{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:THPCHYGLXEX4AXBDAIGYVKV7D6","short_pith_number":"pith:THPCHYGL","canonical_record":{"source":{"id":"2310.03030","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2023-09-20T17:21:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e3020a705fd49eebd40ce396a4ed6dcc9d717ce93dc87864a6ae838e9862eeed","abstract_canon_sha256":"1e4512fdd44c59cbc73611c5b245534517b1d09d86361251a8bf834fabcf48b3"},"schema_version":"1.0"},"canonical_sha256":"99de23e0cbb92fc05c23020d8aaabf1fadeb29b17c9bd5349459aa5f90fc117f","source":{"kind":"arxiv","id":"2310.03030","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.03030","created_at":"2026-07-05T06:59:23Z"},{"alias_kind":"arxiv_version","alias_value":"2310.03030v3","created_at":"2026-07-05T06:59:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03030","created_at":"2026-07-05T06:59:23Z"},{"alias_kind":"pith_short_12","alias_value":"THPCHYGLXEX4","created_at":"2026-07-05T06:59:23Z"},{"alias_kind":"pith_short_16","alias_value":"THPCHYGLXEX4AXBD","created_at":"2026-07-05T06:59:23Z"},{"alias_kind":"pith_short_8","alias_value":"THPCHYGL","created_at":"2026-07-05T06:59:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:THPCHYGLXEX4AXBDAIGYVKV7D6","target":"record","payload":{"canonical_record":{"source":{"id":"2310.03030","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2023-09-20T17:21:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e3020a705fd49eebd40ce396a4ed6dcc9d717ce93dc87864a6ae838e9862eeed","abstract_canon_sha256":"1e4512fdd44c59cbc73611c5b245534517b1d09d86361251a8bf834fabcf48b3"},"schema_version":"1.0"},"canonical_sha256":"99de23e0cbb92fc05c23020d8aaabf1fadeb29b17c9bd5349459aa5f90fc117f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:23.134815Z","signature_b64":"2HUdimIVkG+XDhsLGRO3c+8kBY9HkiUAP28/PdX1tQVaiBZUEpX5iscAHW066q280Q6+Ow5Lqg8drrNXL7eADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99de23e0cbb92fc05c23020d8aaabf1fadeb29b17c9bd5349459aa5f90fc117f","last_reissued_at":"2026-07-05T06:59:23.134336Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:23.134336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.03030","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":"2026-07-05T06:59:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pMnbgACmToA7X16LycHfGlLZGh2hkni8BdXdLirRYkdb+CXp62YypOtzIY+c6+KFi09p+2PkdBlO6dWU4NnpDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:39:11.339055Z"},"content_sha256":"b606acf6c3fbe11a0fdbefdc8f1135f34d517a751b550a812ce5afc89d5d0098","schema_version":"1.0","event_id":"sha256:b606acf6c3fbe11a0fdbefdc8f1135f34d517a751b550a812ce5afc89d5d0098"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:THPCHYGLXEX4AXBDAIGYVKV7D6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GPT-MolBERTa: GPT Molecular Features Language Model for molecular property prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.chem-ph","authors_text":"Amir Barati Farimani, Rishikesh Magar, Suryanarayanan Balaji, Yayati Jadhav","submitted_at":"2023-09-20T17:21:43Z","abstract_excerpt":"With the emergence of Transformer architectures and their powerful understanding of textual data, a new horizon has opened up to predict the molecular properties based on text description. While SMILES are the most common form of representation, they are lacking robustness, rich information and canonicity, which limit their effectiveness in becoming generalizable representations. Here, we present GPT-MolBERTa, a self-supervised large language model (LLM) which uses detailed textual descriptions of molecules to predict their properties. A text based description of 326000 molecules were collecte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03030","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/2310.03030/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":"2026-07-05T06:59:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ExFxN/L1Qktk5IIKkb8j5RBnUFyau924KNde48n+N50rpAhT8oibjekXgjhYs4okOrsL1Pboa3R5IWwUtVYHBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:39:11.339733Z"},"content_sha256":"8125ce7e3aa76ac94b927bbcd6d2080cb05146deb7f5e95ed7083331f4270c92","schema_version":"1.0","event_id":"sha256:8125ce7e3aa76ac94b927bbcd6d2080cb05146deb7f5e95ed7083331f4270c92"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/THPCHYGLXEX4AXBDAIGYVKV7D6/bundle.json","state_url":