{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:XFETXKGV3HJNNVROPCC7EQI2KJ","short_pith_number":"pith:XFETXKGV","canonical_record":{"source":{"id":"2209.01712","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-05T00:31:12Z","cross_cats_sorted":["cs.AI","q-bio.BM"],"title_canon_sha256":"58fe0fa8821086ae5433100f4e68457cffafef45fdf7c4679d13397bdb8f759b","abstract_canon_sha256":"a9d0fb5cebe2cbe10e1c879ba8552180b46a5f03ff60eaa42850aa7e4ba005e1"},"schema_version":"1.0"},"canonical_sha256":"b9493ba8d5d9d2d6d62e7885f2411a527e23f35dca2b8ab00d35a34baa300455","source":{"kind":"arxiv","id":"2209.01712","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.01712","created_at":"2026-07-05T04:54:33Z"},{"alias_kind":"arxiv_version","alias_value":"2209.01712v1","created_at":"2026-07-05T04:54:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.01712","created_at":"2026-07-05T04:54:33Z"},{"alias_kind":"pith_short_12","alias_value":"XFETXKGV3HJN","created_at":"2026-07-05T04:54:33Z"},{"alias_kind":"pith_short_16","alias_value":"XFETXKGV3HJNNVRO","created_at":"2026-07-05T04:54:33Z"},{"alias_kind":"pith_short_8","alias_value":"XFETXKGV","created_at":"2026-07-05T04:54:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:XFETXKGV3HJNNVROPCC7EQI2KJ","target":"record","payload":{"canonical_record":{"source":{"id":"2209.01712","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-05T00:31:12Z","cross_cats_sorted":["cs.AI","q-bio.BM"],"title_canon_sha256":"58fe0fa8821086ae5433100f4e68457cffafef45fdf7c4679d13397bdb8f759b","abstract_canon_sha256":"a9d0fb5cebe2cbe10e1c879ba8552180b46a5f03ff60eaa42850aa7e4ba005e1"},"schema_version":"1.0"},"canonical_sha256":"b9493ba8d5d9d2d6d62e7885f2411a527e23f35dca2b8ab00d35a34baa300455","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:54:33.035358Z","signature_b64":"mypyjDzE8zkkuEDcif6EHgIYprVuoVTWVFK9DBz9yUuhmGT2Y4nyfEbvFRImUmPIbHXhti6eSmaZdUzRa8J8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9493ba8d5d9d2d6d62e7885f2411a527e23f35dca2b8ab00d35a34baa300455","last_reissued_at":"2026-07-05T04:54:33.034923Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:54:33.034923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.01712","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":"2026-07-05T04:54:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lo+z+u4LkB8UudQV37dYKbBPuvRLTtypyZ0i4Et+zoKR7G41YY/XyQzPQzx+eHC5bfP4WKQFBGj/nvTHk/LvAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:51:28.114894Z"},"content_sha256":"c8818e99dd8b97e99a878c9fc084a4fd0d4874e0142f167fcda8b89c44c46c10","schema_version":"1.0","event_id":"sha256:c8818e99dd8b97e99a878c9fc084a4fd0d4874e0142f167fcda8b89c44c46c10"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:XFETXKGV3HJNNVROPCC7EQI2KJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ChemBERTa-2: Towards Chemical Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Bharath Ramsundar, Elana Simon, Gabriel Grand, Seyone Chithrananda, Walid Ahmad","submitted_at":"2022-09-05T00:31:12Z","abstract_excerpt":"Large pretrained models such as GPT-3 have had tremendous impact on modern natural language processing by leveraging self-supervised learning to learn salient representations that can be used to readily finetune on a wide variety of downstream tasks. We investigate the possibility of transferring such advances to molecular machine learning by building a chemical foundation model, ChemBERTa-2, using the language of SMILES. While labeled data for molecular prediction tasks is typically scarce, libraries of SMILES strings are readily available. In this work, we build upon ChemBERTa by optimizing "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.01712","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/2209.01712/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":"2026-07-05T04:54:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qOM5XXXoMqEnwX48v8as6b5GQCKHs/RDD30npVC1uLk3HBHQk4YBiO4RMZi4vFZlgqyTlv4kWM61/6oMSb/dDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:51:28.115272Z"},"content_sha256":"108b0a1af84accaf2e78ed937815370f79f2663efd2407ce9f6cbb13718e5e3b","schema_version":"1.0","event_id":"sha256:108b0a1af84accaf2e78ed937815370f79f2663efd2407ce9f6cbb13718e5e3b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XFETXKGV3HJNNVROPCC7EQI2KJ/bundle.json","state_url":"https://pith.science/pith/XFETXKGV3HJNNVROPCC7EQI2KJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XFETXKGV3HJNNVROPCC7EQI2KJ/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":"2026-08-03T15:51:28Z","links":{"resolver":"https://pith.science/pith/XFETXKGV3HJNNVROPCC7EQI2KJ","bundle":"https://pith.science/pith/XFETXKGV3HJNNVROPCC7EQI2KJ/bundle.json","state":"https://pith.science/pith/XFETXKGV3HJNNVROPCC7EQI2KJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XFETXKGV3HJNNVROPCC7EQI2KJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XFETXKGV3HJNNVROPCC7EQI2KJ","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":"a9d0fb5cebe2cbe10e1c879ba8552180b46a5f03ff60eaa42850aa7e4ba005e1","cross_cats_sorted":["cs.AI","q-bio.BM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-05T00:31:12Z","title_canon_sha256":"58fe0fa8821086ae5433100f4e68457cffafef45fdf7c4679d13397bdb8f759b"},"schema_version":"1.0","source":{"id":"2209.01712","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.01712","created_at":"2026-07-05T04:54:33Z"},{"alias_kind":"arxiv_version","alias_value":"2209.01712v1","created_at":"2026-07-05T04:54:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.01712","created_at":"2026-07-05T04:54:33Z"},{"alias_kind":"pith_short_12","alias_value":"XFETXKGV3HJN","created_at":"2026-07-05T04:54:33Z"},{"alias_kind":"pith_short_16","alias_value":"XFETXKGV3HJNNVRO","created_at":"2026-07-05T04:54:33Z"},{"alias_kind":"pith_short_8","alias_value":"XFETXKGV","created_at":"2026-07-05T04:54:33Z"}],"graph_snapshots":[{"event_id":"sha256:108b0a1af84accaf2e78ed937815370f79f2663efd2407ce9f6cbb13718e5e3b","target":"graph","created_at":"2026-07-05T04:54:33Z","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/2209.01712/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large pretrained models such as GPT-3 have had tremendous impact on modern natural language processing by leveraging self-supervised learning to learn salient representations that can be used to readily finetune on a wide variety of downstream tasks. We investigate the possibility of transferring such advances to molecular machine learning by building a chemical foundation model, ChemBERTa-2, using the language of SMILES. While labeled data for molecular prediction tasks is typically scarce, libraries of SMILES strings are readily available. In this work, we build upon ChemBERTa by optimizing ","authors_text":"Bharath Ramsundar, Elana Simon, Gabriel Grand, Seyone Chithrananda, Walid Ahmad","cross_cats":["cs.AI","q-bio.BM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-05T00:31:12Z","title":"ChemBERTa-2: Towards Chemical Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.01712","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:c8818e99dd8b97e99a878c9fc084a4fd0d4874e0142f167fcda8b89c44c46c10","target":"record","created_at":"2026-07-05T04:54:33Z","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":"a9d0fb5cebe2cbe10e1c879ba8552180b46a5f03ff60eaa42850aa7e4ba005e1","cross_cats_sorted":["cs.AI","q-bio.BM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-05T00:31:12Z","title_canon_sha256":"58fe0fa8821086ae5433100f4e68457cffafef45fdf7c4679d13397bdb8f759b"},"schema_version":"1.0","source":{"id":"2209.01712","kind":"arxiv","version":1}},"canonical_sha256":"b9493ba8d5d9d2d6d62e7885f2411a527e23f35dca2b8ab00d35a34baa300455","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b9493ba8d5d9d2d6d62e7885f2411a527e23f35dca2b8ab00d35a34baa300455","first_computed_at":"2026-07-05T04:54:33.034923Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:54:33.034923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mypyjDzE8zkkuEDcif6EHgIYprVuoVTWVFK9DBz9yUuhmGT2Y4nyfEbvFRImUmPIbHXhti6eSmaZdUzRa8J8BA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:54:33.035358Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.01712","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8818e99dd8b97e99a878c9fc084a4fd0d4874e0142f167fcda8b89c44c46c10","sha256:108b0a1af84accaf2e78ed937815370f79f2663efd2407ce9f6cbb13718e5e3b"],"state_sha256":"a9ed820f307fa7ea589319a9274e215a80404ab6f1b6e600acf6d27ff76eafa2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"avAYpnBcHmLUK4HhOe0eT4xRC+ZcVc9WRlnirVzhJzlUVisK/PYiLJoIRef2TPRAvzdLOBK7jkWVzGKl/zDoCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:51:28.117565Z","bundle_sha256":"ed869ff4b26f89ce069d837d272b3c7cbe04a26eae477c9c1aa724e835fb20d5"}}