{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5CTWA2JE5SPVDQT7MCR3SEZU7U","short_pith_number":"pith:5CTWA2JE","canonical_record":{"source":{"id":"2309.03099","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-bio.BM","submitted_at":"2023-08-28T01:09:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8df6ad69ce94416bda613e37a5b7d9986b80df6be2f54322218ff6a91378de7a","abstract_canon_sha256":"21b8e0c15e1036f6e4aeca2b5ab549d3a237006e105cc1aa9ebce3ba9918f322"},"schema_version":"1.0"},"canonical_sha256":"e8a7606924ec9f51c27f60a3b91334fd0fb16a41ce76272641e45914dc35326b","source":{"kind":"arxiv","id":"2309.03099","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.03099","created_at":"2026-07-05T06:48:20Z"},{"alias_kind":"arxiv_version","alias_value":"2309.03099v1","created_at":"2026-07-05T06:48:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.03099","created_at":"2026-07-05T06:48:20Z"},{"alias_kind":"pith_short_12","alias_value":"5CTWA2JE5SPV","created_at":"2026-07-05T06:48:20Z"},{"alias_kind":"pith_short_16","alias_value":"5CTWA2JE5SPVDQT7","created_at":"2026-07-05T06:48:20Z"},{"alias_kind":"pith_short_8","alias_value":"5CTWA2JE","created_at":"2026-07-05T06:48:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5CTWA2JE5SPVDQT7MCR3SEZU7U","target":"record","payload":{"canonical_record":{"source":{"id":"2309.03099","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-bio.BM","submitted_at":"2023-08-28T01:09:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8df6ad69ce94416bda613e37a5b7d9986b80df6be2f54322218ff6a91378de7a","abstract_canon_sha256":"21b8e0c15e1036f6e4aeca2b5ab549d3a237006e105cc1aa9ebce3ba9918f322"},"schema_version":"1.0"},"canonical_sha256":"e8a7606924ec9f51c27f60a3b91334fd0fb16a41ce76272641e45914dc35326b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:48:20.850650Z","signature_b64":"32X/faQvpX0d5cAOYiCWQFnTBIAMENws6OPhQQRVMuLWLfftAYtaPogYyM7Wx3jcq3BNHGzilbCE4egWIRp/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8a7606924ec9f51c27f60a3b91334fd0fb16a41ce76272641e45914dc35326b","last_reissued_at":"2026-07-05T06:48:20.850155Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:48:20.850155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.03099","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":"2026-07-05T06:48:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+0khelwyVcPO6ykppRnDhDm+dxIpaSAml/pzIamjq48BBlawHnP8poSJLTkSEaNUN/C7zgJcajRwUhkHDQY3Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:53:13.543006Z"},"content_sha256":"1dd5c6d30cf1d965429e7ac3084ec13e69a280aebbf4dddbcb1fc62e952365a1","schema_version":"1.0","event_id":"sha256:1dd5c6d30cf1d965429e7ac3084ec13e69a280aebbf4dddbcb1fc62e952365a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5CTWA2JE5SPVDQT7MCR3SEZU7U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PeptideBERT: A Language Model based on Transformers for Peptide Property Prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Adrita Das, Amir Barati Farimani, Chakradhar Guntuboina, Parisa Mollaei, Seongwon Kim","submitted_at":"2023-08-28T01:09:21Z","abstract_excerpt":"Recent advances in Language Models have enabled the protein modeling community with a powerful tool since protein sequences can be represented as text. Specifically, by taking advantage of Transformers, sequence-to-property prediction will be amenable without the need for explicit structural data. In this work, inspired by recent progress in Large Language Models (LLMs), we introduce PeptideBERT, a protein language model for predicting three key properties of peptides (hemolysis, solubility, and non-fouling). The PeptideBert utilizes the ProtBERT pretrained transformer model with 12 attention "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.03099","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/2309.03099/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":"2026-07-05T06:48:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dPRdJDoOUrV1lieBN/GD9iBSzPnYI4kiNXDrLv7FOyM3fAyJWGCmSJ20YZw76PzqzI4cvYWEhKU0g4569cERCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:53:13.543535Z"},"content_sha256":"3fd82e90cdd699da1c6c77b1dff1f4e76f48f9499c9f9d58c604d19b3025ea35","schema_version":"1.0","event_id":"sha256:3fd82e90cdd699da1c6c77b1dff1f4e76f48f9499c9f9d58c604d19b3025ea35"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5CTWA2JE5SPVDQT7MCR3SEZU7U/bundle.json","state_url":"https://pith.science/pith