{"as_of":"2026-08-09T17:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c2c0f3afc5c9944c56644c20576e967ffca0678884035d3a616d050a70ef9d08","coverage":[{"denominator":68,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":68,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T18:39:14.068280Z","state":"measured"},{"denominator":68,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":68,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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/2607.18332/citation-record","integrity":"/paper/2607.18332/integrity","json":"/paper/2607.18332/citation-record.json","paper":"/paper/2607.18332"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T18:39:07.898580Z","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":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:07.898580Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:d83839ba43f7b474829566539cc8b170da554f098a05687aac0c517f052d38c0","observation_id":"52ae8b5c-06b8-4943-a0fd-fb9e9c20e17e","resolution":{"observed_at":"2026-08-01T18:39:07.898580Z","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":"2026-08-01T18:39:07.999315Z","title":"Artificial intelligence foundation for therapeutic science.Nature chemical biology, 18(10):1033–1036, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:07.999315Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:bc0b256a66eec6be60e6e80254af5b49aefd41a8477076211660fef256ed41e7","observation_id":"a763fe1c-514d-4500-b56e-9e9c2f6ae2c6","resolution":{"observed_at":"2026-08-01T18:39:07.999315Z","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":"2026-08-01T18:39:08.060743Z","title":"Smiles, a chemical language and information system","venue":null,"work_id":null,"year":1988},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:08.060743Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:b9a54226dd3109214bd3332497d93ae03202f4ba8549b089043066d7aaa56cef","observation_id":"82138948-6880-44af-9621-3ac5091d5496","resolution":{"observed_at":"2026-08-01T18:39:08.060743Z","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":"2026-08-01T18:39:08.160917Z","title":"An open source chemical structure curation pipeline using rdkit.Journal of Cheminformatics, 12(1):51, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:08.160917Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:0e383bf06dad90cafda966fd4a6c5109af28b6ce04b328964c8014ec08c88a20","observation_id":"98af3310-cf8f-4ee9-b51d-3a79976b606a","resolution":{"observed_at":"2026-08-01T18:39:08.160917Z","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":"2026-08-01T18:39:08.260261Z","title":"Analyzing learned molecular representations for property prediction","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:08.260261Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:4572efb995430f4c0b6ee707da665d0d64d6fe69fef44cbc55371c2dc84b448d","observation_id":"1017fdf4-b6c9-408c-a40a-c921a8db59b0","resolution":{"observed_at":"2026-08-01T18:39:08.260261Z","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":"2026-08-01T18:39:08.359101Z","title":"Cornell university press, 1960","venue":null,"work_id":null,"year":1960},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:08.359101Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:bcb4d0a78a558fd4ea91eea7f95ea7b401854cb53d831e144f9d902d80521fc0","observation_id":"debd0629-9fa2-477b-a862-72415dd08b82","resolution":{"observed_at":"2026-08-01T18:39:08.359101Z","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":"2026-08-01T18:39:08.458329Z","title":"Iterative partial equalization of orbital electronegativity—a rapid access to atomic charges.Tetrahedron, 36(22):3219–3228, 1980","venue":null,"work_id":null,"year":1980},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:08.458329Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:1b73ba441997882771a5615f3a4b9b1d203d5e2a8ad919273a1df31b31d49b84","observation_id":"bb88b84f-ec8d-4fa3-93c1-7f11f77b3fb5","resolution":{"observed_at":"2026-08-01T18:39:08.458329Z","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":"2026-08-01T18:39:08.553050Z","title":"Uni-mol: A universal 3d molecular representation learning framework","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:08.553050Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:023c5d1cc7a11e9ffc438c7bf9f635a88dfead9e94da25fddc70b304fbaafeee","observation_id":"62d0ce4f-9177-4657-a1b5-dc319e2aab40","resolution":{"observed_at":"2026-08-01T18:39:08.553050Z","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":"2026-08-01T18:39:08.624889Z","title":"Data-driven