{"as_of":"2026-08-13T06:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9b829f184643b04e6891d2472a27e97a755434ee74294a5998603ddc586f9669","coverage":[{"denominator":174,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T16:20:13.284487Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2411.13688/citation-record","integrity":"/paper/2411.13688/integrity","json":"/paper/2411.13688/citation-record.json","paper":"/paper/2411.13688"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.630627Z","title":null,"venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.630627Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:94b3ffd7e325795cc4438b0dfd2c934c6d506713febebc43e6e3837262a4df52","observation_id":"1a893619-efa3-4a55-b824-d6c534d9e275","resolution":{"observed_at":"2026-08-12T16:20:12.630627Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-08-12T14:19:29.389332Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-12T16:20:12.636797Z","title":"Very deep convolutional networks for large-scale image recognition","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.636797Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:a0e2aad15ea59b120177ad89850bb041cea9ad7f784f321f46f0116027cd1fd3","observation_id":"b9addd10-8ca0-4229-90e7-023a8b419fa1","resolution":{"observed_at":"2026-08-12T16:20:12.636797Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.643279Z","title":"Zeiler and Rob Fergus","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.643279Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:86210535493bfb22d7f8be4e72c93aff67974db956e46b597d825027725383a2","observation_id":"0988d2dd-d9be-4e71-b393-c74ae7095c4e","resolution":{"observed_at":"2026-08-12T16:20:12.643279Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.649168Z","title":"Going deeper with convolutions","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.649168Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:ad7688e74c1e5fe3d88d38db02c20afe69d9785e278cb3ac2436f19b9da09848","observation_id":"824fee54-9ce2-41fd-846a-e406ff8c8007","resolution":{"observed_at":"2026-08-12T16:20:12.649168Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.655057Z","title":"Deep residual learn- ing for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.655057Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:3ac28ef684a54dc25e6304557c353265bd08b1e23e600faaea3e2a618dc307dd","observation_id":"702e90d9-c3af-4e12-b99f-0f19f9714eca","resolution":{"observed_at":"2026-08-12T16:20:12.655057Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.660591Z","title":"A comprehensive comparison of molecular feature representations for use in predictive modeling","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.660591Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:09df60f63b29a928386701c94c818d5f7fb2c1a573601a197ade523273950748","observation_id":"af9fddb4-4a6a-4dcb-958d-85ab5128c3c0","resolution":{"observed_at":"2026-08-12T16:20:12.660591Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.666690Z","title":"Large-scale comparison of machine learning methods for drug target prediction on ChEMBL","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.666690Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:030eb6c7b48fa62e29c9872a36fe159748e991eb8ea8eadc718c164134b9c93e","observation_id":"124f2f91-5342-46d0-a48e-ed44c455ce4c","resolution":{"observed_at":"2026-08-12T16:20:12.666690Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.671675Z","title":"Could 163 graph neural networks learn better molecular representation for drug discov- ery? A comparison study of descriptor-based and graph-based models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.671675Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:0d627df1c52a76905d89cd23684cfec1b4ef6cccc053ce11194b2f01ea08157a","observation_id":"4f9559df-b320-437d-aed0-0dbaf4cc24a3","resolution":{"observed_at":"2026-08-12T16:20:12.671675Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.10056","last_updated":"2022-01-17T22:16:20Z","snapshot_observed_at":"2026-08-10T17:59:12.666725Z","submitted_at":"2021-02-19T17:35:18Z","title":"Molecular Contrastive Learning of Representations via Graph Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.10056","snapshot_observed_at":"2026-08-12T16:20:12.677479Z","title":"Mol- CLR: Molecular contrastive learning of representations via graph neural net- works","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.677479Z"},"links":{"cited_paper":"/paper/2102.10056","citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:9eb5dc4fb2b1e9f3e2a66fb6725a8b1912467e2a542a17e256bf6ef99400f739","observation_id":"3aae7c13-1b5f-40cc-bdd7-6d93853619a2","resolution":{"observed_at":"2026-08-12T16:20:12.677479Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.682869Z","title":"Using domain-specific fingerprints generated through neural networks to enhance ligand-based virtual screening","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.682869Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:85b59428a5b67b5ad7ffa705c7c16403a8f530c6c76e7bb5e164aa7f2cfd0d18","observation_id":"f493888c-895f-4481-bf92-8cec0b86ffe3","resolution":{"observed_at":"2026-08-12T16:20:12.682869Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.09885","last_updated":"2020-10-23T04:22:37Z","snapshot_observed_at":"2026-08-08T06:02:13.053327Z","submitted_at":"2020-10-19T21:41:41Z","title":"ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.09885","snapshot_observed_at":"2026-08-12T16:20:12.690963Z","title":"ChemBERTa: Large-Scale self-supervised pretraining for molecular property prediction","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.690963Z"},"links":{"cited_paper":"/paper/2010.09885","citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:2332816e5d0ef700f1b2fd2e67b704e96e853a4422630678391f2f5c970f6053","observation_id":"6f057a23-d8d9-4469-b627-0153bbd3c1c9","resolution":{"observed_at":"2026-08-12T16:20:12.690963Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.02604","last_updated":"2021-07-28T15:30:22Z","snapshot_observed_at":"2026-07-06T10:56:57.973956Z","submitted_at":"2021-03-20T21:45:22Z","title":"Using Molecular Embeddings in QSAR Modeling: Does it Make a Difference?","version":2},"cited_work":{"arxiv_id":"2104.02604","doi":null,"metadata_source":"pith","pith_arxiv_id":"2104.02604","snapshot_observed_at":"2026-08-12T16:20:14.715483Z","title":"Using Molecular Embeddings in QSAR Modeling: Does it Make a Difference?","venue":"q-bio.BM","work_id":"846c3d79-6fdd-46a1-9444-4495d0611cc8","year":2021},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.700609Z"},"links":{"cited_paper":"/paper/2104.02604","citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:5c1b1031ff4a87ae69ba9fdd04a8675a3422ccc584efb60da8e6453e39b69041","observation_id":"7eeff78b-d600-4187-a143-dabcf111b26e","resolution":{"observed_at":"2026-08-12T16:20:14.725906Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.708785Z","title":"Learn- ing continuous and data-driven molecular descriptors by translating equivalent chemical representations","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.708785Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:2669235fa89260326c92fa5c6a978101aa3b4d8fd9ff2d9d58a2e7024831a146","observation_id":"7b8a21e7-a17c-4057-84da-922029d2e8b3","resolution":{"observed_at":"2026-08-12T16:20:12.708785Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.720660Z","title":"Handbook of Molecular Descriptors","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.720660Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:8c75463e4110b30b92adae6ac4c3922feb09567c2f9a43737c948af5df912d76","observation_id":"cea2ab5a-a91c-46ed-9a1e-37375122d59e","resolution":{"observed_at":"2026-08-12T16:20:12.720660Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.725875Z","title":"Fingerprints, and other molec- ular descriptions for database analysis and searching","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.725875Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:9c80724396a9992fcf40ef18260e37dad8911d5d4a8d8c32500c22f3de0df8c7","observation_id":"981af4d6-2a24-4eac-994b-c01eed5d52fe","resolution":{"observed_at":"2026-08-12T16:20:12.725875Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.732626Z","title":"Extended-connectivity fingerprints","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.732626Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:ca00e27182bd2095ef802cfcd19dc854f484b50affd063a644207a2f6ab3a6b5","observation_id":"f03acb23-57c5-4770-a443-9fedd47d8855","resolution":{"observed_at":"2026-08-12T16:20:12.732626Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.738379Z","title":"Schoenholz, Patrick F","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.738379Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:6691cfce608aa8b2f51b0999d6cda1071d1f92940889ef388d3fe01a074f8c0a","observation_id":"bde524d1-a1da-496b-9127-e1e4aa618957","resolution":{"observed_at":"2026-08-12T16:20:12.738379Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1609.02907","last_updated":"2017-02-22T09:55:36Z","snapshot_observed_at":"2026-07-06T05:10:16.862707Z","submitted_at":"2016-09-09T19:48:41Z","title":"Semi-Supervised Classification with Graph Convolutional Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.02907","snapshot_observed_at":"2026-08-12T16:20:12.743736Z","title":"Kipf and Max Welling","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.743736Z"},"links":{"cited_paper":"/paper/1609.02907","citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:5854728ac4a5eff55c1ae56a0cbc4b85fd08f7c94b0c6bacf74ab1846cc8c842","observation_id":"88b30a78-bea1-4650-86aa-a559cfcad4da","resolution":{"observed_at":"2026-08-12T16:20:12.743736Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.750663Z","title":"Molecular graph convolutions: Moving beyond fingerprints","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.750663Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:ed1d41037ad3392188ca297389309265d87795b21cd772aa6bd71b1008cba2fb","observation_id":"3afc0037-4108-4171-9c30-aa68a76ce91e","resolution":{"observed_at":"2026-08-12T16:20:12.750663Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.756398Z","title":"Duvenaud, Dougal Maclaurin, Jorge Iparraguirre, Rafael Bombarell, Timothy Hirzel, Al´ an Aspuru-Guzik, and Ryan P","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.756398Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:bcc339e4163f917bf2b2d6e9a82204261329cacbdc4f900175ecfc2b8c343d21","observation_id":"c33ed13d-6b7a-42e6-b9da-9a825e375e79","resolution":{"observed_at":"2026-08-12T16:20:12.756398Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1905.12265","last_updated":"2020-02-18T19:49:48Z","snapshot_observed_at":"2026-08-04T16:33:25.229105Z","submitted_at":"2019-05-29T08:11:52Z","title":"Strategies for Pre-training Graph Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.12265","snapshot_observed_at":"2026-08-12T16:20:12.762020Z","title":"Strategies for pre-training graph neural networks","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.762020Z"},"links":{"cited_paper":"/paper/1905.12265","citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:b35b6a7999b9d5326c6584f8904afa5a0c776915c02cd96f2d080460abc4cb03","observation_id":"2d97a4fe-8b90-451b-9fc6-b3e3e2611f9f","resolution":{"observed_at":"2026-08-12T16:20:12.762020Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.767749Z","title":"Analyzing learned molecular representations for property prediction","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.767749Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:860181d3f744929113045bcb5a5a206ef759e9bf13567040fa9f916c51cafaec","observation_id":"9a7109d2-c896-4e94-84cc-a3cd308f6ea1","resolution":{"observed_at":"2026-08-12T16:20:12.767749Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.773067Z","title":"Yu Philip","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.773067Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:2dcad78154180779c315dd7f9c886f6e267be4efd57ced407270f64a5a360578","observation_id":"37d3f98f-7675-4c65-a4a3-baec6b298e92","resolution":{"observed_at":"2026-08-12T16:20:12.773067Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.778206Z","title":"A compact review of molecu- lar property prediction with graph neural networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.778206Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:b8a600416c1bb45e5f6c468dc52ada0d2ef8088093f4aacded69e959dbbdef5b","observation_id":"8e1057f3-a171-46fd-b5cc-a7e6961c65f6","resolution":{"observed_at":"2026-08-12T16:20:12.778206Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1511.05493","last_updated":"2017-09-22T21:36:00Z","snapshot_observed_at":"2026-07-06T04:36:48.493556Z","submitted_at":"2015-11-17T18:10:12Z","title":"Gated