{"as_of":"2026-08-19T10:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:bb989b5bec080d2817e6cf3f236db40aa33b8e439261e2a6c30dc10b67f13a65","coverage":[{"denominator":48,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":48,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-26T08:55:55.570158Z","state":"measured"},{"denominator":48,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":48,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+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/2606.23361/citation-record","integrity":"/paper/2606.23361/integrity","json":"/paper/2606.23361/citation-record.json","paper":"/paper/2606.23361"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T08:55:55.570158Z","title":"Deeper insights into graph convolutional networks for semi-supervised learning","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:b4e82d296ed3483bfebef193eb732ff69a4aac3a331b9e5d3b439b934ec43be1","observation_id":"3654eae7-2e91-4c5e-abd1-034cfb03c0b0","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Graph neural networks: A review of methods and applications","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:08d7851da4960d037c2b3866de2073cc07752c50947ebf68c4a8040f3c3b8c9c","observation_id":"8bfca69c-57d5-4b8d-9cf8-be44609e691f","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Moleculenet: a benchmark for molecular machine learning.Chemical science, 9(2):513–530, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:62737cfbb82a2e65dfd4252a398b277a0b1c80c177395b839b455e0556275cd9","observation_id":"67c7b339-e515-4f3f-a887-b3acca45f4b3","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Neural message passing for quantum chemistry","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:b383fe17bf68a266d9111a0ff3e309e626dba5759ce49eebc003eb1d336db32f","observation_id":"ac934a25-331a-4732-a469-cf204db515b2","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Motif-backdoor: Rethinking the backdoor attack on graph neural networks via motifs.IEEE Transactions on Computational Social Systems, 11(2):2479–2493, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:7547bf93fe4f323d26caf9e18b97ee5cddaadad6213aabaa3c76f1d8710ee586","observation_id":"5502c3f3-ba26-491d-89e4-b62d9079404b","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Unnoticeable backdoor attacks on graph neural networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:00a2996760f2455a242ce84911b71b6d23bf0f8a84d091a1e5bf853ccbb75484","observation_id":"6ed00738-1d18-4d1d-b66a-6ca35ccce1de","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Rethinking graph backdoor attacks: A distribution-preserving perspective","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:0f96973e01beced1439bf5f6d4fd6d921098be625a8d6f37799d2d32e4511c92","observation_id":"81da2b8a-0466-4b10-ae0f-3a69c0be0c14","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Lr-gnn: A graph neural network based on link representation for predicting molecular associations.Briefings in Bioinformatics, 23(1): bbab513, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:5f4e6c2235c6ecaf97a772575edc37de1fd268ca154b7d6e588bd00ac896cfe8","observation_id":"396622e0-2307-494a-9252-26f3cd91fd1f","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Pre-training graph neural networks for link prediction in biomedical networks.Bioinformatics, 38(8): 2254–2262, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:09e2bc56c5a3eec1bc6baa4d6b6c888162a8862eca7d27fc4a4e7730b5bf7213","observation_id":"1fda070b-e9fa-4a9d-903b-90d8bfb73c1f","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"A compact review of molecular property prediction with graph neural networks.Drug Discovery Today: Technologies, 37:1–12, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:7293a5e7f269bee6acdf6844b3a9e37568e11800ba13b8409d8fda234ff99511","observation_id":"8c1e8083-7df5-427f-bdf1-4e5b58ebe3a6","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Enhancing drug discovery with ai: Predictive modeling of pharmacokinetics using graph neural networks and ensemble learning.Intelligent Pharmacy, 3(2):127–140, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:9b5116c5bc06abe0366bdcd3197220e2c40a9c3cb9f8417ad7d13f8ac91a72a9","observation_id":"91a963e8-92c6-494d-9c76-44e2480d3301","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Rdkit documentation.Release, 1(1-79):4, 2013","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:24ee7ddcd399b7602ad5dd32c66584259f0f8277f15ea087f2e2bcee967c1b3f","observation_id":"5c707b44-cfcf-43ce-86be-869a3088d330","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Open