quantum chemical property prediction leveraging 3d conformations with uni-mol+.Nature communications, 15(1):7104, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:08.624889Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:790f92add52a66b73f5fb5911311b03fb3f415aab6f7bc968ab191372f7a402a","observation_id":"5c3b3554-cfda-4611-9bd5-69d0038e4aba","resolution":{"observed_at":"2026-08-01T18:39:08.624889Z","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":"2026-08-01T18:39:08.725005Z","title":"Exploring molecular pretraining model at scale.Advances in Neural Information Processing Systems, 37:46956–46978, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:08.725005Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:b1c18487398d33b98764a6b5844ffde72dfca82eff124746f575d22ba1d2a9dc","observation_id":"be0919ea-9a44-4b29-9664-3b44662b462b","resolution":{"observed_at":"2026-08-01T18:39:08.725005Z","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":"2026-08-01T18:39:08.820133Z","title":"Magnetic eigenmaps for community detection in directed networks.Physical Review E, 95(2):022302, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:08.820133Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:e4a6da39e0e33e9f257e1d197ca796b64ab88c1feed22426a48acf25bbcf386c","observation_id":"396956d8-cdef-4434-b3d2-9d2945834893","resolution":{"observed_at":"2026-08-01T18:39:08.820133Z","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":"2026-08-01T18:39:08.895210Z","title":"Magnet: A neural network for directed graphs.Advances in neural information processing systems, 34:27003–27015, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:08.895210Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:3f2c944970a7611f6b8023bcea1c1b6a0aded6488831dc15a399541c264fa676","observation_id":"f363ec53-aca7-414d-8fda-138ddb3b8a27","resolution":{"observed_at":"2026-08-01T18:39:08.895210Z","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":"2026-08-01T18:39:08.963292Z","title":"Young, and Sinan Guven Aksoy","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:08.963292Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:25806192286682402faa6669183985aedc40b940aecf500243da2c9ee76b3f56","observation_id":"6fb00660-fc8e-4a80-8530-12ec927cb0e9","resolution":{"observed_at":"2026-08-01T18:39:08.963292Z","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":"2026-08-01T18:39:09.030219Z","title":"Directed graph contrastive learning.Advances in neural information processing systems, 34:19580–19593, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:09.030219Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:1aebd37163384c580da71483d978f81fd9aa00f131253c0d952da81961bf4d59","observation_id":"dd3dcf3c-3da2-4743-a26f-6361954efb78","resolution":{"observed_at":"2026-08-01T18:39:09.030219Z","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":"2026-08-01T18:39:09.159536Z","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":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:09.159536Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:a890f6db765eb1cb29689f3172d922ce5c94729db69584979afbe9a03e7b43cf","observation_id":"2edd87cd-5f4b-4ab7-937f-e0ffb90c1b4a","resolution":{"observed_at":"2026-08-01T18:39:09.159536Z","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":"2026-08-01T18:39:09.259353Z","title":"pkcsm: predicting small-molecule pharmacokinetic and toxicity properties using graph-based signatures.Journal of medicinal chemistry, 58(9):4066–4072, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:09.259353Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:1566f5c2e6e9180e1d3294d48db498a0c5dd41cd6fa9d5ac44b8d6354f7b19cf","observation_id":"d35dfe5f-2f2a-49ba-a7a3-5f07a23fbe5b","resolution":{"observed_at":"2026-08-01T18:39:09.259353Z","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":"2026-08-01T18:39:09.349440Z","title":"Swissadme: a free web tool to evaluate pharmacokinetics, drug-likeness and medicinal chemistry friendliness of small molecules.Scientific reports, 7(1):42717, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:09.349440Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:26ecec540a56146f29262ac2b57abbf0c5529ebbe6093878360096f6b6bb4fe1","observation_id":"6a4b7dd1-42a8-49b9-b1c1-0a5c83ebe820","resolution":{"observed_at":"2026-08-01T18:39:09.349440Z","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":"2026-08-01T18:39:09.449207Z","title":"vnn