Graph Sequence Neural Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1511.05493","snapshot_observed_at":"2026-08-12T16:20:12.783499Z","title":"Gated graph sequence neural networks","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.783499Z"},"links":{"cited_paper":"/paper/1511.05493","citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:94ee4d925d7b46771a5e3c6620b04614b7dcde836d5551eb082352af0dcb6692","observation_id":"ae4346d7-f469-411d-a0ec-1660cf052c0a","resolution":{"observed_at":"2026-08-12T16:20:12.783499Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.789294Z","title":"Interaction networks for learning about objects, relations and physics","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.789294Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:b20196ce0df696e7af2dcf7e800a452c29ebecf485b1671cc5cf44a9eed2df9c","observation_id":"78fc3984-bcd7-4e50-b590-3fcb08b915aa","resolution":{"observed_at":"2026-08-12T16:20:12.789294Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.794984Z","title":"Convolutional neural networks on graphs with fast localized spectral filtering","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.794984Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:cf8eff59a6431772b4d4f75667b32146ce04807dcd4aa0bb2169204d6a31f72c","observation_id":"8566a170-f70c-4719-8059-72c583af2647","resolution":{"observed_at":"2026-08-12T16:20:12.794984Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.801046Z","title":"Chemi-Net: A molecular graph convo- lutional network for accurate drug property prediction","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.801046Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:83e9c10af1e65ec2a531efc17c55166e7c1e2d9669bf6d68807c99eea7567aaa","observation_id":"c1a8921c-9d55-4a25-9306-0d036b699b69","resolution":{"observed_at":"2026-08-12T16:20:12.801046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.00826","last_updated":"2019-02-22T19:15:54Z","snapshot_observed_at":"2026-08-13T05:06:48.606308Z","submitted_at":"2018-10-01T17:11:31Z","title":"How Powerful are Graph Neural Networks?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.00826","snapshot_observed_at":"2026-08-12T16:20:12.806384Z","title":"How powerful are graph neural networks? arXiv preprint arXiv:1810.00826 , 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.806384Z"},"links":{"cited_paper":"/paper/1810.00826","citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:1006870225419b25baed775a2f244bd0aecb20f7e3478d6353151286b88eff9c","observation_id":"fe47c212-fa2f-4830-bde4-5f196c608103","resolution":{"observed_at":"2026-08-12T16:20:12.806384Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.812855Z","title":"Towards deeper graph neural networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.812855Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:07a9d398bc2d58b52822419f947e7f8cff7cec19c90a70ac149275e0d5b4720c","observation_id":"2d3921da-81ab-4660-8640-c1825c264cb2","resolution":{"observed_at":"2026-08-12T16:20:12.812855Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.818603Z","title":"Universal readout for graph convolutional neural networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.818603Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:b5baec0cc84fb94dee1e5d4d54113fd786a21c8fa5e3c71213d15407915a8f65","observation_id":"a8b75008-9d47-47d0-b64f-7d928c42317a","resolution":{"observed_at":"2026-08-12T16:20:12.818603Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.824661Z","title":"Quantitative evaluation of explainable graph neural networks for molecular property predic- tion","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.824661Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:642f68bd82370e39c1c54e25b002e502a300c79a472205ce91e143990ef53035","observation_id":"18211412-d150-46bc-8371-0a99c78e6ca9","resolution":{"observed_at":"2026-08-12T16:20:12.824661Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.831714Z","title":"Geometric deep learning au- tonomously learns chemical features that outperform those engineered by do- main experts","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.831714Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:e4e3a63f2b344c1079af5c85bb6dc415e25e20c85c2b87c4bddd23972101bd32","observation_id":"7e085498-0de2-4a74-a04f-9a508db1bcfc","resolution":{"observed_at":"2026-08-12T16:20:12.831714Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1802.04944","last_updated":"2018-05-20T14:28:06Z","snapshot_observed_at":"2026-07-06T06:23:19.106346Z","submitted_at":"2018-02-14T03:52:58Z","title":"Edge Attention-based Multi-Relational Graph Convolutional Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.04944","snapshot_observed_at":"2026-08-12T16:20:12.838426Z","title":"Edge attention-based multi-relational graph convolutional networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.838426Z"},"links":{"cited_paper":"/paper/1802.04944","citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:10d2a434e5b594fd48efcd917e23b34f33a47d8bea6faff41b63336c3d73b855","observation_id":"ead447cd-a435-4fb8-ac3b-dcd5d3556624","resolution":{"observed_at":"2026-08-12T16:20:12.838426Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1709.03741","last_updated":"2017-09-16T03:21:59Z","snapshot_observed_at":"2026-07-06T05:59:13.356080Z","submitted_at":"2017-09-12T08:41:39Z","title":"Learning Graph-Level Representation for Drug Discovery","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1709.03741","snapshot_observed_at":"2026-08-12T16:20:12.843758Z","title":"Learning graph-level representation for drug discovery","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.843758Z"},"links":{"cited_paper":"/paper/1709.03741","citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:3328eb73a8e81676bdb3400aa36840443ef49096cc8263d196b1c52873766ecf","observation_id":"953995e7-698b-4df6-9be3-7b417293df4e","resolution":{"observed_at":"2026-08-12T16:20:12.843758Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.851135Z","title":"Pushing the boundaries of molecular representation for drug discovery with the graph attention