{"as_of":"2026-08-07T22:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6ca3b34462e9abbe1f0bf40fe77e4be3ef7f27f55a554d83ed6e79e6015caf2b","coverage":[{"denominator":72,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":72,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T14:56:48.182251Z","state":"measured"},{"denominator":72,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":72,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+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/2509.22468/citation-record","integrity":"/paper/2509.22468/integrity","json":"/paper/2509.22468/citation-record.json","paper":"/paper/2509.22468"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T14:56:47.933172Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.933172Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:89833d3ba5987bc633e3ba2093f7ea3a4b8a1b52b5af5d3bbdd0dda9924c98a9","observation_id":"d514100f-9db8-4a6e-a34e-daa9005c1e83","resolution":{"observed_at":"2026-08-04T14:56:47.933172Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.01179","last_updated":"2021-06-04T14:52:04Z","snapshot_observed_at":"2026-07-31T03:18:54.464120Z","submitted_at":"2020-10-02T19:53:05Z","title":"The Surprising Power of Graph Neural Networks with Random Node Initialization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.01179","snapshot_observed_at":"2026-08-04T14:56:47.935962Z","title":"The surprising power of graph neural networks with random node initialization, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.935962Z"},"links":{"cited_paper":"/paper/2010.01179","citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:ff99b714dcd93b1bfc98372446c444a6bb903232d124b4494b13514b30e31414","observation_id":"16fb38a1-ff67-4f07-94a0-d292abb9066e","resolution":{"observed_at":"2026-08-04T14:56:47.935962Z","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":"2026-08-04T14:56:47.938475Z","title":"Self- Supervised Learning From Images With a Joint-Embedding Predictive Architecture","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.938475Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:cd73e61c7dc853921035ae423f475422079a788ccc11b65ff5ec3ebced928ab4","observation_id":"fb393b34-926b-4034-b96a-639b0e690c3e","resolution":{"observed_at":"2026-08-04T14:56:47.938475Z","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":"2026-08-04T14:56:47.940792Z","title":"Geom, energy-annotated molecular conformations for property prediction and molecular generation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.940792Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:72eefa72284858c2207dfdd6ac154e31737eb19099c5648f64754dca6e1d91e6","observation_id":"2af052c5-e291-4f24-b746-4eb54c97a6a0","resolution":{"observed_at":"2026-08-04T14:56:47.940792Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.00483","last_updated":"2023-09-01T14:20:48Z","snapshot_observed_at":"2026-08-04T00:06:23.053195Z","submitted_at":"2023-09-01T14:20:48Z","title":"Geometry-aware Line Graph Transformer Pre-training for Molecular Property Prediction","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.00483","snapshot_observed_at":"2026-08-04T14:56:47.942774Z","title":"Geometry-aware line graph transformer pre-training for molecular property prediction, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.942774Z"},"links":{"cited_paper":"/paper/2309.00483","citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:265d956ffad9c7d4b1624532012320ee3e588c4e5a76389edc4bc2a6389dbd80","observation_id":"78452e43-d602-4ae1-a60f-c3ebbf6bbd8e","resolution":{"observed_at":"2026-08-04T14:56:47.942774Z","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":"2026-08-04T14:56:47.945158Z","title":"Towards foundational models for molecular learning on large-scale multi-task datasets","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.945158Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:33e7c605ec5169ea836c7ec3a4b753d5381cabf9bdf689e7968a23be3d8c8957","observation_id":"fdf6a44a-4745-4504-ab7d-41b85dd62edc","resolution":{"observed_at":"2026-08-04T14:56:47.945158Z","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":"2026-08-04T14:56:47.947238Z","title":"Bronstein, and Haggai Maron","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.947238Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:f690127986f0034484fd8166609b351f7d9277aba0fc8ef0dac17b157860d8e5","observation_id":"93568bae-e443-4b28-be5d-835f4be88334","resolution":{"observed_at":"2026-08-04T14:56:47.947238Z","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":"2026-08-04T14:56:47.949400Z","title":"Design of protein-binding proteins from the target