWBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:25:03.552357Z"},"content_sha256":"fc40538a6bc86d3dedfed1ad3fc3e4a0a292e0de7586919f2981f3a86d4252b2","schema_version":"1.0","event_id":"sha256:fc40538a6bc86d3dedfed1ad3fc3e4a0a292e0de7586919f2981f3a86d4252b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HRY3L6OFY3LCIULXGKMRR6FDI7/bundle.json","state_url":"https://pith.science/pith/HRY3L6OFY3LCIULXGKMRR6FDI7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HRY3L6OFY3LCIULXGKMRR6FDI7/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":"2026-08-07T18:25:03Z","links":{"resolver":"https://pith.science/pith/HRY3L6OFY3LCIULXGKMRR6FDI7","bundle":"https://pith.science/pith/HRY3L6OFY3LCIULXGKMRR6FDI7/bundle.json","state":"https://pith.science/pith/HRY3L6OFY3LCIULXGKMRR6FDI7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HRY3L6OFY3LCIULXGKMRR6FDI7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HRY3L6OFY3LCIULXGKMRR6FDI7","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":"139816554703f4266f3f4889aa35aa5b5e4d5d2737368fc2e0308baedeae931a","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.chem-ph","submitted_at":"2024-12-28T03:40:25Z","title_canon_sha256":"74e216168789202a52830ac9cf774a44ebc9e346f6d5987a775cb073d432dbee"},"schema_version":"1.0","source":{"id":"2412.19994","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19994","created_at":"2026-07-05T09:54:52Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19994v1","created_at":"2026-07-05T09:54:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19994","created_at":"2026-07-05T09:54:52Z"},{"alias_kind":"pith_short_12","alias_value":"HRY3L6OFY3LC","created_at":"2026-07-05T09:54:52Z"},{"alias_kind":"pith_short_16","alias_value":"HRY3L6OFY3LCIULX","created_at":"2026-07-05T09:54:52Z"},{"alias_kind":"pith_short_8","alias_value":"HRY3L6OF","created_at":"2026-07-05T09:54:52Z"}],"graph_snapshots":[{"event_id":"sha256:fc40538a6bc86d3dedfed1ad3fc3e4a0a292e0de7586919f2981f3a86d4252b2","target":"graph","created_at":"2026-07-05T09:54:52Z","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/2412.19994/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have significantly transformed our daily life and established a new paradigm in natural language processing (NLP). However, the predominant pretraining of LLMs on extensive web-based texts remains insufficient for advanced scientific discovery, particularly in chemistry. The scarcity of specialized chemistry data, coupled with the complexity of multi-modal data such as 2D graph, 3D structure and spectrum, present distinct challenges. Although several studies have reviewed Pretrained Language Models (PLMs) in chemistry, there is a conspicuous absence of a systematic","authors_text":"Kai Yu, Lu Chen, Xin Chen, Yang Han, Ziping Wan","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.chem-ph","submitted_at":"2024-12-28T03:40:25Z","title":"From Generalist to Specialist: A Survey of Large Language Models for Chemistry"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19994","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":"sha256:4e1a1507959a6d947f1b351032e1c97cf166f1c1cdd7197e31a2d93f59db40e2","target":"record","created_at":"2026-07-05T09:54:52Z","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":"139816554703f4266f3f4889aa35aa5b5e4d5d2737368fc2e0308baedeae931a","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.chem-ph","submitted_at":"2024-12-28T03:40:25Z","title_canon_sha256":"74e216168789202a52830ac9cf774a44ebc9e346f6d5987a775cb073d432dbee"},"schema_version":"1.0","source":{"id":"2412.19994","kind":"arxiv","version":1}},"canonical_sha256":"3c71b5f9c5c6d6245177329918f8a347f6cec908f319ac90e79e9ccd90539bae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c71b5f9c5c6d6245177329918f8a347f6cec908f319ac90e79e9ccd90539bae","first_computed_at":"2026-07-05T09:54:52.944144Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:52.944144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w2US7mwYTd3LK68iLmRfkg0pcq5v+LQtGrfj1D9leHT62Prcii/QUdTFXIEG7GCex9M7momCfcEaRy5BTQ5WCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:52.944599Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.19994","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e1a1507959a6d947f1b351032e1c97cf166f1c1cdd7197e31a2d93f59db40e2","sha256:fc40538a6bc86d3dedfed1ad3fc3e4a0a292e0de7586919f2981f3a86d4252b2"],"state_sha256":"470d46eee3c9db17be0294e8e59f54f418f0014324e37c889f643a56820e438e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rhvhY7OuGwfWNVCz+fWcnPktC6LNTPZjpeH3KibpnLt9V0/Kz2hXU1fq+NVVDtqm4DzGuP4pm0UxO15C0X/CCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:25:03.564114Z","bundle_sha256":"ef918a4801a8be9fcf37f4b0c8a6c20857ac231399bc65ce903f7964b16a2085"}}