"https://pith.science/pith/THPCHYGLXEX4AXBDAIGYVKV7D6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/THPCHYGLXEX4AXBDAIGYVKV7D6/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":"2026-08-04T20:39:11Z","links":{"resolver":"https://pith.science/pith/THPCHYGLXEX4AXBDAIGYVKV7D6","bundle":"https://pith.science/pith/THPCHYGLXEX4AXBDAIGYVKV7D6/bundle.json","state":"https://pith.science/pith/THPCHYGLXEX4AXBDAIGYVKV7D6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/THPCHYGLXEX4AXBDAIGYVKV7D6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:THPCHYGLXEX4AXBDAIGYVKV7D6","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":"1e4512fdd44c59cbc73611c5b245534517b1d09d86361251a8bf834fabcf48b3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2023-09-20T17:21:43Z","title_canon_sha256":"e3020a705fd49eebd40ce396a4ed6dcc9d717ce93dc87864a6ae838e9862eeed"},"schema_version":"1.0","source":{"id":"2310.03030","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.03030","created_at":"2026-07-05T06:59:23Z"},{"alias_kind":"arxiv_version","alias_value":"2310.03030v3","created_at":"2026-07-05T06:59:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03030","created_at":"2026-07-05T06:59:23Z"},{"alias_kind":"pith_short_12","alias_value":"THPCHYGLXEX4","created_at":"2026-07-05T06:59:23Z"},{"alias_kind":"pith_short_16","alias_value":"THPCHYGLXEX4AXBD","created_at":"2026-07-05T06:59:23Z"},{"alias_kind":"pith_short_8","alias_value":"THPCHYGL","created_at":"2026-07-05T06:59:23Z"}],"graph_snapshots":[{"event_id":"sha256:8125ce7e3aa76ac94b927bbcd6d2080cb05146deb7f5e95ed7083331f4270c92","target":"graph","created_at":"2026-07-05T06:59:23Z","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/2310.03030/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the emergence of Transformer architectures and their powerful understanding of textual data, a new horizon has opened up to predict the molecular properties based on text description. While SMILES are the most common form of representation, they are lacking robustness, rich information and canonicity, which limit their effectiveness in becoming generalizable representations. Here, we present GPT-MolBERTa, a self-supervised large language model (LLM) which uses detailed textual descriptions of molecules to predict their properties. A text based description of 326000 molecules were collecte","authors_text":"Amir Barati Farimani, Rishikesh Magar, Suryanarayanan Balaji, Yayati Jadhav","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2023-09-20T17:21:43Z","title":"GPT-MolBERTa: GPT Molecular Features Language Model for molecular property prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03030","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:b606acf6c3fbe11a0fdbefdc8f1135f34d517a751b550a812ce5afc89d5d0098","target":"record","created_at":"2026-07-05T06:59:23Z","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":"1e4512fdd44c59cbc73611c5b245534517b1d09d86361251a8bf834fabcf48b3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2023-09-20T17:21:43Z","title_canon_sha256":"e3020a705fd49eebd40ce396a4ed6dcc9d717ce93dc87864a6ae838e9862eeed"},"schema_version":"1.0","source":{"id":"2310.03030","kind":"arxiv","version":3}},"canonical_sha256":"99de23e0cbb92fc05c23020d8aaabf1fadeb29b17c9bd5349459aa5f90fc117f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"99de23e0cbb92fc05c23020d8aaabf1fadeb29b17c9bd5349459aa5f90fc117f","first_computed_at":"2026-07-05T06:59:23.134336Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:59:23.134336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2HUdimIVkG+XDhsLGRO3c+8kBY9HkiUAP28/PdX1tQVaiBZUEpX5iscAHW066q280Q6+Ow5Lqg8drrNXL7eADA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:59:23.134815Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.03030","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b606acf6c3fbe11a0fdbefdc8f1135f34d517a751b550a812ce5afc89d5d0098","sha256:8125ce7e3aa76ac94b927bbcd6d2080cb05146deb7f5e95ed7083331f4270c92"],"state_sha256":"542883a3be1d0bfa44d1d1fb2ea03df768affa36b9e78236a8fc8aeb56ad7ab1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/xgyclyeN0k1AZEvkxuVqmsX8wyR0K8Of7aMgBiZsW7Wgymr0FXYGZ9KOhXVX5ypvd0UZ5zKeFVQDXzxX0HtAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T20:39:11.345523Z","bundle_sha256":"50e8aa052d20dd4125800d14dec54e8b220003aadf0ef8c87e1642edf193c42e"}}