babel: An open chemical toolbox.Journal of cheminformatics, 3(1):33, 2011","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:1f44a24526d518f5424470fc528e01819b1cd8350426c7409924fd40e142d76e","observation_id":"a1a3a956-d897-4651-996d-44348ac195ab","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Indigo: universal cheminformatics api.Journal of cheminformatics, 3(Suppl 1):P4, 2011","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:af552bea3057c011e4ea8005b5d565d7cde24aeae01ff2fa1eca4a5d687cb516","observation_id":"74f7604e-5ca2-4d1e-8013-eb395a8736d0","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Extended-connectivity fingerprints.Journal of chemical information and modeling, 50(5):742–754, 2010","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:21a6c1b4cdfed2f88148dc6480f42de345b8fd173b22f4569a0b648edbd57ff9","observation_id":"f170952d-ee9c-4b0a-9f3e-e3088ed8cb1e","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Why is tanimoto index an appropriate choice for fingerprint-based similarity calculations?Journal of cheminformatics, 7(1):20, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:3995d6abe29e3da8eb58836440ef560c1380ec8e1c011be6cea1f7c9578d4341","observation_id":"6a05aa07-ac6e-442c-8597-42a68f7dd06a","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2008.20056","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-04T10:19:47.747362Z","title":"The graph neural network model.IEEE Transactions on Neural Networks, 20(1):61–80, 2009","venue":null,"work_id":"6b5f52a9-8793-41b9-b9eb-bc37379953a2","year":2009},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:1dc47030e5f8476cf7309b85f29024a6e93c70840a248d3af43ddfe76bedf208","observation_id":"d53aaab6-b4fb-4af4-b899-ecd3c97e9667","resolution":{"observed_at":"2026-07-04T10:19:47.748797Z","resolver_source":"arxiv_id","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-26T08:55:55.570158Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:07b873bb85ed2a4fc1f7e502d4ea2e1a705a137dc1111a58d675aab34eee4cb6","observation_id":"f1f7a792-3671-40e6-8077-05328d595912","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Kipf and Max Welling","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:eba264d72d21f0e40b1ee8fb75c6379642c6c2ad42bb5bab0c112696f0fff054","observation_id":"ae5da300-6b27-4e0d-83b8-15ce2884f40a","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Hamilton, Rex Ying, and Jure Leskovec","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:d9c6104a22550ab1b19d024e9334cdedfcaec8948129752406f1bd0957ca5bca","observation_id":"c26fc13d-79e1-40ba-911d-4782cf175176","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Self- supervised graph transformer on large-scale molecular data.Advances in neural information processing systems, 33:12559–12571, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:4ab3c37f747e6e1e0ff373114d0e607e98f149ad43c9c143acb79f4d10c1acb5","observation_id":"8df3c8e2-86f0-4f08-b71b-10b8a895764c","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.06733","last_updated":"2019-03-11T20:45:33Z","snapshot_observed_at":"2026-08-12T15:43:59.037380Z","submitted_at":"2017-08-22T17:31:54Z","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","version":2},"cited_work":{"arxiv_id":"1708.06733","doi":null,"metadata_source":"pith","pith_arxiv_id":"1708.06733","snapshot_observed_at":"2026-07-11T00:47:43.661742Z","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","venue":"cs.CR","work_id":"7b1cd3ac-9abd-4579-8d13-c75d30c83a5f","year":2017},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"cited_paper":"/paper/1708.06733","citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:b7e31ec485b91551272571e62bba3fab31d0832500f12ebd8b91bfa2e2fcb577","observation_id":"33ce39ba-f08d-4182-929a-7bd1e925bfed","resolution":{"observed_at":"2026-07-04T10:19:47.746211Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-26T08:55:55.570158Z","title":"Input-aware dynamic backdoor attack.Advances in Neural Information Processing Systems, 33:3454–3464, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:081f62db7eaaf1b775ceda3478c17b5570bb5c9a3cccafe9d5e53e2a77ca0c13","observation_id":"b0ca472b-3601-4e3c-8f4a-cd5ed50d0d2a","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Lira: Learnable, imperceptible and robust backdoor attacks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:0bce0cda088edd11a7d777412a4fcd00446d5892f3095aa6e9e19b68e9b54b3d","observation_id":"a5ad8aac-2cf1-4eff-9fae-eed5c4e9533d","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Backdoor