mechanism","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.851135Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:17c96480a856afaec49cc87f4469200bef478665d239119a03e2f9a6b50eea2b","observation_id":"4f67e176-aff9-4aeb-9830-834fd5bfd2ce","resolution":{"observed_at":"2026-08-12T16:20:12.851135Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.26434/chemrxiv-2022-mfq52","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.882433Z","title":"Exposing the limitations of molecular machine learning with activity cliffs","venue":null,"work_id":"4474be8e-4925-4a79-a1c5-6d4d90843c22","year":2022},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.859035Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:3f016e4628d5d61936623daa33fb054ba21f979fbfbf8eb9442246ee6ee80719","observation_id":"636b7588-d29f-420e-b461-970a2be7b3d5","resolution":{"observed_at":"2026-08-12T16:20:13.890610Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.866331Z","title":"QSAR, rational approaches to the design of bioactive compounds","venue":null,"work_id":null,"year":1991},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.866331Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:d18483d08285d319eda0d95c508308c694fbcf9e873d522ffba4a60c4575f5d1","observation_id":"04fb3dfe-3553-42bb-9aa7-2e361c1b1d3e","resolution":{"observed_at":"2026-08-12T16:20:12.866331Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.871973Z","title":"Maggiora","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.871973Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:18a00fc14e8d9cee278f7171b0e5d1a7887fc5a0bd653eb58ee0e7d21453d269","observation_id":"303a8986-33e2-4ef0-87dd-264a225e3e37","resolution":{"observed_at":"2026-08-12T16:20:12.871973Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.878739Z","title":"Sheridan, Prabha Karnachi, Matthew Tudor, Yuting Xu, Andy Liaw, Falgun Shah, Alan C","venue":null,"work_id":null,"year":1969},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.878739Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:192e53e4370705cd77ea0e97611a176937b5bd2fdb4fd7766cbf1320cc28a0f1","observation_id":"bd16c900-65b5-490d-ba80-5a3c1e384e22","resolution":{"observed_at":"2026-08-12T16:20:12.878739Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.884087Z","title":"Medina-Franco, Yunierkis P´ erez-Castillo, Orazio Nicolotti, M","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.884087Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:e94aded86e257586953aa2616b40540495cd77da6002d16d19a569d1397c9fd2","observation_id":"972968ce-6c4f-467a-aa3c-869c75341d16","resolution":{"observed_at":"2026-08-12T16:20:12.884087Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.889841Z","title":"Recent progress in understanding activity cliffs and their utility in medicinal chem- istry: miniperspective","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.889841Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:9f46d3961e8e2d6efee4b140a3f9864a1ce9c0ac61b79f7e8b7df135eb93c2fc","observation_id":"25f9ff5f-6b16-4762-baa2-4d9edf5b6d4a","resolution":{"observed_at":"2026-08-12T16:20:12.889841Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.895341Z","title":"Evolving concept of ac- tivity cliffs","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.895341Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:d108d559510b71b0381829d9867f3bec1047fb6131f492b907bb43b8a7b268eb","observation_id":"dd340442-4a74-4403-a3fb-727dab277629","resolution":{"observed_at":"2026-08-12T16:20:12.895341Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.902722Z","title":"Advances in exploring activity cliffs","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.902722Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:4b05a56608b25cf9ea0b8c76228b4c91d9a718d2495aa8790f05921cf31b6a7c","observation_id":"ca88f901-9569-4d13-9ae5-78b1cee4b1ee","resolution":{"observed_at":"2026-08-12T16:20:12.902722Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.911673Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.911673Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:4c403d7bcd4d391625c826fceb6f10d4a9b9427c4e8b78c9495db282c167640f","observation_id":"4213a813-835c-4654-b26e-2ef9d6c32562","resolution":{"observed_at":"2026-08-12T16:20:12.911673Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"5914.34241","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:14.466587Z","title":"Mor- ris","venue":null,"work_id":"5a57382e-7a36-431f-8c27-79ab45ad82b0","year":2023},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.917528Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:a3288ca21824ff8e3b4e3766359f70e656ef26279136630b96f0a619b28da770","observation_id":"ce7262dd-f519-4cf3-8340-c83248c2a743","resolution":{"observed_at":"2026-08-12T16:20:14.481453Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.13140/rg.2.2.18137","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.841728Z","title":null,"venue":null,"work_id":"acde43ab-7541-4264-8561-fb32dd1e7e74","year":2021},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.925048Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:327bdfe5af6ee4d3bb27679de5b1903d0c2b1392f265a27eb09a044cd06abb42","observation_id":"79759f54-86bb-42cc-9b64-e4c877b0e201","resolution":{"observed_at":"2026-08-12T16:20:13.848449Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.930818Z","title":"(2022) Reduced collision fingerprints and pairwise molec- ular comparisons for explainable property prediction using deep learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.930818Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:4cb2a0c22e271c3588cb54bb0179935fefdf66e904c571205dcd6f0cf2584965","observation_id":"e42e58e4-3de5-4136-a0b6-03d08caa9e49","resolution":{"observed_at":"2026-08-12T16:20:12.930818Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1706.06689","last_updated":"2017-06-20T22:25:57Z","snapshot_observed_at":"2026-08-05T14:15:02.425071Z","submitted_at":"2017-06-20T22:25:57Z","title":"Chemception: A Deep Neural Network with Minimal Chemistry Knowledge Matches the Performance of Expert-developed QSAR/QSPR Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.06689","snapshot_observed_at":"2026-08-12T16:20:12.940875Z","title":"Goh, Charles Siegel, Abhinav Vishnu, Nathan O","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.940875Z"},"links":{"cited_paper":"/paper/1706.06689","citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:32b5911ad0b4f6e9da1ce7c77ff2672a3d64b544ca1809b4c38f1d2a551a8a1b","observation_id":"64680b10-8b0b-457c-90a3-71e039a72d0e","resolution":{"observed_at":"2026-08-12T16:20:12.940875Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.949222Z","title":"Prediction