{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IAIF6B5CVCRWIJNFEMXB34KI3G","short_pith_number":"pith:IAIF6B5C","canonical_record":{"source":{"id":"2412.13519","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-18T05:41:15Z","cross_cats_sorted":["q-bio.BM"],"title_canon_sha256":"0f427ca09a4e61421f82a3638126ebf36fb5dac4e6086d2d66698d25180ca516","abstract_canon_sha256":"e573a30d73f8060d27aea23496ab9601077d5645d4a2863ac5ff7f80b8c4ad11"},"schema_version":"1.0"},"canonical_sha256":"40105f07a2a8a36425a5232e1df148d989ad4030c1a8867084991011460a0d74","source":{"kind":"arxiv","id":"2412.13519","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13519","created_at":"2026-07-05T09:51:03Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13519v1","created_at":"2026-07-05T09:51:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13519","created_at":"2026-07-05T09:51:03Z"},{"alias_kind":"pith_short_12","alias_value":"IAIF6B5CVCRW","created_at":"2026-07-05T09:51:03Z"},{"alias_kind":"pith_short_16","alias_value":"IAIF6B5CVCRWIJNF","created_at":"2026-07-05T09:51:03Z"},{"alias_kind":"pith_short_8","alias_value":"IAIF6B5C","created_at":"2026-07-05T09:51:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IAIF6B5CVCRWIJNFEMXB34KI3G","target":"record","payload":{"canonical_record":{"source":{"id":"2412.13519","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-18T05:41:15Z","cross_cats_sorted":["q-bio.BM"],"title_canon_sha256":"0f427ca09a4e61421f82a3638126ebf36fb5dac4e6086d2d66698d25180ca516","abstract_canon_sha256":"e573a30d73f8060d27aea23496ab9601077d5645d4a2863ac5ff7f80b8c4ad11"},"schema_version":"1.0"},"canonical_sha256":"40105f07a2a8a36425a5232e1df148d989ad4030c1a8867084991011460a0d74","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:03.219868Z","signature_b64":"PZAC4Da6DQiXQw3zPVTTyHICH5am//yP+ckmJpa/sNjAU59PRxixL6aeIkHRhFhssCUXsF3Rh/3fCegU6IAiDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40105f07a2a8a36425a5232e1df148d989ad4030c1a8867084991011460a0d74","last_reissued_at":"2026-07-05T09:51:03.219447Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:03.219447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.13519","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":"2026-07-05T09:51:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U5Riutctx/+46kdf9GnBHI8VGaQl2Mg2r7D5WdLqszH8yTjXn6No96f5bWLDJuUzZSXsAjYlEgR8uTzMPDRSDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T13:43:59.222658Z"},"content_sha256":"2cf911ab3f0e2cda6c663b79ce1ce6006495ed89455c513b99fcc048591e8464","schema_version":"1.0","event_id":"sha256:2cf911ab3f0e2cda6c663b79ce1ce6006495ed89455c513b99fcc048591e8464"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IAIF6B5CVCRWIJNFEMXB34KI3G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Open-Source Protein Language Models for Function Prediction and Protein Design","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Bharath Ramsundar, Shivasankaran Vanaja Pandi","submitted_at":"2024-12-18T05:41:15Z","abstract_excerpt":"Protein language models (PLMs) have shown promise in improving the understanding of protein sequences, contributing to advances in areas such as function prediction and protein engineering. However, training these models from scratch requires significant computational resources, limiting their accessibility. To address this, we integrate a PLM into DeepChem, an open-source framework for computational biology and chemistry, to provide a more accessible platform for protein-related tasks.\n  We evaluate the performance of the integrated model on various protein prediction tasks, showing that it a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13519","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/2412.13519/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":"2026-07-05T09:51:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KL6Rpy9AWOoG7P4mZPPYvDy/Kx6j3r4DJirUdZkwXJyAQ8rJGnztt5VMqJ8NnlS294VgACD+JupRWNLXb3egBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T13:43:59.223007Z"},"content_sha256":"9a180e96b5a7c37707698ee205d32ccc6782d34206052026995ec7697c5d8122","schema_version":"1.0","event_id":"sha256:9a180e96b5a7c37707698ee205d32ccc6782d34206052026995ec7697c5d8122"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IAIF6B5CVCRWIJNFEMXB34KI3G/bundle.json","state_url":"https://pith.science/pith/IAIF6B5CVCRWIJNFEMXB34