attacks and defenses in federated learning: Survey, challenges and future research directions","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:eeb2016fa5bbbce292324c3198cc008f98d56111026bbe46efdd43c8e1b230bb","observation_id":"33508a53-eaf1-48e5-bfd7-a4c5fd683844","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Graph backdoor","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:34e68c48c379e0f71a0c483dddcfb3634cbaced0406d7fbc4356489762ba730d","observation_id":"6ecbeedf-c1ea-47e8-992f-1ce62b0acf6c","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2019.00031","doi":"10.1109/aike.2019.00031","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Chechik and T","venue":null,"work_id":"4014da35-e946-4662-b1ec-ae89c62a730b","year":2019},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:958775e630c7a75ce726d72228fafa432ff7d8063e252653bb7ffb1ad0f2dbab","observation_id":"329105c0-a9dd-4263-82f0-c31d962ee9a9","resolution":{"observed_at":"2026-06-26T08:59:15.106843Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-26T08:55:55.570158Z","title":"Spectral signatures in backdoor attacks.Advances in neural information processing systems, 31, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:6070a6d76d7263c76db2cd42620e2fcfa65c821650708b389865a392a9ac3a24","observation_id":"f0ce09bb-7886-4c1c-8270-927b8c34695e","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Dshield: Defending against backdoor attacks on graph neural networks via discrepancy learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:345f8ed26f614298653912161739833d4cf3b78435e17c71b277a17bab44dae5","observation_id":"a393fc7b-f74f-40a8-872f-82c1c2483556","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.09836","last_updated":"2025-03-12T02:55:02Z","snapshot_observed_at":"2026-08-16T13:43:02.882767Z","submitted_at":"2024-06-14T08:46:26Z","title":"Robustness Inspired Graph Backdoor Defense","version":2},"cited_work":{"arxiv_id":"2406.09836","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.09836","snapshot_observed_at":"2026-07-04T10:19:47.742498Z","title":"Robustness- inspired defense against backdoor attacks on graph neural networks","venue":null,"work_id":"01c74371-2d73-4883-90f4-3faa308eb7fa","year":2024},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"cited_paper":"/paper/2406.09836","citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:6c77b225275954d2709edac428d06c5de5748f1c1bc5937c8a7b35c873c06fcf","observation_id":"5e854dda-fdc2-4224-a785-1916b84be309","resolution":{"observed_at":"2026-07-04T10:19:47.743910Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-26T08:55:55.570158Z","title":"Robust graph convolutional networks against adversarial attacks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:0dd8c6e433beabaa2419559ad152f13b76476d0ec2159e35460aa71c9f638bad","observation_id":"bfc62d6f-2171-42d0-b7e8-882c5822101b","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Gnnguard: Defending graph neural networks against adversarial attacks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:d5c0fe811f731f395fb5a5b063ca246dfb338c548abbb6c52a1fa8ac362935e5","observation_id":"15a46417-8ce8-4455-988c-522139356b69","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Graph structure learning for robust graph neural networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:cfb21121f612490273d1fe2322b33845008fb64988ceb3b906ccd90e99632dd0","observation_id":"ba2541d0-798c-4413-aa08-d67276fac095","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Certified robustness of graph neural networks against adversarial structural perturbation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:23b86668310e5ed1d488ae91063d34a507932188e20f93f9391c7ee36ba79f1c","observation_id":"924f5fc1-4292-4fa9-a129-bfaf804ce7b3","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Distributed backdoor attacks on federated graph learning and certified defenses","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:6ea844905d005937f274b6984e8d51d753f00956507027094f4b56a385a80531","observation_id":"eeb575b8-5a09-462d-ad59-235c2927e6b7","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Deterministic certification of graph neural networks against graph poisoning attacks with arbitrary perturbations","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:59f8725e520182602aecbf547860c3d1581f735ebc390d0162c228232a0c5359","observation_id":"55bb6902-5912-48bc-8a82-192120fff2cf","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"A