{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:J6DAO7UGEVJOS7OXAEMLJ6JLJE","short_pith_number":"pith:J6DAO7UG","canonical_record":{"source":{"id":"2211.02657","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2022-11-03T21:22:05Z","cross_cats_sorted":["cs.LG","q-bio.BM"],"title_canon_sha256":"c746ad6a75f4dbdb6e9d823c220b01587b3ead733c2a7312a00d49f0284d31ba","abstract_canon_sha256":"5b990e2ab3b82b8e1cb4e3a1af7c329fe6b1154c09ab88367ed526b68915c28b"},"schema_version":"1.0"},"canonical_sha256":"4f86077e862552e97dd70118b4f92b490995c543223ccbbee0c06d9eb38e0f7e","source":{"kind":"arxiv","id":"2211.02657","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.02657","created_at":"2026-07-05T05:13:20Z"},{"alias_kind":"arxiv_version","alias_value":"2211.02657v1","created_at":"2026-07-05T05:13:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.02657","created_at":"2026-07-05T05:13:20Z"},{"alias_kind":"pith_short_12","alias_value":"J6DAO7UGEVJO","created_at":"2026-07-05T05:13:20Z"},{"alias_kind":"pith_short_16","alias_value":"J6DAO7UGEVJOS7OX","created_at":"2026-07-05T05:13:20Z"},{"alias_kind":"pith_short_8","alias_value":"J6DAO7UG","created_at":"2026-07-05T05:13:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:J6DAO7UGEVJOS7OXAEMLJ6JLJE","target":"record","payload":{"canonical_record":{"source":{"id":"2211.02657","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2022-11-03T21:22:05Z","cross_cats_sorted":["cs.LG","q-bio.BM"],"title_canon_sha256":"c746ad6a75f4dbdb6e9d823c220b01587b3ead733c2a7312a00d49f0284d31ba","abstract_canon_sha256":"5b990e2ab3b82b8e1cb4e3a1af7c329fe6b1154c09ab88367ed526b68915c28b"},"schema_version":"1.0"},"canonical_sha256":"4f86077e862552e97dd70118b4f92b490995c543223ccbbee0c06d9eb38e0f7e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:20.160292Z","signature_b64":"3ZTsb/OxHPyhWjsoqsvwHykWHCWKajv0QkMZ24d9Sn5+u3roEpzzfpDHcvSA7SLJ8mdaKftmK9seOyi60mYmCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f86077e862552e97dd70118b4f92b490995c543223ccbbee0c06d9eb38e0f7e","last_reissued_at":"2026-07-05T05:13:20.159905Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:20.159905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.02657","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":"2026-07-05T05:13:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tV7XasK9+GT2ixkbZF+vEkFdnRMvdC3uA4v64bmxtBcyU3SM9+CzaU3e7WjkYpWVT2UfD3xsrcHPpmAvGXCtAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T10:47:00.443740Z"},"content_sha256":"ab5c439e572ece8fe8596017867e41b9d2777aeb0d957e91f0dd1677c39cddd3","schema_version":"1.0","event_id":"sha256:ab5c439e572ece8fe8596017867e41b9d2777aeb0d957e91f0dd1677c39cddd3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:J6DAO7UGEVJOS7OXAEMLJ6JLJE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MolE: a molecular foundation model for drug discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","q-bio.BM"],"primary_cat":"q-bio.QM","authors_text":"Berton Earnshaw, Christos Nicolaou, Oscar M\\'endez-Lucio","submitted_at":"2022-11-03T21:22:05Z","abstract_excerpt":"Models that accurately predict properties based on chemical structure are valuable tools in drug discovery. However, for many properties, public and private training sets are typically small, and it is difficult for the models to generalize well outside of the training data. Recently, large language models have addressed this problem by using self-supervised pretraining on large unlabeled datasets, followed by fine-tuning on smaller, labeled datasets. In this paper, we report MolE, a molecular foundation model that adapts the DeBERTa architecture to be used on molecular graphs together with a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.02657","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/2211.02657/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":"2026-07-05T05:13:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lXqJswqfO1ULtSM64QodFrIAeHDkduBg5EOtxHKUDCuo2jBXcYscWk10DAtlDUstYnpRl6fN0h8knH9nSsz3Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T10:47:00.444281Z"},"content_sha256":"26e2e34b3f50f20eca7317e7fa035ffd803c723cd4f2f31c4886facaa12e4496","schema_version":"1.0","event_id":"sha256:26e2e34b3f50f20eca7317e7fa035ffd803c723cd4f2f31c4886facaa12e4496"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J6DAO7UGEVJOS7OXAEMLJ6JLJE/bundle.json","state_url":"https://pith.science/pith/J6