structure alone","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.949400Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:06d5ca958e4146726da818b290ddae6936348f8ce900c657df8c21adcc69cea0","observation_id":"d363d459-deb3-4971-a96d-5982208a585a","resolution":{"observed_at":"2026-08-04T14:56:47.949400Z","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":"2026-08-04T14:56:47.951285Z","title":"Emerging properties in self-supervised vision transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.951285Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:eca906e88ec511292f221413933d117f1d2a616b7aa381a81bef9bdf3791b5ef","observation_id":"1de0b216-056d-42b1-b2b4-d0902e14851d","resolution":{"observed_at":"2026-08-04T14:56:47.951285Z","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":"2026-08-04T14:56:47.953275Z","title":"A simple framework for contrastive learning of visual representations","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.953275Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:192242e2e61f6cad63d3e91f7f961eb0e466da0db77333f159760b4a255e63ab","observation_id":"78a78749-ad2a-49bd-b17f-01032d696293","resolution":{"observed_at":"2026-08-04T14:56:47.953275Z","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":"2026-08-04T14:56:47.955251Z","title":"BERT : Pre-training of Deep Bidirectional Transformers for Language Understanding","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.955251Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:eb598277343db25827ab012c3fba5a01f3db2d5091c625af63fb16a23d9a2d49","observation_id":"067cfaaf-63b1-4390-830e-e281dab9b6bd","resolution":{"observed_at":"2026-08-04T14:56:47.955251Z","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":"2026-08-04T14:56:47.957256Z","title":"Elton, Zois Boukouvalas, Mark D","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.957256Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:500fe51789f27e2a23cdc1f125dda08122356f0ba20ae4fada02c4e88abeff4e","observation_id":"aa1493b2-6d98-469e-808e-e78c59bd8507","resolution":{"observed_at":"2026-08-04T14:56:47.957256Z","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":"2026-08-04T14:56:47.959387Z","title":"UniCorn : A Unified Contrastive Learning Approach for Multi-view Molecular Representation Learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.959387Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:815944bfbc58a007677b763adfc78717f019c00024a52d243685738be565840c","observation_id":"4ea702aa-d126-42b5-bad6-fb88438b723c","resolution":{"observed_at":"2026-08-04T14:56:47.959387Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.02428","last_updated":"2019-04-25T10:06:09Z","snapshot_observed_at":"2026-08-02T18:54:43.326912Z","submitted_at":"2019-03-06T14:50:02Z","title":"Fast Graph Representation Learning with PyTorch Geometric","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.02428","snapshot_observed_at":"2026-08-04T14:56:47.961224Z","title":"Fast graph representation learning with pytorch geometric","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.961224Z"},"links":{"cited_paper":"/paper/1903.02428","citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:ad80f240485d974379ee77af692f6b965e8ec93315cb25450d2cb981b7a4fa73","observation_id":"1e358066-de9b-4f68-ba74-f76725c9a692","resolution":{"observed_at":"2026-08-04T14:56:47.961224Z","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":"2026-08-04T14:56:47.963427Z","title":"Gemnet: Universal directional graph neural networks for molecules","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.963427Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:be44a01de7b3094554d7954523af9126f2bfba53e418dce848e38a7feb183983","observation_id":"5c09f722-d34a-4879-8bd9-1e5cc410d127","resolution":{"observed_at":"2026-08-04T14:56:47.963427Z","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":"2026-08-04T14:56:47.965729Z","title":"A comprehensive discovery platform for organophosphorus ligands for catalysis","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.965729Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:71246966911555fe3d2a5d957dd56eb5ada347e46878e89144c7041cf3cf9208","observation_id":"a89841d8-37e9-4973-b646-c6c5e099260e","resolution":{"observed_at":"2026-08-04T14:56:47.965729Z","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":"2026-08-04T14:56:47.967544Z","title":"Schoenholz, Patrick F","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.967544Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:b1411d226323e25be44ce50e53172c083c66d03610333fb881b4a1ae84a9c461","observation_id":"c099be09-92d5-4b14-a77d-deb6bec9bf01","resolution":{"observed_at":"2026-08-04T14:56:47.967544Z","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":"2026-08-04T14:56:47.969326Z","title":"Bootstrap