of molecular properties using molecular topo- graphic map","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.949222Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:8c7a8bb1e265881d089292cd4bb166a37cfffad7506e105bd0178b7e22fffc9b","observation_id":"246839b9-688c-471c-8763-e89a98032323","resolution":{"observed_at":"2026-08-12T16:20:12.949222Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.959781Z","title":"Prediction of activity cliffs on the basis of images using convolutional neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.959781Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:d88cd51d08a273313f50884e409ea5104c750fab9ad0f506e9b46c06213ed21a","observation_id":"e6f2ebd3-093f-4955-a2b1-3d2aea8b0d22","resolution":{"observed_at":"2026-08-12T16:20:12.959781Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.968566Z","title":"Can one hear the shape of a molecule (from its Coulomb matrix eigenvalues)? Journal of Chemical Information and Modeling, 60(8):3804–3811, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.968566Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:e59403822fa55945cec400a5f63b7591873c7705d08f8e038f698d8c0c0687d3","observation_id":"71d79aac-17ab-4990-b51f-548dec757728","resolution":{"observed_at":"2026-08-12T16:20:12.968566Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.974336Z","title":"Uni-Mol: A universal 3D molecu- lar representation learning framework","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.974336Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:c309c9451845c31fab2a21b8373907239a395afa80b0b9764156d3bc0a2302b5","observation_id":"1595917c-5443-4ef6-a621-36ee46263fc6","resolution":{"observed_at":"2026-08-12T16:20:12.974336Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.981203Z","title":"Keith Lloyd, and Robin J","venue":null,"work_id":null,"year":1936},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.981203Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:c3062188fe152797487b3edbb2b872fed22a815eab0b47b55c246ffea1a4cbbb","observation_id":"a007340a-9b6d-47ff-8ed8-3a67ba190878","resolution":{"observed_at":"2026-08-12T16:20:12.981203Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.04444","last_updated":"2021-02-12T09:08:20Z","snapshot_observed_at":"2026-08-03T17:18:04.652027Z","submitted_at":"2020-11-23T15:01:44Z","title":"Comparison of Atom Representations in Graph Neural Networks for Molecular Property Prediction","version":2},"cited_work":{"arxiv_id":"2012.04444","doi":null,"metadata_source":"pith","pith_arxiv_id":"2012.04444","snapshot_observed_at":"2026-08-12T16:20:14.302918Z","title":"Comparison of Atom Representations in Graph Neural Networks for Molecular Property Prediction","venue":"physics.chem-ph","work_id":"e098fb0f-440d-45be-b363-7d5946c0c1dc","year":2020},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.986419Z"},"links":{"cited_paper":"/paper/2012.04444","citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:9b89aecec36313d617ab48314593abb90dd566280ccfe5368ff04687048376f5","observation_id":"5fd9e835-8073-49a1-bde0-f4fb132846a2","resolution":{"observed_at":"2026-08-12T16:20:14.308988Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.993686Z","title":"SMILES, a chemical language and information system","venue":null,"work_id":null,"year":1988},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.993686Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:c2c0260957c86991f38133f3fdb17d4d75e000bb7fdb534d5caada59448e663e","observation_id":"03706ee5-e400-4909-bc15-98ed694d6a4b","resolution":{"observed_at":"2026-08-12T16:20:12.993686Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:12.999091Z","title":"Weininger","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:12.999091Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:f7c906dcce07dfe8695a0bf88b73972433f705d6a50d34cf1b004b0d342b14e2","observation_id":"6a264574-0da5-4a83-8486-8f09fb343bdc","resolution":{"observed_at":"2026-08-12T16:20:12.999091Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.006010Z","title":"Graphical depiction of chemical structures","venue":null,"work_id":null,"year":1990},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.006010Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:ba2a73a3b5ecab0e1ded481425df737f0f1b44a2a1d153cf59195543ecd72ff4","observation_id":"2aa7ebf1-d347-4129-a7bc-33dad3e53973","resolution":{"observed_at":"2026-08-12T16:20:13.006010Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.014146Z","title":"Image: Deriving the SMILES represen- tation of a chemical molecule, Shown example: ciprofloxacin, a fluoroquinolone antibiotic","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.014146Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:42731ff0bd1ce20cc4ba244fb68a253ea9daca0ddc8f1a72b09e2ebf5399933c","observation_id":"3bdaa187-5265-41a3-91a1-078265ee4f55","resolution":{"observed_at":"2026-08-12T16:20:13.014146Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.020118Z","title":"InChI - the worldwide chemical structure identifier standard","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.020118Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:4dc9aade75b66a8f92f2eb2ac3095f42dea9284f4d2475e00cbaf4090695478a","observation_id":"dd900880-cc73-4374-98c2-b0059880208a","resolution":{"observed_at":"2026-08-12T16:20:13.020118Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.025504Z","title":"Wei, David Duvenaud, Jos´ e Miguel Hern´ andez-Lobato, Benjam ´ ın S´ anchez-Lengeling, Dennis Sheberla, Jorge Aguilera-Iparraguirre, Timothy D","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.025504Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:b6d83369e847a349f36647d25070545ce58d39e5767d473c2e28dffc4c4fd022","observation_id":"31381c4b-59a5-404b-82ff-37a6209913ca","resolution":{"observed_at":"2026-08-12T16:20:13.025504Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.030467Z","title":"Self-referencing embedded strings (SELFIES): A 100% robust molecular string representation","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.030467Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:47b059cbd83bcf1fb57bf429d2efada78e9dc6a627358f878cef936d82c9703b","observation_id":"d58e7c93-8127-4667-9e26-1af2e4373266","resolution":{"observed_at":"2026-08-12T16:20:13.030467Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.037409Z","title":"DeepSMILES: An adaptation of SMILES for use in machine-learning of chemical structures","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.037409Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:da1a3fd047c308d3b743a1bc06b54110c1f807c8cd8022504e0e22173bb8a5a9","observation_id":"682e2f58-1826-4cae-b2c0-4578975f49bf","resolution":{"observed_at":"2026-08-12T16:20:13.037409Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.042926Z","title":null,"venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.042926Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:2a107bec3c86ae15da45407fc2bc9b62f97014919c04f4ad8c93170931bf098f","observation_id":"6ec173a4-6eb3-4ad1-b48a-58640208d01c","resolution":{"observed_at":"2026-08-12T16:20:13.042926Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.049844Z","title":"Mold 2, molecular descriptors 169 from 2D structures for chemoinformatics and toxicoinformatics","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.049844Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:7658ddee8b8d8a27975bb6c8c1abf8215175a6dde1623b4427eb58ed0f3b4e2e","observation_id":"6829e4f6-6cdc-4082-8905-1661a4e54f73","resolution":{"observed_at":"2026-08-12T16:20:13.049844Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.057044Z","title":"Molecular descriptors in chemoinformatics, computational combinatorial chemistry, and virtual screening","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.057044Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:ad5d7cf2bd48e7c9113787f8f6916f38178bfa2dc949ffd3b5bc7c327b8af108","observation_id":"61572a8f-fcf8-4cd5-a899-cf654b15dad1","resolution":{"observed_at":"2026-08-12T16:20:13.057044Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.063153Z","title":"Molecular descriptors","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.063153Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:debdc7c907a2c3cb2d6faabd25eb9f4a86bc3c083206432ba9abf2afb284c8ca","observation_id":"7a4871b8-5677-42ee-80eb-c24b35f7bcae","resolution":{"observed_at":"2026-08-12T16:20:13.063153Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.068616Z","title":"Lipinski, Franco Lombardo, Beryl W","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.068616Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:74b142b2221017ae0c721b6d9b532f0368598f56c54121c5516009a4155df8ad","observation_id":"54d067c5-e486-44a9-8db6-d9413bd7ab96","resolution":{"observed_at":"2026-08-12T16:20:13.068616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.073733Z","title":"Wildman and Gordon M","venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.073733Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:a305957a409dd4ea83cafa06cd3408bc9660b0f6ad0ec2afc9fec6b4be0f2642","observation_id":"e64618ca-e830-4d9a-b86e-7ce1d172304b","resolution":{"observed_at":"2026-08-12T16:20:13.073733Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.078794Z","title":"RDKit: Open-source cheminformatics","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.078794Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:0beddfc14062a4a0d67debde3b25d99ec7079a1b8a3282ccd28a01de6146098b","observation_id":"a9c71a91-a18f-475c-ae39-1c66b250beda","resolution":{"observed_at":"2026-08-12T16:20:13.078794Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.084786Z","title":null,"venue":null,"work_id":null,"year":1982},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.084786Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:a7e966f1670cc99039ce3890f59a0a101c60c4970105343c2589bf8a0edefd8d","observation_id":"145fa826-29bc-41f8-a0c5-2f9f35a2fd03","resolution":{"observed_at":"2026-08-12T16:20:13.084786Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2011.13230","last_updated":"2020-11-26T10:55:05Z","snapshot_observed_at":"2026-08-11T00:35:07.298620Z","submitted_at":"2020-11-26T10:55:05Z","title":"Molecular representation learning with language models and domain-relevant auxiliary tasks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.13230","snapshot_observed_at":"2026-08-12T16:20:13.091665Z","title":"Molecular representation learn- ing with language models and domain-relevant auxiliary tasks","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.091665Z"},"links":{"cited_paper":"/paper/2011.13230","citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:68efc102d44c197a4b8d24b0ad0b5a02f057716958fc48bf80bf81e81e6b5eba","observation_id":"d92a413c-e113-4830-b3b1-ee9568381927","resolution":{"observed_at":"2026-08-12T16:20:13.091665Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.097921Z","title":null,"venue":null,"work_id":null,"year":1965},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.097921Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:b48aa0a40b1307ec866bd91b11bbce557c11fa28254f7079901dd21c4683b3ec","observation_id":"13285e04-6dcc-4c18-a962-660e4db9c60e","resolution":{"observed_at":"2026-08-12T16:20:13.097921Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.104265Z","title":"Durant, Burton A","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.104265Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:0a36eaa645093b556b70e3528dd0b2055b0d5a8fe5a4fb72024d43f881a1232e","observation_id":"bc9cd035-f178-4e7a-a8d7-e83d5ba07600","resolution":{"observed_at":"2026-08-12T16:20:13.104265Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.110259Z","title":"URL https://ftp","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.110259Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:54d137da7ad4b4d2ec72a42e55886ec42db06b6bca01b477a259c76903e2f3da","observation_id":"3809a635-f52e-4d5c-856d-9e3c40b20cc7","resolution":{"observed_at":"2026-08-12T16:20:13.110259Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.117165Z","title":null,"venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.117165Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:122eb04fd9a1acf46bbe3341330b3703ba4d3e42439e0b951bc6d39c63e28749","observation_id":"02aec52f-583c-439e-8739-f73764faba6d","resolution":{"observed_at":"2026-08-12T16:20:13.117165Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.122253Z","title":"URL