DAO7UGEVJOS7OXAEMLJ6JLJE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J6DAO7UGEVJOS7OXAEMLJ6JLJE/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":"2026-08-14T10:47:00Z","links":{"resolver":"https://pith.science/pith/J6DAO7UGEVJOS7OXAEMLJ6JLJE","bundle":"https://pith.science/pith/J6DAO7UGEVJOS7OXAEMLJ6JLJE/bundle.json","state":"https://pith.science/pith/J6DAO7UGEVJOS7OXAEMLJ6JLJE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J6DAO7UGEVJOS7OXAEMLJ6JLJE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:J6DAO7UGEVJOS7OXAEMLJ6JLJE","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":"5b990e2ab3b82b8e1cb4e3a1af7c329fe6b1154c09ab88367ed526b68915c28b","cross_cats_sorted":["cs.LG","q-bio.BM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2022-11-03T21:22:05Z","title_canon_sha256":"c746ad6a75f4dbdb6e9d823c220b01587b3ead733c2a7312a00d49f0284d31ba"},"schema_version":"1.0","source":{"id":"2211.02657","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.02657","created_at":"2026-07-05T05:13:20Z"},{"alias_kind":"arxiv_version","alias_value":"2211.02657v1","created_at":"2026-07-05T05:13:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.02657","created_at":"2026-07-05T05:13:20Z"},{"alias_kind":"pith_short_12","alias_value":"J6DAO7UGEVJO","created_at":"2026-07-05T05:13:20Z"},{"alias_kind":"pith_short_16","alias_value":"J6DAO7UGEVJOS7OX","created_at":"2026-07-05T05:13:20Z"},{"alias_kind":"pith_short_8","alias_value":"J6DAO7UG","created_at":"2026-07-05T05:13:20Z"}],"graph_snapshots":[{"event_id":"sha256:26e2e34b3f50f20eca7317e7fa035ffd803c723cd4f2f31c4886facaa12e4496","target":"graph","created_at":"2026-07-05T05:13:20Z","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/2211.02657/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Models that accurately predict properties based on chemical structure are valuable tools in drug discovery. However, for many properties, public and private training sets are typically small, and it is difficult for the models to generalize well outside of the training data. Recently, large language models have addressed this problem by using self-supervised pretraining on large unlabeled datasets, followed by fine-tuning on smaller, labeled datasets. In this paper, we report MolE, a molecular foundation model that adapts the DeBERTa architecture to be used on molecular graphs together with a ","authors_text":"Berton Earnshaw, Christos Nicolaou, Oscar M\\'endez-Lucio","cross_cats":["cs.LG","q-bio.BM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2022-11-03T21:22:05Z","title":"MolE: a molecular foundation model for drug discovery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.02657","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:ab5c439e572ece8fe8596017867e41b9d2777aeb0d957e91f0dd1677c39cddd3","target":"record","created_at":"2026-07-05T05:13:20Z","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":"5b990e2ab3b82b8e1cb4e3a1af7c329fe6b1154c09ab88367ed526b68915c28b","cross_cats_sorted":["cs.LG","q-bio.BM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2022-11-03T21:22:05Z","title_canon_sha256":"c746ad6a75f4dbdb6e9d823c220b01587b3ead733c2a7312a00d49f0284d31ba"},"schema_version":"1.0","source":{"id":"2211.02657","kind":"arxiv","version":1}},"canonical_sha256":"4f86077e862552e97dd70118b4f92b490995c543223ccbbee0c06d9eb38e0f7e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f86077e862552e97dd70118b4f92b490995c543223ccbbee0c06d9eb38e0f7e","first_computed_at":"2026-07-05T05:13:20.159905Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:13:20.159905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3ZTsb/OxHPyhWjsoqsvwHykWHCWKajv0QkMZ24d9Sn5+u3roEpzzfpDHcvSA7SLJ8mdaKftmK9seOyi60mYmCg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:13:20.160292Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.02657","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab5c439e572ece8fe8596017867e41b9d2777aeb0d957e91f0dd1677c39cddd3","sha256:26e2e34b3f50f20eca7317e7fa035ffd803c723cd4f2f31c4886facaa12e4496"],"state_sha256":"2e72931b16b843dda24f1b0a9da4b2c39be120a6e9648ea9acfddb80cca37eb6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kTOcJ1SFbs6PaELAGzS7VREwaCi2PecHFS7hjiIu4ztWMfqL2Pule6aXAPTVgIoUEh3YxuSewuEVFmSU0tpVDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T10:47:00.449699Z","bundle_sha256":"cda52d84cce90bb2ba2bf0168c8c56368d1a5019a61b44c43e7d352887cdb7e9"}}