your own latent - a new approach to self-supervised learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.969326Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:c2cc3a27d3a549c4662cfa0e33b2f7e3177df08142e399248622a3de039f5c38","observation_id":"518d4d35-ed9b-49d7-ba9d-c2c487940267","resolution":{"observed_at":"2026-08-04T14:56:47.969326Z","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":"2026-08-04T14:56:47.971218Z","title":"Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.971218Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:3d720a323ac5b05e25beec5dc6be32175ef605fd97263248122a207fea0dfbe9","observation_id":"665e655e-fb4b-4b78-b7e2-b54f996d37e6","resolution":{"observed_at":"2026-08-04T14:56:47.971218Z","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":"2026-08-04T14:56:47.973268Z","title":"Inductive Representation Learning on Large Graphs","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.973268Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:783f29a3c73af884ee40bf151400b67d5529a89b4f8dc6aaaae124e725945a3b","observation_id":"94e0dda5-de0c-415a-a7ed-2ea1600f578c","resolution":{"observed_at":"2026-08-04T14:56:47.973268Z","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":"2026-08-04T14:56:47.975369Z","title":"Masked Autoencoders Are Scalable Vision Learners","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.975369Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:6ae9f1a37805f1495992975f6b5645bd93a9388424fa6c8e331cf13505128e37","observation_id":"fd729e10-0a32-49f5-a3fd-66023af62cf6","resolution":{"observed_at":"2026-08-04T14:56:47.975369Z","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":"2026-08-04T14:56:47.977268Z","title":"Convolutional neural network based on smiles representation of compounds for detecting chemical motif","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.977268Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:7349e7c2a25fdcc1bb8f77ca5ba23a85eb2ba0f5871582db6a7ee8ceff5e2619","observation_id":"bbaff363-8bd4-4548-8388-c274115f7a6d","resolution":{"observed_at":"2026-08-04T14:56:47.977268Z","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":"2026-08-04T14:56:47.979166Z","title":"GraphMAE : Self-Supervised Masked Graph Autoencoders","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.979166Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:b42f98075775e5d1fd79c8c5c348bee8b417d6e7b36851396dbb3e66c8ec80be","observation_id":"ce550f6b-6b46-4b2d-adfa-5d5885c47067","resolution":{"observed_at":"2026-08-04T14:56:47.979166Z","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":"2026-08-04T14:56:47.981272Z","title":"Strategies for Pre-training Graph Neural Networks , February 2020 a","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.981272Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:a50b3733957863d4af207e9f61494d56fc97f24b4997aa58e0200b9f69388c1d","observation_id":"26b71734-8065-42b2-822e-6f556b7e94ef","resolution":{"observed_at":"2026-08-04T14:56:47.981272Z","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":"2026-08-04T14:56:47.983205Z","title":"Gpt-gnn: Generative pre-training of graph neural networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.983205Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:1d7687f1024b408568fb54ca63836aa08875118a418dbc896de62d96397a347a","observation_id":"62e9843f-f140-4a81-bd11-dab0eb0ac84f","resolution":{"observed_at":"2026-08-04T14:56:47.983205Z","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":"2026-08-04T14:56:47.984987Z","title":"A fast and high quality multilevel scheme for partitioning irregular graphs","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.984987Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:661a79a6a767e02f92b12dcf6fbd49a7ef3a20000b42e55eb9d5f3a8584cb56b","observation_id":"de03bacd-bc3c-483a-ae0a-d3d93eb9c7f1","resolution":{"observed_at":"2026-08-04T14:56:47.984987Z","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":"2026-08-04T14:56:47.986838Z","title":"Kipf and Max Welling","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.986838Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:1ae5e78fde746f2249af18440fb94f2eec4f62860790bde8818ca067eaaf2a59","observation_id":"a041091d-2401-4d91-8d58-004fc81810c1","resolution":{"observed_at":"2026-08-04T14:56:47.986838Z","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":"2026-08-04T14:56:47.988887Z","title":"3D-Mol : A Novel Contrastive Learning Framework for Molecular Property Prediction with 3D