https:// www.daylight.com/dayhtml/doc/theory/theory.finger.html","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.122253Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:dc1c3bd457eece9cf0e422624ea1ed0ccfa6ce10a870e2578f89debbdef836fb","observation_id":"cfb608e9-0fa8-40a9-8924-bf538ca111ce","resolution":{"observed_at":"2026-08-12T16:20:13.122253Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.129518Z","title":"Open-source platform to benchmark fin- gerprints for ligand-based virtual screening","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.129518Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:14f977341af17dbcb0ddb70f694674f558db8b5a3600f9c98d3a0157e19f7e0e","observation_id":"d14f8beb-413e-4621-a43b-d5d30ad1fb91","resolution":{"observed_at":"2026-08-12T16:20:13.129518Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.136451Z","title":"Webel, Talia B","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.136451Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:9c9f21856db080a0184b434c1733b7f30498dc9054a510cd3e71346e3881a74d","observation_id":"3e6266f3-09ed-4f49-8c1d-24c450b69b84","resolution":{"observed_at":"2026-08-12T16:20:13.136451Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.142753Z","title":"Brown, and Mathew Hahn","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.142753Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:0ce4537964d75f5ac36c6545d5eea2ee5eb51153f46467f38b9010b60dc95252","observation_id":"76a931d6-1324-4a98-b6fc-ca222bac3f0b","resolution":{"observed_at":"2026-08-12T16:20:13.142753Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.148725Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.148725Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:a1eaf7cbcc174600507ecf5c8ce306573b0d769d2343fc956c7f067e55fc98a1","observation_id":"e7bc12c5-41cf-4d5f-8380-3d7eed760e70","resolution":{"observed_at":"2026-08-12T16:20:13.148725Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.157031Z","title":"Bronstein, Joan Bruna, Yann LeCun, Arthur Szlam, and Pierre Vandergheynst","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.157031Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:b4d9606505f86eede0489b9e2c4197b30e5d8e1963fd5543dfaf04c71c21e91b","observation_id":"db1bf406-3aba-4e28-905e-1dc5fe97bb90","resolution":{"observed_at":"2026-08-12T16:20:13.157031Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.13478","last_updated":"2021-05-02T16:16:03Z","snapshot_observed_at":"2026-08-12T23:06:05.148534Z","submitted_at":"2021-04-27T21:09:51Z","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.13478","snapshot_observed_at":"2026-08-12T16:20:13.166070Z","title":"Bronstein, Joan Bruna, Taco Cohen, and Petar Veliˇ ckovi´ c","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.166070Z"},"links":{"cited_paper":"/paper/2104.13478","citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:e5bcc627ef77aadda556a4bb752959f49823c26e061a81c3d0628fc943abc0cc","observation_id":"6180b2ef-80cd-47ef-9f39-3ca371713007","resolution":{"observed_at":"2026-08-12T16:20:13.166070Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.00982","last_updated":"2022-12-28T04:57:24Z","snapshot_observed_at":"2026-08-10T00:17:51.124629Z","submitted_at":"2020-03-02T15:58:46Z","title":"Benchmarking Graph Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.00982","snapshot_observed_at":"2026-08-12T16:20:13.173005Z","title":"Joshi, Thomas Laurent, Yoshua Bengio, and Xavier Bresson","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.173005Z"},"links":{"cited_paper":"/paper/2003.00982","citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:31ccd1c54e9824f98f764b76fc204cd118875a6d704832267a77069a28986e14","observation_id":"2d67026a-a4d4-4207-b541-0eadc8a414f4","resolution":{"observed_at":"2026-08-12T16:20:13.173005Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.08152","last_updated":"2020-04-17T10:19:55Z","snapshot_observed_at":"2026-08-05T00:18:29.747675Z","submitted_at":"2020-04-17T10:19:55Z","title":"Continuous Representation of Molecules Using Graph Variational Autoencoder","version":1},"cited_work":{"arxiv_id":"2004.08152","doi":null,"metadata_source":"pith","pith_arxiv_id":"2004.08152","snapshot_observed_at":"2026-08-12T16:20:14.180102Z","title":"Continuous Representation of Molecules Using Graph Variational Autoencoder","venue":"cs.LG","work_id":"213159a9-a6df-481a-91e5-6c1d2850c564","year":2020},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.178920Z"},"links":{"cited_paper":"/paper/2004.08152","citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:85350089be0942b68364e0ceb70051d33beba7f74671e251b6a4d19756638ced","observation_id":"60a16557-3f82-4a1f-bfbe-2adba620dd07","resolution":{"observed_at":"2026-08-12T16:20:14.186618Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.185893Z","title":"Open graph benchmark: Datasets for machine learning on graphs","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.185893Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:c540ee227292cf3b2001c7b0328b6583d4d4b9e303e6afd9a3acae2b627b05fe","observation_id":"c3f0f746-5266-41ff-b3a7-3461ba0d7fcd","resolution":{"observed_at":"2026-08-12T16:20:13.185893Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.197374Z","title":"Multilayer feedforward networks are universal approximators","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.197374Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:0882ae4315d41ff82d446c5742f1631c4c278c6bb3e1b3e12d03b9006332415f","observation_id":"ad3085a4-33be-4fe5-86ca-f1798f3c5253","resolution":{"observed_at":"2026-08-12T16:20:13.197374Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.204900Z","title":"Understanding graph isomorphism net- work for rs-fMRI functional connectivity analysis","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.204900Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:cd5386e779a07bec89ed666483a91f1253f439a58f07de962540fa1446991eaf","observation_id":"a7711fcd-278d-41c8-a5f4-8953c377decb","resolution":{"observed_at":"2026-08-12T16:20:13.204900Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.210771Z","title":"The reduction of a graph to canonical form and the algebra which appears therein","venue":null,"work_id":null,"year":1968},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.210771Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:bbc032eb423cf9df1dfd29bb77659ed8e12e764ee7631f43024e3736fd40a3b4","observation_id":"3978c762-d474-4c9a-b1b7-bfc70157a7a8","resolution":{"observed_at":"2026-08-12T16:20:13.210771Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.217508Z","title":"Zafeiriou, and