KI3G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IAIF6B5CVCRWIJNFEMXB34KI3G/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":"2026-08-22T13:43:59Z","links":{"resolver":"https://pith.science/pith/IAIF6B5CVCRWIJNFEMXB34KI3G","bundle":"https://pith.science/pith/IAIF6B5CVCRWIJNFEMXB34KI3G/bundle.json","state":"https://pith.science/pith/IAIF6B5CVCRWIJNFEMXB34KI3G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IAIF6B5CVCRWIJNFEMXB34KI3G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IAIF6B5CVCRWIJNFEMXB34KI3G","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":"e573a30d73f8060d27aea23496ab9601077d5645d4a2863ac5ff7f80b8c4ad11","cross_cats_sorted":["q-bio.BM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-18T05:41:15Z","title_canon_sha256":"0f427ca09a4e61421f82a3638126ebf36fb5dac4e6086d2d66698d25180ca516"},"schema_version":"1.0","source":{"id":"2412.13519","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13519","created_at":"2026-07-05T09:51:03Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13519v1","created_at":"2026-07-05T09:51:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13519","created_at":"2026-07-05T09:51:03Z"},{"alias_kind":"pith_short_12","alias_value":"IAIF6B5CVCRW","created_at":"2026-07-05T09:51:03Z"},{"alias_kind":"pith_short_16","alias_value":"IAIF6B5CVCRWIJNF","created_at":"2026-07-05T09:51:03Z"},{"alias_kind":"pith_short_8","alias_value":"IAIF6B5C","created_at":"2026-07-05T09:51:03Z"}],"graph_snapshots":[{"event_id":"sha256:9a180e96b5a7c37707698ee205d32ccc6782d34206052026995ec7697c5d8122","target":"graph","created_at":"2026-07-05T09:51:03Z","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/2412.13519/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Protein language models (PLMs) have shown promise in improving the understanding of protein sequences, contributing to advances in areas such as function prediction and protein engineering. However, training these models from scratch requires significant computational resources, limiting their accessibility. To address this, we integrate a PLM into DeepChem, an open-source framework for computational biology and chemistry, to provide a more accessible platform for protein-related tasks.\n  We evaluate the performance of the integrated model on various protein prediction tasks, showing that it a","authors_text":"Bharath Ramsundar, Shivasankaran Vanaja Pandi","cross_cats":["q-bio.BM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-18T05:41:15Z","title":"Open-Source Protein Language Models for Function Prediction and Protein Design"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13519","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":"sha256:2cf911ab3f0e2cda6c663b79ce1ce6006495ed89455c513b99fcc048591e8464","target":"record","created_at":"2026-07-05T09:51:03Z","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":"e573a30d73f8060d27aea23496ab9601077d5645d4a2863ac5ff7f80b8c4ad11","cross_cats_sorted":["q-bio.BM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-18T05:41:15Z","title_canon_sha256":"0f427ca09a4e61421f82a3638126ebf36fb5dac4e6086d2d66698d25180ca516"},"schema_version":"1.0","source":{"id":"2412.13519","kind":"arxiv","version":1}},"canonical_sha256":"40105f07a2a8a36425a5232e1df148d989ad4030c1a8867084991011460a0d74","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40105f07a2a8a36425a5232e1df148d989ad4030c1a8867084991011460a0d74","first_computed_at":"2026-07-05T09:51:03.219447Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:51:03.219447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PZAC4Da6DQiXQw3zPVTTyHICH5am//yP+ckmJpa/sNjAU59PRxixL6aeIkHRhFhssCUXsF3Rh/3fCegU6IAiDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:51:03.219868Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.13519","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2cf911ab3f0e2cda6c663b79ce1ce6006495ed89455c513b99fcc048591e8464","sha256:9a180e96b5a7c37707698ee205d32ccc6782d34206052026995ec7697c5d8122"],"state_sha256":"d7fa78cb762667ac5e374c58457c7d05a0c89f3e2843882e80cc414139e80fda"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+qRhLv8ZEhzbP4qVP4Y7+xrgy6KAdqhwq4Rw9+ql4SNsvTyXp5O0QSK56KiWWL4ewH2UwOtPjUFlo/vIIUYBBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T13:43:59.226289Z","bundle_sha256":"8fb9b858916ca53753ea66c3cc3eb99a8dc09c4c99871d6262ccc8090e2f2a3e"}}