web server for admet predictions","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:09.449207Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:311f4199e2e3ebff2bc7bce2ed165114d3058a9292097e650a00c0aad8aa7eeb","observation_id":"6d23274f-8b0b-4e87-8063-617658312682","resolution":{"observed_at":"2026-08-01T18:39:09.449207Z","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":"2026-08-01T18:39:09.555276Z","title":"Admetboost: a web server for accurate admet prediction.Journal of molecular modeling, 28(12):408, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:09.555276Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:f9444094f6aeb8668eb27087219d0df626d91af7d468b904b3f39607177c7b6d","observation_id":"2e53fb40-8b98-443b-a59a-d39547104f51","resolution":{"observed_at":"2026-08-01T18:39:09.555276Z","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":"2026-08-01T18:39:09.620677Z","title":"Admetlab 2.0: an integrated online platform for accurate and comprehensive predictions of admet properties.Nucleic acids research, 49(W1):W5–W14, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:09.620677Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:fa4d095d2388e1f71b06e4ee9a3013825c9266ebb16347a3f1b86bdbc02f4928","observation_id":"4ba16e05-9a3a-4c88-b56f-95fb62200de0","resolution":{"observed_at":"2026-08-01T18:39:09.620677Z","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":"2026-08-01T18:39:09.709112Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:09.709112Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:450e4a98c843f694e716891ae270ff64e1cd47920af10b39005789a52753d195","observation_id":"7514f78d-c3e3-4fbb-8ae7-8779538a066d","resolution":{"observed_at":"2026-08-01T18:39:09.709112Z","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":"2026-08-01T18:39:09.803678Z","title":"Admet-ai: a machine learning admet platform for evaluation of large-scale chemical libraries","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:09.803678Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:f52d48c2c1ec82cb2cfdb05c865bbffb0554f19cbfe37bc3ed97e03b88f46c1f","observation_id":"6a002e3f-04c6-4324-9a95-54851651d989","resolution":{"observed_at":"2026-08-01T18:39:09.803678Z","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":"2026-08-01T18:39:09.912124Z","title":"Potentialnet for molecular property prediction.ACS central science, 4(11):1520–1530, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:09.912124Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:a1bba47c1f476341ce5f7636d6f26da728e9e0544f7cd8f74aa2d0b4703aa5e1","observation_id":"332eaedb-9d75-4fa0-bb66-5aac6d540056","resolution":{"observed_at":"2026-08-01T18:39:09.912124Z","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":"2026-08-01T18:39:10.000437Z","title":"Chemprop: a machine learning package for chemical property prediction.Journal of Chemical Information and Modeling, 64(1):9–17, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:10.000437Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:e315ac99ead4a0a2c3500559585bef6d6742fbaaf29b41368f16489790d33f6f","observation_id":"6c804ed3-81c2-4e70-bf4f-a067a2166841","resolution":{"observed_at":"2026-08-01T18:39:10.000437Z","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":"2026-08-01T18:39:10.104180Z","title":"Chemprop v2: An efficient, modular machine learning package for chemical property prediction.Journal of Chemical Information and Modeling, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:10.104180Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:4359031cf83565792e2da66efdb24643169ceeca70cda74b2389166352161d02","observation_id":"d5bd591b-32ab-4a34-a69b-e521389fcf33","resolution":{"observed_at":"2026-08-01T18:39:10.104180Z","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":"2026-08-01T18:39:10.200431Z","title":"Do transformers really perform badly for graph representation?Advances in neural information processing systems, 34:28877–28888, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:10.200431Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:0b3aa1d3eb1b89d85dada46888fd243457907ac5d67f1cbbbdb923f6f1dc2698","observation_id":"ffc8f03f-dc35-459a-ae59-d42c871e7396","resolution":{"observed_at":"2026-08-01T18:39:10.200431Z","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":"2026-08-01T18:39:10.262362Z","title":"Admet property prediction via multi-task graph learning under adaptive auxiliary