Information , June 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.988887Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:eb964ae5c76a7c914f912c61ea06eeadfec265c12aa9340a5c62bdad6754058a","observation_id":"ced94549-3182-4545-af89-598623314a4e","resolution":{"observed_at":"2026-08-04T14:56:47.988887Z","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":"2026-08-04T14:56:47.990811Z","title":"Rdkit: Open-source cheminformatics http://www.rdkit.org","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.990811Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:b1346303cbc66762036c70c4fcdaadca0f1974e388a373d3fe3a292e4d369bf2","observation_id":"87e55e5b-c488-4a68-9603-1563e3e3c24d","resolution":{"observed_at":"2026-08-04T14:56:47.990811Z","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":"2026-08-04T14:56:47.992759Z","title":"A path towards autonomous machine intelligence","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.992759Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:9e53041c6ee771fb4baac6cca832afc37b9113fac9006f75cdb054f364b447ee","observation_id":"ecefb6b3-db8b-4e82-8915-130812f6b6c0","resolution":{"observed_at":"2026-08-04T14:56:47.992759Z","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":"2026-08-04T14:56:47.994732Z","title":"Augmentation- Free Self-Supervised Learning on Graphs","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.994732Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:af8e3f4ed2f3e70bfe91f6adb143695d31c48992f00fc0c5ce61784bbc7ad670","observation_id":"0f49f6c7-c738-4be5-9b7e-ed66066f82aa","resolution":{"observed_at":"2026-08-04T14:56:47.994732Z","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":"2026-08-04T14:56:47.996586Z","title":"Pre-training Molecular Graph Representation with 3D Geometry , May 2022 a","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.996586Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:cfefee729f400f972da91bed74da835b0c84f903b6ac3f2f1600c730783d6dfd","observation_id":"ea45fade-9f0b-41f1-8f3e-777c88d95079","resolution":{"observed_at":"2026-08-04T14:56:47.996586Z","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":"2026-08-04T14:56:47.998456Z","title":"A group symmetric stochastic differential equation model for molecule multi-modal pretraining","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:47.998456Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:d420292ce51e948148ee0d6486af203b829a87294a9e4f0399074f455fe3cf36","observation_id":"ecbda52e-dc16-4e3d-b88b-81e489c959fc","resolution":{"observed_at":"2026-08-04T14:56:47.998456Z","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":"2026-08-04T14:56:48.000256Z","title":"Auto3d: Automatic generation of the low-energy 3d structures with ani neural network potentials","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.000256Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:eb5d682192a4ab9ef79a72648b23659c7e088fb7887797e3bece9f6e77ceda6c","observation_id":"cc154c98-48fd-42ff-9f46-bc2d0a476e45","resolution":{"observed_at":"2026-08-04T14:56:48.000256Z","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":"2026-08-04T14:56:48.002319Z","title":"The challenge of balancing model sensitivity and robustness in predicting yields: a benchmarking study of amide coupling reactions","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.002319Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:c5c3adf094f48da9380f576a9b38729a3d12cc12afb086e52ad9a6fb9ac3db0a","observation_id":"b6f60f58-c0b9-48f6-84ed-d2d59937e7ee","resolution":{"observed_at":"2026-08-04T14:56:48.002319Z","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":"2026-08-04T14:56:48.004303Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.004303Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:525192314cf209081a11d22f2ad151d24b7f729c6761d8ce292ad0b269f83071","observation_id":"23f2b328-a7f0-4580-bfd0-7091293d73bc","resolution":{"observed_at":"2026-08-04T14:56:48.004303Z","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":"2026-08-04T14:56:48.006159Z","title":"MolMix : A Simple Yet Effective Baseline for Multimodal Molecular Representation Learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.006159Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:2cb0734f7b8f251544080e3fc902b7f4b2283d5d1da2540b18ccd95b3f423754","observation_id":"30a988d4-e909-41b8-9680-55c85c2726cb","resolution":{"observed_at":"2026-08-04T14:56:48.006159Z","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":"2026-08-04T14:56:48.007981Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.007981Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:b789d22a3f0940e0ad040b8df7b3dd269669105bedf6028542639fe3e1cb1bfd","observation_id":"8a1e00c4-7cd3-479f-88ca-92903ede26ba","resolution":{"observed_at":"2026-08-04T14:56:48.007981Z","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":"2026-08-04T14:56:48.009797Z","title":"Graph