Michael Bron- stein","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.217508Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:aeba9422b70eba136dffcf7433a2240b654bb5769c4b3be195d49344b6eccb06","observation_id":"6150922b-f589-411a-8cb4-d44fc7e6ef94","resolution":{"observed_at":"2026-08-12T16:20:13.217508Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.225036Z","title":"Hamilton, Jan Eric Lenssen, Gaurav Rattan, and Martin Grohe","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.225036Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:91ff5c90aa46dba64b9b29417d73d1e9e76e8095f37679df6121cdebe6e29c3e","observation_id":"e441683f-ae14-4acf-846c-ca4996886902","resolution":{"observed_at":"2026-08-12T16:20:13.225036Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.07743","last_updated":"2022-06-15T18:13:52Z","snapshot_observed_at":"2026-07-31T16:57:32.126222Z","submitted_at":"2022-06-15T18:13:52Z","title":"Feature Overcorrelation in Deep Graph Neural Networks: A New Perspective","version":1},"cited_work":{"arxiv_id":"2206.07743","doi":null,"metadata_source":"pith","pith_arxiv_id":"2206.07743","snapshot_observed_at":"2026-08-12T16:20:14.141730Z","title":"Feature Overcorrelation in Deep Graph Neural Networks: A New Perspective","venue":"cs.LG","work_id":"1c98d536-cc16-455b-8285-9f0f47c1b43e","year":2022},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.234957Z"},"links":{"cited_paper":"/paper/2206.07743","citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:e146d28c750b51e85f606fe91ab530bc01fab02562bd9e64d8ceb882ea4cc5c5","observation_id":"1956dd6e-dbfd-46de-a61b-5a0a667e2af5","resolution":{"observed_at":"2026-08-12T16:20:14.153379Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2108.00955","last_updated":"2021-08-02T14:55:10Z","snapshot_observed_at":"2026-08-10T03:16:32.308470Z","submitted_at":"2021-08-02T14:55:10Z","title":"Evaluating Deep Graph Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.00955","snapshot_observed_at":"2026-08-12T16:20:13.240639Z","title":"Evaluating deep graph neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.240639Z"},"links":{"cited_paper":"/paper/2108.00955","citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:c0a05ecd34605ad27b4ab63f533ea6901594d2a48bb0b036adca1d7c819571c4","observation_id":"16f4ef82-fd1c-43a1-9126-de98c2628b1c","resolution":{"observed_at":"2026-08-12T16:20:13.240639Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.246278Z","title":"Gaunt, Alvaro Sanchez-Gonzalez, Yulia Rubanova, Petar Veliˇ ckovi´ c, James Kirkpatrick, and 172 Peter Battaglia","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.246278Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:4e3130b4b05af96fe85a420486cbce71697de360d265f0bbd3a64770625126f4","observation_id":"e3058ef9-8b5b-4bec-9568-8d7f6bbd315f","resolution":{"observed_at":"2026-08-12T16:20:13.246278Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.252181Z","title":"Measuring and relieving the over-smoothing problem for graph neural networks from the topo- logical view","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.252181Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:748dda2be06f9f3edc6feb89014103a30dfd08e3093119aca9f000baf4110012","observation_id":"ce7becf8-a3ed-4610-9b13-af1309aefe4b","resolution":{"observed_at":"2026-08-12T16:20:13.252181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.02428","last_updated":"2019-04-25T10:06:09Z","snapshot_observed_at":"2026-08-02T18:54:43.326912Z","submitted_at":"2019-03-06T14:50:02Z","title":"Fast Graph Representation Learning with PyTorch Geometric","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.02428","snapshot_observed_at":"2026-08-12T16:20:13.259034Z","title":"Fast graph representation learning with PyTorch Geometric","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.259034Z"},"links":{"cited_paper":"/paper/1903.02428","citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:68c0bf58fb4d7811a9edd32d02e0dd1aed9c10f068d7cbcc7fa644037c9cb034","observation_id":"06470f0c-b386-4249-b8bf-006beda13aeb","resolution":{"observed_at":"2026-08-12T16:20:13.259034Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.266048Z","title":"Data set modelability by QSAR","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.266048Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:d7aa03e8af1fcc67ba2afdca408263434e905fd75ed9060fb5e7b960d39d25d7","observation_id":"5aa6ed90-40e1-4ad3-b7eb-a617794b7818","resolution":{"observed_at":"2026-08-12T16:20:13.266048Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.271275Z","title":"Leadley et al","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.271275Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:1b0d663483d3793f27b1b8e602915072d0d8d60d216d05cc2b2dc8204fdab2d7","observation_id":"b8a5d138-b489-4b88-8acf-4441b94f187e","resolution":{"observed_at":"2026-08-12T16:20:13.271275Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.278135Z","title":"From activity cliffs to activity ridges: Informative data structures for SAR analysis","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.278135Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:a63c31017e33c8f63069239af3b3d89b9f90db02ccb5cd6a3857263866f976a8","observation_id":"5b7f3a52-2d09-4f6a-8a3c-24ed6c6d3dea","resolution":{"observed_at":"2026-08-12T16:20:13.278135Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:20:13.284487Z","title":"Activity cliff clusters as a source of structure–activity relationship information","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-12T16:20:13.284487Z"},"links":{"citing_paper":"/paper/2411.13688"},"observation_digest":"sha256:95528429ead7d783048893c49ef4080471da9659822531ef6060b9a73feec3ff","observation_id":"89cc1156-d8be-47a8-af57-14cb8819d550","resolution":{"observed_at":"2026-08-12T16:20:13.284487Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2411.13688","last_updated":"2024-11-20T20:07:48Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-12T15:57:44.334020Z","submitted_at":"2024-11-20T20:07:48Z","title":"Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":6,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":87,"verified_exact":7,"verified_fuzzy":0},"total_outbound_references":174},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 100 of 174 outbound references and 0 inbound Pith citation observations for arXiv:2411.13688."}