task selection.Iscience, 26(11), 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:10.262362Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:05befa5ff5b5468902ad5218ac726849bd6c6312e91f554be78c76f52607bec9","observation_id":"be1da040-dd51-4441-a2a1-7a11e4235065","resolution":{"observed_at":"2026-08-01T18:39:10.262362Z","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":"2026-08-01T18:39:10.389345Z","title":"Deepdelta: predicting admet improvements of molecular derivatives with deep learning.Journal of cheminformatics, 15(1):101, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:10.389345Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:4a5ac77a7cfe31edd93754a40d2e667d76b2ea2d6cd98130beadee3b9abeeed8","observation_id":"8677d7fa-8f58-4be2-9f83-15e7300530c3","resolution":{"observed_at":"2026-08-01T18:39:10.389345Z","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":"2026-08-01T18:39:10.482815Z","title":"Unified and explainable molecular representation learning for imperfectly annotated data from the hypergraph view.Nature Communications, 16(1):1–18, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:10.482815Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:0f3405a1ac00fe65dd18203ca605491a17c142cd23b28da12fc887d66b1a900a","observation_id":"529cd476-dc42-4221-8433-a23c7535e688","resolution":{"observed_at":"2026-08-01T18:39:10.482815Z","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":"2026-08-01T18:39:10.555950Z","title":"Quantum-informed molecular representation learning enhancing admet property prediction.Journal of Chemical Information and Modeling, 64(13):5028–5040, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:10.555950Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:4271a71f590a44362ccb0e755e53a37bc223d7e77d5cbff8674569889b0962a9","observation_id":"6c00d244-629b-48c8-b3fc-74b74edc4f43","resolution":{"observed_at":"2026-08-01T18:39:10.555950Z","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":"2026-08-01T18:39:10.641222Z","title":"Pretraining graph transformers with atom-in-a-molecule quantum properties for improved admet modeling.Journal of Cheminformatics, 17(1):25, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:10.641222Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:6ae75e07e9fc4e6a7aafdae5765ebd79fa80916ef2e9a235de3a2a5955b75f11","observation_id":"d4b00b04-11aa-44db-8806-546269740ad2","resolution":{"observed_at":"2026-08-01T18:39:10.641222Z","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":"2026-08-01T18:39:10.733978Z","title":"Hypergraph neural networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:10.733978Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:7018793de64fa4d67794a687d26ecf912452f9e8e5374feafcdd9d85f7c26754","observation_id":"3cf2d256-be5d-497c-a901-eaf5f1aff367","resolution":{"observed_at":"2026-08-01T18:39:10.733978Z","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":"2026-08-01T18:39:10.832535Z","title":"Recent advances in hypergraph neural networks: M.-r","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:10.832535Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:db84ad4fac6d70b49a6eba7587552751313cf92efc01dc0693e5769f251d604e","observation_id":"781dbab7-5c02-43cc-a30a-5f5f97388b9e","resolution":{"observed_at":"2026-08-01T18:39:10.832535Z","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":"2026-08-01T18:39:10.935068Z","title":"You are allset: A multiset function framework for hypergraph neural networks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:10.935068Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:117e9fa6aad4d7836aa095878bb4a247d952a8ab683d702e71cf15c816a05d51","observation_id":"b56d5703-f5ef-41bf-9906-85fb9af5951c","resolution":{"observed_at":"2026-08-01T18:39:10.935068Z","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":"2026-08-01T18:39:11.033750Z","title":"Sheaf hypergraph networks.Advances in Neural Information Processing Systems, 36:12087–12099, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:11.033750Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:8df7c9a534f6d0a872b250a20d55cd3c6af8a31f030c76fec9eba29bd9035b49","observation_id":"10e4b0f7-0695-4b5c-b2c0-731db7f845fb","resolution":{"observed_at":"2026-08-01T18:39:11.033750Z","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":"2026-08-01T18:39:11.138253Z","title":"Directed hypergraph representation learning for link