{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:S2YY4F5RJO7ACRYNXL2VHUJEON","short_pith_number":"pith:S2YY4F5R","canonical_record":{"source":{"id":"1904.10370","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2019-04-23T15:11:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7b7712c52c87cbef76bc409914511b2df7549f6fb90b19e1919cadc1e1df6a75","abstract_canon_sha256":"122bbac7dc1cba74e6934d0ecc88d3f58ff4727658f5dfab4624f44ab8bcd3e2"},"schema_version":"1.0"},"canonical_sha256":"96b18e17b14bbe01470dbaf553d124736b155a362663d2fff053edd9967e22de","source":{"kind":"arxiv","id":"1904.10370","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.10370","created_at":"2026-05-17T23:47:54Z"},{"alias_kind":"arxiv_version","alias_value":"1904.10370v1","created_at":"2026-05-17T23:47:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.10370","created_at":"2026-05-17T23:47:54Z"},{"alias_kind":"pith_short_12","alias_value":"S2YY4F5RJO7A","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"S2YY4F5RJO7ACRYN","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"S2YY4F5R","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:S2YY4F5RJO7ACRYNXL2VHUJEON","target":"record","payload":{"canonical_record":{"source":{"id":"1904.10370","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2019-04-23T15:11:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7b7712c52c87cbef76bc409914511b2df7549f6fb90b19e1919cadc1e1df6a75","abstract_canon_sha256":"122bbac7dc1cba74e6934d0ecc88d3f58ff4727658f5dfab4624f44ab8bcd3e2"},"schema_version":"1.0"},"canonical_sha256":"96b18e17b14bbe01470dbaf553d124736b155a362663d2fff053edd9967e22de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:54.311894Z","signature_b64":"5roo+vnpfSBX350bTkxn8uJ5Uxjh4irFt5n2Tsj3PN2ERCaTcCe+E0xzERzCERDYxKx8IhTZ13kF+T8DWtXcCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96b18e17b14bbe01470dbaf553d124736b155a362663d2fff053edd9967e22de","last_reissued_at":"2026-05-17T23:47:54.311335Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:54.311335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.10370","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":"2026-05-17T23:47:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BgBGkrooX5/uYSu1uNYTs8+ga4t2l2HbhqK4XK3po4JykNufSPNOEle0vdgZr4WP4Wv7o+P1ch39kR992cA/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T15:26:33.125952Z"},"content_sha256":"fc96da2ba09a181ce967e12cf6ba318e885e5663340827f202b180afd46c4d72","schema_version":"1.0","event_id":"sha256:fc96da2ba09a181ce967e12cf6ba318e885e5663340827f202b180afd46c4d72"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:S2YY4F5RJO7ACRYNXL2VHUJEON","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A survey on Big Data and Machine Learning for Chemistry","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.chem-ph","authors_text":"Dermot Diamond, Jose F Rodrigues Jr, Larisa Florea, Maria C F de Oliveira, Osvaldo N Oliveira Jr","submitted_at":"2019-04-23T15:11:45Z","abstract_excerpt":"Herein we review aspects of leading-edge research and innovation in chemistry which exploits big data and machine learning (ML), two computer science fields that combine to yield machine intelligence. ML can accelerate the solution of intricate chemical problems and even solve problems that otherwise would not be tractable. But the potential benefits of ML come at the cost of big data production; that is, the algorithms, in order to learn, demand large volumes of data of various natures and from different sources, from materials properties to sensor data. In the survey, we propose a roadmap fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.10370","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":""},"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":"2026-05-17T23:47:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EjgtcQ4VlOZEQyAKoJ1+ioLFiZj12meMymo0cfyXuo4DKvf6q7QB37Tvy6I1VeBrrVJd5dWiTfLv1VxaxFJGCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T15:26:33.126294Z"},"content_sha256":"3b8f7634a14d6947a887b7d3fe6fd48259f9a6468843085c5589fc9a0e200978","schema_version":"1.0","event_id":"sha256:3b8f7634a14d6947a887b7d3fe6fd48259f9a6468843085c5589fc9a0e200978"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S2YY4F5RJO7ACRYNXL2VHUJEON/bundle.json