/5CTWA2JE5SPVDQT7MCR3SEZU7U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5CTWA2JE5SPVDQT7MCR3SEZU7U/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":"2026-08-09T05:53:13Z","links":{"resolver":"https://pith.science/pith/5CTWA2JE5SPVDQT7MCR3SEZU7U","bundle":"https://pith.science/pith/5CTWA2JE5SPVDQT7MCR3SEZU7U/bundle.json","state":"https://pith.science/pith/5CTWA2JE5SPVDQT7MCR3SEZU7U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5CTWA2JE5SPVDQT7MCR3SEZU7U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5CTWA2JE5SPVDQT7MCR3SEZU7U","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":"21b8e0c15e1036f6e4aeca2b5ab549d3a237006e105cc1aa9ebce3ba9918f322","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-bio.BM","submitted_at":"2023-08-28T01:09:21Z","title_canon_sha256":"8df6ad69ce94416bda613e37a5b7d9986b80df6be2f54322218ff6a91378de7a"},"schema_version":"1.0","source":{"id":"2309.03099","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.03099","created_at":"2026-07-05T06:48:20Z"},{"alias_kind":"arxiv_version","alias_value":"2309.03099v1","created_at":"2026-07-05T06:48:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.03099","created_at":"2026-07-05T06:48:20Z"},{"alias_kind":"pith_short_12","alias_value":"5CTWA2JE5SPV","created_at":"2026-07-05T06:48:20Z"},{"alias_kind":"pith_short_16","alias_value":"5CTWA2JE5SPVDQT7","created_at":"2026-07-05T06:48:20Z"},{"alias_kind":"pith_short_8","alias_value":"5CTWA2JE","created_at":"2026-07-05T06:48:20Z"}],"graph_snapshots":[{"event_id":"sha256:3fd82e90cdd699da1c6c77b1dff1f4e76f48f9499c9f9d58c604d19b3025ea35","target":"graph","created_at":"2026-07-05T06:48:20Z","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/2309.03099/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in Language Models have enabled the protein modeling community with a powerful tool since protein sequences can be represented as text. Specifically, by taking advantage of Transformers, sequence-to-property prediction will be amenable without the need for explicit structural data. In this work, inspired by recent progress in Large Language Models (LLMs), we introduce PeptideBERT, a protein language model for predicting three key properties of peptides (hemolysis, solubility, and non-fouling). The PeptideBert utilizes the ProtBERT pretrained transformer model with 12 attention ","authors_text":"Adrita Das, Amir Barati Farimani, Chakradhar Guntuboina, Parisa Mollaei, Seongwon Kim","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-bio.BM","submitted_at":"2023-08-28T01:09:21Z","title":"PeptideBERT: A Language Model based on Transformers for Peptide Property Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.03099","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":"sha256:1dd5c6d30cf1d965429e7ac3084ec13e69a280aebbf4dddbcb1fc62e952365a1","target":"record","created_at":"2026-07-05T06:48:20Z","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":"21b8e0c15e1036f6e4aeca2b5ab549d3a237006e105cc1aa9ebce3ba9918f322","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-bio.BM","submitted_at":"2023-08-28T01:09:21Z","title_canon_sha256":"8df6ad69ce94416bda613e37a5b7d9986b80df6be2f54322218ff6a91378de7a"},"schema_version":"1.0","source":{"id":"2309.03099","kind":"arxiv","version":1}},"canonical_sha256":"e8a7606924ec9f51c27f60a3b91334fd0fb16a41ce76272641e45914dc35326b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8a7606924ec9f51c27f60a3b91334fd0fb16a41ce76272641e45914dc35326b","first_computed_at":"2026-07-05T06:48:20.850155Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:48:20.850155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"32X/faQvpX0d5cAOYiCWQFnTBIAMENws6OPhQQRVMuLWLfftAYtaPogYyM7Wx3jcq3BNHGzilbCE4egWIRp/Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:48:20.850650Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.03099","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1dd5c6d30cf1d965429e7ac3084ec13e69a280aebbf4dddbcb1fc62e952365a1","sha256:3fd82e90cdd699da1c6c77b1dff1f4e76f48f9499c9f9d58c604d19b3025ea35"],"state_sha256":"f202b913e17ad9bfeee74f4961c4b4a802374dbe2f542be11c82870ed731cac5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sKx1xyn72r6TcHqxhwAx6o7zuHnsByUyFzXwXpez8U+qOGDMRbiC9VLDbCkJOErCdn7Fe807AAA63G6kzpbvAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T05:53:13.549084Z","bundle_sha256":"5fe1978881847fb87854a299556c8bc4293deaa96f46aace94fab7226b0ff00c"}}