prediction","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:11.138253Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:34d1936e5f484009ae50af1bbd83678b8b200e29029826e66e7392089217eb6e","observation_id":"7b75b205-77bf-4bd6-a3f1-ff4c6b6cf416","resolution":{"observed_at":"2026-08-01T18:39:11.138253Z","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":"2026-08-01T18:39:11.235771Z","title":"Directional sheaf hypergraph networks: Unifying learning on directed and undirected hypergraphs.arXiv preprint arXiv:2510.04727, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:11.235771Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:fcab8dcb0a5708cd271640cb5c0c76cb74d5ab31198e5f79ae368284bccb7dd3","observation_id":"29f73f54-ddec-463e-a04b-0111d79e5279","resolution":{"observed_at":"2026-08-01T18:39:11.235771Z","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":"2026-08-01T18:39:11.329147Z","title":"Molecular hypergraph grammar with its application to molecular optimization","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:11.329147Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:00a1057663fe582ec94bf0f5d4b0d86fa57e2659a1e7385f306065affc3db1c0","observation_id":"6d4490c3-1e79-4495-a8cd-b8d97b36f0fc","resolution":{"observed_at":"2026-08-01T18:39:11.329147Z","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":"2026-08-01T18:39:11.453177Z","title":"Molecular hypergraph neural networks.The Journal of Chemical Physics, 160(14), 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:11.453177Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:fa8076ad1ef5d5735d4d6de3f9bdf288e81dcb3607bd8f0f6e22f5860d0b1809","observation_id":"18052e27-f174-4cfa-b267-b596e034b7e7","resolution":{"observed_at":"2026-08-01T18:39:11.453177Z","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":"2026-08-01T18:39:11.585264Z","title":"A hypergraph convolutional neural network for molecular properties prediction using functional group.arXiv, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:11.585264Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:78da24553b833ca4e6e77a92be7ffb6fbf7daed823ac7089c4ed9827a61d323e","observation_id":"cc69f708-c077-4a4a-a0fd-1987a77287b9","resolution":{"observed_at":"2026-08-01T18:39:11.585264Z","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":"2026-08-01T18:39:11.712759Z","title":"Msgnn: A spectral graph neural network based on a novel magnetic signed laplacian","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:11.712759Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:4d1c420abf1b4ec2530772ec5318eb46d428515adbda60f59be54fae92b3ec7b","observation_id":"254a557d-0cd3-46fb-ab95-ff003551d792","resolution":{"observed_at":"2026-08-01T18:39:11.712759Z","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":"2026-08-01T18:39:11.830107Z","title":"A spectral graph convolution for signed directed graphs via magnetic laplacian.Neural Networks, 164:562–574, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:11.830107Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:bce8ef5b73e1b7acc94e225a67d25ae745fb0fae52f4e906e943aa013f11aea3","observation_id":"005423bf-066e-4d4f-b967-0ecb909bbc96","resolution":{"observed_at":"2026-08-01T18:39:11.830107Z","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":"2026-08-01T18:39:11.960831Z","title":"Exploitation of a latent mechanism in graph contrastive learning: Representation scattering.Advances in Neural Information Processing Systems, 37:115351–115376, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:11.960831Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:f9d6545ac971d2643a1a170bb865c7bb8c8ee4d20392a4c0b4bb7ee2beee55e6","observation_id":"55e27a93-3777-458f-9ed1-977c4e3faef1","resolution":{"observed_at":"2026-08-01T18:39:11.960831Z","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":"2026-08-01T18:39:12.080121Z","title":"Graph contrastive learning with augmentations.Advances in neural information processing systems, 33:5812–5823, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:12.080121Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:f71a7370d295acc5bbf370ad6acfad9159c099aa857d6068cf3c0f0e1c4b2b67","observation_id":"11a3e304-c951-4fcf-b0f0-434676d45c25","resolution":{"observed_at":"2026-08-01T18:39:12.080121Z","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":"2026-08-01T18:39:12.208591Z","title":"Adversarial graph augmentation to improve graph contrastive learning.Advances in Neural Information Processing Systems, 