","state_url":"https://pith.science/pith/S2YY4F5RJO7ACRYNXL2VHUJEON/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S2YY4F5RJO7ACRYNXL2VHUJEON/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":"2026-05-28T15:26:33Z","links":{"resolver":"https://pith.science/pith/S2YY4F5RJO7ACRYNXL2VHUJEON","bundle":"https://pith.science/pith/S2YY4F5RJO7ACRYNXL2VHUJEON/bundle.json","state":"https://pith.science/pith/S2YY4F5RJO7ACRYNXL2VHUJEON/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S2YY4F5RJO7ACRYNXL2VHUJEON/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:S2YY4F5RJO7ACRYNXL2VHUJEON","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":"122bbac7dc1cba74e6934d0ecc88d3f58ff4727658f5dfab4624f44ab8bcd3e2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2019-04-23T15:11:45Z","title_canon_sha256":"7b7712c52c87cbef76bc409914511b2df7549f6fb90b19e1919cadc1e1df6a75"},"schema_version":"1.0","source":{"id":"1904.10370","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.10370","created_at":"2026-05-17T23:47:54Z"},{"alias_kind":"arxiv_version","alias_value":"1904.10370v1","created_at":"2026-05-17T23:47:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.10370","created_at":"2026-05-17T23:47:54Z"},{"alias_kind":"pith_short_12","alias_value":"S2YY4F5RJO7A","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"S2YY4F5RJO7ACRYN","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"S2YY4F5R","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:3b8f7634a14d6947a887b7d3fe6fd48259f9a6468843085c5589fc9a0e200978","target":"graph","created_at":"2026-05-17T23:47:54Z","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"},"paper":{"abstract_excerpt":"Herein we review aspects of leading-edge research and innovation in chemistry which exploits big data and machine learning (ML), two computer science fields that combine to yield machine intelligence. ML can accelerate the solution of intricate chemical problems and even solve problems that otherwise would not be tractable. But the potential benefits of ML come at the cost of big data production; that is, the algorithms, in order to learn, demand large volumes of data of various natures and from different sources, from materials properties to sensor data. In the survey, we propose a roadmap fo","authors_text":"Dermot Diamond, Jose F Rodrigues Jr, Larisa Florea, Maria C F de Oliveira, Osvaldo N Oliveira Jr","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2019-04-23T15:11:45Z","title":"A survey on Big Data and Machine Learning for Chemistry"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.10370","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:fc96da2ba09a181ce967e12cf6ba318e885e5663340827f202b180afd46c4d72","target":"record","created_at":"2026-05-17T23:47:54Z","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":"122bbac7dc1cba74e6934d0ecc88d3f58ff4727658f5dfab4624f44ab8bcd3e2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2019-04-23T15:11:45Z","title_canon_sha256":"7b7712c52c87cbef76bc409914511b2df7549f6fb90b19e1919cadc1e1df6a75"},"schema_version":"1.0","source":{"id":"1904.10370","kind":"arxiv","version":1}},"canonical_sha256":"96b18e17b14bbe01470dbaf553d124736b155a362663d2fff053edd9967e22de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96b18e17b14bbe01470dbaf553d124736b155a362663d2fff053edd9967e22de","first_computed_at":"2026-05-17T23:47:54.311335Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:54.311335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5roo+vnpfSBX350bTkxn8uJ5Uxjh4irFt5n2Tsj3PN2ERCaTcCe+E0xzERzCERDYxKx8IhTZ13kF+T8DWtXcCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:54.311894Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.10370","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc96da2ba09a181ce967e12cf6ba318e885e5663340827f202b180afd46c4d72","sha256:3b8f7634a14d6947a887b7d3fe6fd48259f9a6468843085c5589fc9a0e200978"],"state_sha256":"7436f191f4914716eeac721be174f2a56af3ae73abb7fb5bc7a9a933315e199c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2Pc3LTYSWFcZc4Buu0yeVzi40Zgld2iw3WfljCqYZBKB3RqHkmQxUL/lzLG1ooGezDtXq6QEKi6HdmF+lgL7BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T15:26:33.128304Z","bundle_sha256":"339289f790fe3776ed1bee02b090093410953640b1d0fd2a34a06eef60cccc7c"}}