bayesian approach to in silico blood-brain barrier penetration modeling.Journal of chemical information and modeling, 52(6): 1686–1697, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:e428dc6971eaa3058f778f1b13e0b5a348a50fb17625d6a9a6290d987afa1b0c","observation_id":"00fc5973-e4c7-4573-977c-45cf0bc15139","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Computational modeling of β-secretase 1 (bace-1) inhibitors using ligand based approaches.Journal of chemical information and modeling, 56(10):1936–1949, 2016","venue":null,"work_id":null,"year":1936},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:10e192677bdbf58c2d56b407e77e8bc9ebb94fa0260221b4b17dae5c1d15b374","observation_id":"520ded86-5b0d-4e28-84ba-a95c6a01e39f","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"The sider database of drugs and side effects","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:6edd028c25b85282a8f7d1997cc3a3baea676297d3c450f2e38149e065dbb7bc","observation_id":"374fea2f-4e3c-4869-9f36-eff901ed9901","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:d76014aa971e5c926883372cd24dd24144d1452128cda801919ddbcfc8bff894","observation_id":"cd82f04e-63fd-46e4-8edd-131f9dc7b642","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Pubchem’s bioassay database.Nucleic acids research, 40(D1):D400–D412, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:5b34d0f16f0fc2fd9f3dfc93a5cc3b1f817c50c4a7db75a8a05094c9e3871d75","observation_id":"be1f7132-4e24-4bfd-a7c7-e7c033081448","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Maximum unbiased validation (muv) data sets for virtual screening based on pubchem bioactivity data.Journal of chemical information and modeling, 49(2):169–184, 2009","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:40526ac6d64bc35739642de502d01be247825796f3eef2abf3f6848e02448fcf","observation_id":"c6619b86-523c-4e36-823c-88405d964802","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settings.Advanced drug delivery reviews, 23(1-3):3–25, 1997","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:67230bd55144f9c524048be2ff8daaf0ba2261a1ffdf32eb71b70917b7034a33","observation_id":"f371a68c-9af9-4337-b2e7-50ed1111686c","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Molecular properties that influence the oral bioavailability of drug candidates.Journal of medicinal chemistry, 45(12):2615–2623, 2002","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:bace3833fce3e4041dde5ab5fd9332b0a08cb04977d36ebf9abf1bf1b287c539","observation_id":"d651ee81-51fd-42ae-8e77-bc1d56e6c307","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Quantifying the chemical beauty of drugs.Nature chemistry, 4(2):90–98, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:d817976431fc84fcb6641b50df9b545bd648e175a28acc9c08c600cb5afafc5e","observation_id":"693fdc99-26f4-4216-b0e1-9b7457479983","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":null,"venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:ec208a004c6340a63fc553b363dc54d0b2c847739fe45861bbdebb4131bde765","observation_id":"98664bde-e302-40ea-84bc-3bb7798828f1","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":null,"venue":null,"work_id":null,"year":1987},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:b48e037646708f59690e700b31364f96e63938f3070983514d1588a903d73306","observation_id":"46caf574-84b2-4cdc-90c4-f6dcef39e854","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","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":"2026-06-26T08:55:55.570158Z","title":"Equivalence tests: A practical primer for t tests, correlations, and meta-analyses","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:55.570158Z"},"links":{"citing_paper":"/paper/2606.23361"},"observation_digest":"sha256:f0727b1c45928eb1078b18801fb6db00577ceaa1a97a023082c3c0624288a564","observation_id":"e3954824-9699-4135-94c5-949d78ec293d","resolution":{"observed_at":"2026-06-26T08:55:55.570158Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2606.23361","last_updated":"2026-06-22T13:59:59Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T18:45:50.960456Z","submitted_at":"2026-06-22T13:59:59Z","title":"Rethinking Molecular Graph Backdoors under Chemistry-aware Admission"},"reference_resolution":{"displayed":48,"state_counts":{"malformed_identifier":2,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":43,"verified_exact":2,"verified_fuzzy":0},"total_outbound_references":48},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 0 inbound Pith citation observations for arXiv:2606.23361."}