34:15920–15933, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:12.208591Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:68bcc538ed0cbf07586335ee1a085cea4310e9e4fde654d1ed0ad382f39b5aa5","observation_id":"400fa32a-ffa5-4136-9820-566b6ede84ea","resolution":{"observed_at":"2026-08-01T18:39:12.208591Z","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":"2026-08-01T18:39:12.340737Z","title":"Prototypical graph contrastive learning.IEEE transactions on neural networks and learning systems, 35(2):2747–2758, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:12.340737Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:5954fd83c354ca47c4166dae018dbf82df986ad1395bfd553669459c0be16926","observation_id":"7c7968f7-ed20-49cb-b942-0047db207383","resolution":{"observed_at":"2026-08-01T18:39:12.340737Z","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":"2026-08-01T18:39:12.434948Z","title":"An empirical study of graph contrastive learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:12.434948Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:4aa1d9c04bf834360110003bc194e1563c2040f33724daeb12ececc78ef5d6d5","observation_id":"51843cc5-ac61-4939-8800-bf00848aa979","resolution":{"observed_at":"2026-08-01T18:39:12.434948Z","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":"2026-08-01T18:39:12.531862Z","title":"Molecular contrastive learning of representations via graph neural networks.Nature Machine Intelligence, 4(3):279–287, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:12.531862Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:8f3206aa4736a8819e631c9745747604004d4e9732ee1ad3c28235ceb163ffd7","observation_id":"57ed2f7c-ceef-434a-8cf4-b3c6aa08ed45","resolution":{"observed_at":"2026-08-01T18:39:12.531862Z","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":"2026-08-01T18:39:12.636546Z","title":"Pre-training molecular graph representation with 3d geometry","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:12.636546Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:31a17d0997f0d54968a6a60e371c85a812da60678d5ae2c2675b5feb7a91a475","observation_id":"c0eb03b9-255a-42a2-9c70-54f32df8b73e","resolution":{"observed_at":"2026-08-01T18:39:12.636546Z","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":"2026-08-01T18:39:12.711209Z","title":"3d graph contrastive learning for molecular property prediction","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:12.711209Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:d01994bd4b6faa178da4229a343e4980de358e74f480009e700e8cfe9318e4b4","observation_id":"13f996a0-f0f3-4109-af16-5fc7ab95bc34","resolution":{"observed_at":"2026-08-01T18:39:12.711209Z","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":"2026-08-01T18:39:12.806410Z","title":"Attention-wise masked graph contrastive learning for predicting molecular property.Briefings in bioinformatics, 23(5):bbac303, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:12.806410Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:6faad6913642a7e723dda350796772956eb23005a9a5589f9c00f6b67afa4787","observation_id":"4c6c8dd4-f09a-44bb-8c5d-20b93c361f2d","resolution":{"observed_at":"2026-08-01T18:39:12.806410Z","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":"2026-08-01T18:39:12.889086Z","title":"Advancing drug discovery with enhanced chemical understanding via asymmetric contrastive multimodal learning.Journal of chemical information and modeling, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:12.889086Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:4f1fc2feec7ea88b7725fd695c7cfb87054651d908b294c62441bdad8e67f94a","observation_id":"6df7b8ef-67d5-46f0-9e73-67ebc2b287ca","resolution":{"observed_at":"2026-08-01T18:39:12.889086Z","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":"2026-08-01T18:39:12.949731Z","title":"Universal graph contrastive learning with a novel laplacian perturbation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:12.949731Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:060e74acf2d88fc3b7b82acadb808c28b020bd148687385f8f52a9a190dc98ab","observation_id":"8cc4347e-ad8e-4e81-a05d-443bcc22e847","resolution":{"observed_at":"2026-08-01T18:39:12.949731Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.05163","last_updated":"2023-01-12T17:32:19Z","snapshot_observed_at":"2026-08-05T10:04:10.838700Z","submitted_at":"2023-01-12T17:32:19Z","title":"Signed Directed Graph Contrastive Learning with Laplacian Augmentation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.05163","snapshot_observed_at":"2026-08-01T18:39:13.040906Z","title":"Signed