{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GEZH2EJW7VVBDPMUGA343NRCG3","short_pith_number":"pith:GEZH2EJW","canonical_record":{"source":{"id":"2310.04292","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-06T14:51:17Z","cross_cats_sorted":[],"title_canon_sha256":"f4d1c901d86ff091648fbf23d4c292f7bc36af16bc44a748b640a51e200ad76b","abstract_canon_sha256":"b5605b52a6ca2b646cdf59b51d20874de1a7513a87a7bcd1efa45eb006c4261d"},"schema_version":"1.0"},"canonical_sha256":"31327d1136fd6a11bd943037cdb62236ff51ae1ae87b87533e297948f74a7316","source":{"kind":"arxiv","id":"2310.04292","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.04292","created_at":"2026-07-05T07:02:05Z"},{"alias_kind":"arxiv_version","alias_value":"2310.04292v3","created_at":"2026-07-05T07:02:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04292","created_at":"2026-07-05T07:02:05Z"},{"alias_kind":"pith_short_12","alias_value":"GEZH2EJW7VVB","created_at":"2026-07-05T07:02:05Z"},{"alias_kind":"pith_short_16","alias_value":"GEZH2EJW7VVBDPMU","created_at":"2026-07-05T07:02:05Z"},{"alias_kind":"pith_short_8","alias_value":"GEZH2EJW","created_at":"2026-07-05T07:02:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GEZH2EJW7VVBDPMUGA343NRCG3","target":"record","payload":{"canonical_record":{"source":{"id":"2310.04292","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-06T14:51:17Z","cross_cats_sorted":[],"title_canon_sha256":"f4d1c901d86ff091648fbf23d4c292f7bc36af16bc44a748b640a51e200ad76b","abstract_canon_sha256":"b5605b52a6ca2b646cdf59b51d20874de1a7513a87a7bcd1efa45eb006c4261d"},"schema_version":"1.0"},"canonical_sha256":"31327d1136fd6a11bd943037cdb62236ff51ae1ae87b87533e297948f74a7316","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:05.817078Z","signature_b64":"rra5+KthsoFQidPm50fPU4AVLGti7lhrYB2FKcUUez9L4Cgbav6EcZUuwzSQ8NCb0ffdv4BOXI+JkSPJyV4wAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31327d1136fd6a11bd943037cdb62236ff51ae1ae87b87533e297948f74a7316","last_reissued_at":"2026-07-05T07:02:05.816542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:05.816542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.04292","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":"2026-07-05T07:02:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c5VceG/9xpgZute8RlYVsanAU2Z5Q1l7oROJuMZim/vGI/F4g34xfFHIxIK0tht4YqSloB6hKjHs5anNVNOLDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:29:45.346306Z"},"content_sha256":"de54cf7bb1d4d6ce7045338b322e796b5de68888641cf7d9a7575908a160611b","schema_version":"1.0","event_id":"sha256:de54cf7bb1d4d6ce7045338b322e796b5de68888641cf7d9a7575908a160611b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GEZH2EJW7VVBDPMUGA343NRCG3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ali Parviz, Andrew Fitzgibbon, B{\\l}a\\.zej Banaszewski, Callum McLean, Cas Wognum, Chad Martin, Christopher Morris, Cristian Gabellini, Dominic Masters, Dominique Beaini, Frederik Wenkel, Gabriela Moisescu-Pareja, Guillaume Rabusseau, Guy Wolf, Hadrien Mary, Ioannis Koutis, Jama Hussein Mohamud, Jian Tang, Jiarui Lu, Joao Alex Cunha, Josef Dean, Kerstin Klaser, Luis M\\\"uller, Maciej Sypetkowski, Michael Craig, Micha{\\l} Koziarski, Mirco Ravanelli, Oleksandr Dymov, Prudencio Tossou, Reihaneh Rabbany, Samuel Maddrell-Mander, Shenyang Huang, Therence Bois, Zhaocheng Zhu, Zhiyi Li","submitted_at":"2023-10-06T14:51:17Z","abstract_excerpt":"Recently, pre-trained foundation models have enabled significant advancements in multiple fields. In molecular machine learning, however, where datasets are often hand-curated, and hence typically small, the lack of datasets with labeled features, and codebases to manage those datasets, has hindered the development of foundation models. In this work, we present seven novel datasets categorized by size into three distinct categories: ToyMix, LargeMix and UltraLarge. These datasets push the boundaries in both the scale and the diversity of supervised labels for molecular learning. They cover nea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.04292","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/2310.04292/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":"2026-07-05T07:02:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3HxefiPDxmLIzI4+1zkvvsuDV7tJZ44brZpSEIarlyaI45adiryjOv9xLYXho8Lee8oNXHyQ1WelLYc/0XKjBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:29:45.346710Z"},"content_sha256":"0570a26e03f28bcb74231ecbe76fa3e11adfe763aa7aede4dff54886108ba115","schema_version":"1.0","event_id":"sha256:0570a26e03f28bcb74231ecbe76fa3e11adfe763aa7aede4dff54886108ba115"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GEZH2EJW7VVBDPMUGA343NRCG3/bundle.json","state_url":"https://pith.science/pith/GEZH2EJW7VVBDPMUGA343NRCG3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GEZH2EJW7VVBDPMUGA343NRCG3/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":"2026-07-07T12:29:45Z","links":{"resolver":"https://pith.science/pith/GEZH2EJW7VVBDPMUGA343NRCG3","bundle":"https://pith.science/pith/GEZH2EJW7VVBDPMUGA343NRCG3/bundle.json","state":"https://pith.science/pith/GEZH2EJW7VVBDPMUGA343NRCG3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GEZH2EJW7VVBDPMUGA343NRCG3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GEZH2EJW7VVBDPMUGA343NRCG3","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":"b5605b52a6ca2b646cdf59b51d20874de1a7513a87a7bcd1efa45eb006c4261d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-06T14:51:17Z","title_canon_sha256":"f4d1c901d86ff091648fbf23d4c292f7bc36af16bc44a748b640a51e200ad76b"},"schema_version":"1.0","source":{"id":"2310.04292","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.04292","created_at":"2026-07-05T07:02:05Z"},{"alias_kind":"arxiv_version","alias_value":"2310.04292v3","created_at":"2026-07-05T07:02:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04292","created_at":"2026-07-05T07:02:05Z"},{"alias_kind":"pith_short_12","alias_value":"GEZH2EJW7VVB","created_at":"2026-07-05T07:02:05Z"},{"alias_kind":"pith_short_16","alias_value":"GEZH2EJW7VVBDPMU","created_at":"2026-07-05T07:02:05Z"},{"alias_kind":"pith_short_8","alias_value":"GEZH2EJW","created_at":"2026-07-05T07:02:05Z"}],"graph_snapshots":[{"event_id":"sha256:0570a26e03f28bcb74231ecbe76fa3e11adfe763aa7aede4dff54886108ba115","target":"graph","created_at":"2026-07-05T07:02:05Z","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/2310.04292/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, pre-trained foundation models have enabled significant advancements in multiple fields. In molecular machine learning, however, where datasets are often hand-curated, and hence typically small, the lack of datasets with labeled features, and codebases to manage those datasets, has hindered the development of foundation models. In this work, we present seven novel datasets categorized by size into three distinct categories: ToyMix, LargeMix and UltraLarge. These datasets push the boundaries in both the scale and the diversity of supervised labels for molecular learning. They cover nea","authors_text":"Ali Parviz, Andrew Fitzgibbon, B{\\l}a\\.zej Banaszewski, Callum McLean, Cas Wognum, Chad Martin, Christopher Morris, Cristian Gabellini, Dominic Masters, Dominique Beaini, Frederik Wenkel, Gabriela Moisescu-Pareja, Guillaume Rabusseau, Guy Wolf, Hadrien Mary, Ioannis Koutis, Jama Hussein Mohamud, Jian Tang, Jiarui Lu, Joao Alex Cunha, Josef Dean, Kerstin Klaser, Luis M\\\"uller, Maciej Sypetkowski, Michael Craig, Micha{\\l} Koziarski, Mirco Ravanelli, Oleksandr Dymov, Prudencio Tossou, Reihaneh Rabbany, Samuel Maddrell-Mander, Shenyang Huang, Therence Bois, Zhaocheng Zhu, Zhiyi Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-06T14:51:17Z","title":"Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.04292","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:de54cf7bb1d4d6ce7045338b322e796b5de68888641cf7d9a7575908a160611b","target":"record","created_at":"2026-07-05T07:02:05Z","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":"b5605b52a6ca2b646cdf59b51d20874de1a7513a87a7bcd1efa45eb006c4261d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-06T14:51:17Z","title_canon_sha256":"f4d1c901d86ff091648fbf23d4c292f7bc36af16bc44a748b640a51e200ad76b"},"schema_version":"1.0","source":{"id":"2310.04292","kind":"arxiv","version":3}},"canonical_sha256":"31327d1136fd6a11bd943037cdb62236ff51ae1ae87b87533e297948f74a7316","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31327d1136fd6a11bd943037cdb62236ff51ae1ae87b87533e297948f74a7316","first_computed_at":"2026-07-05T07:02:05.816542Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:02:05.816542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rra5+KthsoFQidPm50fPU4AVLGti7lhrYB2FKcUUez9L4Cgbav6EcZUuwzSQ8NCb0ffdv4BOXI+JkSPJyV4wAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:02:05.817078Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.04292","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de54cf7bb1d4d6ce7045338b322e796b5de68888641cf7d9a7575908a160611b","sha256:0570a26e03f28bcb74231ecbe76fa3e11adfe763aa7aede4dff54886108ba115"],"state_sha256":"2bab01c33320a1038a16ff926bda52b79d83aa2d98b6b566d13a24e0ccea4f2e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YZmOinHNYgWMhosU1OYJdvCQu3yE4n5UwLnE7LILevEzejKJqWiMDcsT79N62Cs+7cKKhh9nSDIvVk0UCdFsAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:29:45.348715Z","bundle_sha256":"af651002d663019c9ad60d2a83433d55d6adab7ca1de2275707505e5dc362c59"}}