directed graph contrastive learning with laplacian augmentation.arXiv preprint arXiv:2301.05163, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:13.040906Z"},"links":{"cited_paper":"/paper/2301.05163","citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:f4d8e227d2486b00a34e98ef040d65704677a44341aa773fc0a78bf4f974fa07","observation_id":"31148463-4e19-492e-b2af-aff8d1030266","resolution":{"observed_at":"2026-08-01T18:39:13.040906Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2510.16311","last_updated":"2026-06-18T15:18:42Z","snapshot_observed_at":"2026-08-09T07:13:02.361179Z","submitted_at":"2025-10-18T02:46:53Z","title":"Toward General Digraph Contrastive Learning: A Dual Spatial Perspective","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2510.16311","snapshot_observed_at":"2026-08-01T18:39:13.091018Z","title":"Toward general digraph contrastive learning: A dual spatial perspective.arXiv preprint arXiv:2510.16311, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:13.091018Z"},"links":{"cited_paper":"/paper/2510.16311","citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:ed5d361fa8cfff132584439cc47d2827e1e6ea1dd5159034793f9c018c6e4dec","observation_id":"c8935677-a74d-472a-852f-2e6abd82da0f","resolution":{"observed_at":"2026-08-01T18:39:13.091018Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1807.03748","last_updated":"2019-01-22T18:47:12Z","snapshot_observed_at":"2026-07-06T06:49:24.960992Z","submitted_at":"2018-07-10T16:52:11Z","title":"Representation Learning with Contrastive Predictive Coding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.03748","snapshot_observed_at":"2026-08-01T18:39:13.191786Z","title":"Representation learning with contrastive predictive coding","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:13.191786Z"},"links":{"cited_paper":"/paper/1807.03748","citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:36f46ab36e1c27b2f6110c960fe0c86a342ec34999cefa4b16589d18e66b319a","observation_id":"d12d6d18-7513-4389-a91d-5b096b8d69cf","resolution":{"observed_at":"2026-08-01T18:39:13.191786Z","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":"2026-08-01T18:39:13.242242Z","title":"Ring perception using breadth-first search.Journal of chemical information and computer sciences, 36(5):986–991, 1996","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:13.242242Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:ae6653f3376722761d165d8c8ea40867c5943074726ac946eb1fb4b20afe9f8d","observation_id":"61798a6b-bb49-4bd3-ae9e-5815ed7a46e7","resolution":{"observed_at":"2026-08-01T18:39:13.242242Z","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":"2026-08-01T18:39:13.295475Z","title":"On the art of compiling and using’drug-like’chemical fragment spaces.ChemMedChem, 3(10):1503, 2008","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:13.295475Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:730f2fe1bf78ba390dc3d884792c15c762a485e2f2d4ac3b65d54cdaa85a2f33","observation_id":"890f2401-243b-44d1-9e1a-a696484575c3","resolution":{"observed_at":"2026-08-01T18:39:13.295475Z","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":"2026-08-01T18:39:13.348164Z","title":"The properties of known drugs","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:13.348164Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:066d89dde3f66f087a6424cc29fc502bebb0c15baaa70426fac608559039612e","observation_id":"e372536b-d332-43d2-a04a-1a99d817b236","resolution":{"observed_at":"2026-08-01T18:39:13.348164Z","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":"2026-08-01T18:39:13.437168Z","title":"Convolutional neural networks on graphs with chebyshev approxi- mation, revisited","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:13.437168Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:552bc398bd53474fc2adb03c0532b4e613a4d7c90ed158bcd307b09cce62baec","observation_id":"4df3299d-a0c4-4e6f-b833-4a60d020a141","resolution":{"observed_at":"2026-08-01T18:39:13.437168Z","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":"2026-08-01T18:39:13.519167Z","title":"Convolutional neural networks on graphs with fast localized spectral filtering.Advances in neural information processing systems, 29, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:13.519167Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:876401bb9708f15f193c8ec40767a5eebfe6240e60462c8f328d97ec8ed24cb3","observation_id":"1fac829a-be97-466e-9fa1-2d64a9a68e8e","resolution":{"observed_at":"2026-08-01T18:39:13.519167Z","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":"2026-08-01T18:39:13.584169Z","title":"Mtgl-admet: a novel multi-task graph learning framework for admet prediction enhanced by status-theory and maximum flow","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:13.584169Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:a9e75d7c2a150590e61fc5ce8f9f2bc9203b0500686afddde473ad78420f1eb1","observation_id":"e075fdd2-d2f0-44db-9558-1bd9669dceef","resolution":{"observed_at":"2026-08-01T18:39:13.584169Z","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":"2026-08-01T18:39:13.642612Z","title":"Mtgib-unet: A multi-task graph information bottleneck and uncertainty weighted network for admet prediction","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:13.642612Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:78f707988242af3fff3b626925bbddf7ac8f61ce72c7ed2d59230a9830996951","observation_id":"d7313e98-5651-41a0-ad71-175c438e7124","resolution":{"observed_at":"2026-08-01T18:39:13.642612Z","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":"2026-08-01T18:39:13.751339Z","title":"Semi-supervised classification with graph convolutional networks.arXiv preprint arXiv:1609.02907, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:13.751339Z"},"links":{"cited_paper":"/paper/1609.02907","citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:24db0b0b9b42b1d4707bc1a9c4b74fe986177820b5e96f1c2ebfeabd991cb17c","observation_id":"66b0b971-3ef0-4bf8-88cb-7271bc1814c6","resolution":{"observed_at":"2026-08-01T18:39:13.751339Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.10903","last_updated":"2018-02-04T19:13:29Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-10-30T12:41:12Z","title":"Graph Attention Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.10903","snapshot_observed_at":"2026-08-01T18:39:13.843844Z","title":"Graph attention networks.arXiv preprint arXiv:1710.10903, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:13.843844Z"},"links":{"cited_paper":"/paper/1710.10903","citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:84394ef986d5155fffc326f4fe1d7516b71912511ffcee062e389af0b60efc76","observation_id":"a7d86138-82de-499b-b15f-d91947681879","resolution":{"observed_at":"2026-08-01T18:39:13.843844Z","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":"2026-08-01T18:39:13.925232Z","title":"Chemberta: large-scale self-supervised pretraining for molecular property prediction.arXiv preprint arXiv:2010.09885, 2020","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:13.925232Z"},"links":{"cited_paper":"/paper/2010.09885","citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:bc86c990c8fb26ec6a51273907201599058924fb6e17e4d9b01df28f92feb6a5","observation_id":"d502ff06-32b3-4bb3-9bc2-f8334b22f5a5","resolution":{"observed_at":"2026-08-01T18:39:13.925232Z","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":"2026-08-01T18:39:13.994581Z","title":"Modeling physico-chemical admet endpoints with multitask graph convolutional networks.Molecules, 25(1):44, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:13.994581Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:e5362312fe3be1358a11a3ee392ee10bdae432fcbe4fd44fa26aa1cfdf4603b9","observation_id":"7ba87551-a0f0-4ff7-8926-0e8e84f6860a","resolution":{"observed_at":"2026-08-01T18:39:13.994581Z","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":"2026-08-01T18:39:14.068280Z","title":"Bayesian flow network framework for chemistry tasks.Journal of Chemical Information and Modeling, 65(3):1178–1187, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:14.068280Z"},"links":{"citing_paper":"/paper/2607.18332"},"observation_digest":"sha256:29d8cf4f2395c5c548ca7392a31ac917d60c8b9d2e25b87bc258ba878f4b3159","observation_id":"eb29134e-1bc7-4be1-b323-4f6fd30d2027","resolution":{"observed_at":"2026-08-01T18:39:14.068280Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.18332","last_updated":"2026-07-22T14:11:41Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T15:51:06.659537Z","submitted_at":"2026-07-19T13:33:35Z","title":"ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction"},"reference_resolution":{"displayed":68,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":68,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":68},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 68 of 68 outbound references and 0 inbound Pith citation observations for arXiv:2607.18332."}