neural networks can (often) count substructures","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.009797Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:ec8f38d573120b2099210f05d11e399b05c1ae08cb4d7d1813f20c3435f0209e","observation_id":"df8d974a-c6ce-48a2-a031-255db1642dfe","resolution":{"observed_at":"2026-08-04T14:56:48.009797Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.10241","last_updated":"2020-10-20T13:05:05Z","snapshot_observed_at":"2026-07-06T10:06:13.354003Z","submitted_at":"2020-10-20T13:05:05Z","title":"BYOL works even without batch statistics","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.10241","snapshot_observed_at":"2026-08-04T14:56:48.011793Z","title":"Richemond, Jean-Bastien Grill, Florent Altché, Corentin Tallec, Florian Strub, Andrew Brock, Samuel Smith, Soham De, Razvan Pascanu, Bilal Piot, and Michal Valko","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.011793Z"},"links":{"cited_paper":"/paper/2010.10241","citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:f043d7af005a4b64c79e20caea3639390563ec29700b87d2d8e4f3f6dc637d13","observation_id":"631a5fd7-ce4a-4e72-8875-f4be03b25d27","resolution":{"observed_at":"2026-08-04T14:56:48.011793Z","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":"2026-08-04T14:56:48.014051Z","title":"Self- Supervised Graph Transformer on Large-Scale Molecular Data","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.014051Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:5496b659335793375efadd0f9178653c039e4c1c229d8b3a08ceb45fb3f9b03f","observation_id":"899db52b-0db9-4f93-a6d8-910f6093921a","resolution":{"observed_at":"2026-08-04T14:56:48.014051Z","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":"2026-08-04T14:56:48.015946Z","title":"u tt, Pieter-Jan Kindermans, Huziel E. Sauceda, Stefan Chmiela, Alexandre Tkatchenko, and Klaus-Robert M \\","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.015946Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:12dd5d11254db91221675cfe484260e21bf3252f06bedb1ed8bb8748831ceb61","observation_id":"a5f9e8d8-392d-4759-b40a-c4d9ad9a03d3","resolution":{"observed_at":"2026-08-04T14:56:48.015946Z","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":"2026-08-04T14:56:48.017878Z","title":"Graph-level Representation Learning with Joint-Embedding Predictive Architectures , January 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.017878Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:f64256e51fcfed4356046dcc6ac21fe80d669dc1c287fc131e61315934034ff5","observation_id":"f7b3c9e5-ff66-4404-92f0-c382c452b1e0","resolution":{"observed_at":"2026-08-04T14:56:48.017878Z","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":"2026-08-04T14:56:48.019958Z","title":"a rk, Dominique Beaini, Gabriele Corso, Prudencio Tossou, Christian Dallago, Stephan G \\","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.019958Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:5a33bbb9a851601559dffcca1d69f915ed248a2d242140390b31c2667d115545","observation_id":"3609ab66-8dd5-4de4-8c69-910c21024eb3","resolution":{"observed_at":"2026-08-04T14:56:48.019958Z","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":"2026-08-04T14:56:48.021855Z","title":"InfoGraph : Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization , January 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.021855Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:4b70dc8e277b171c2d76356f57be239722a02e682c4172503aaf2619eca22609","observation_id":"f2519d4e-85e6-44a3-ac9f-06ea8de444d0","resolution":{"observed_at":"2026-08-04T14:56:48.021855Z","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":"2026-08-04T14:56:48.023744Z","title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.023744Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:2939f9d0bccae42b7b1457fc982c3b06ed25cc0da71f5a0ae95f3588f9ecb4ee","observation_id":"413daeff-8fe9-411b-92db-1020e7121f6d","resolution":{"observed_at":"2026-08-04T14:56:48.023744Z","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":"2026-08-04T14:56:48.025606Z","title":"Dyer, R \\'e mi Munos, Petar Veli c kovi \\'c , and Michal Valko","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.025606Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:7c44e5134135d51e4898ef7c98fe6631107f7818b97b175e935f303c4ba89571","observation_id":"3670b46f-c70f-426c-b4ff-5c9a33f3fbe9","resolution":{"observed_at":"2026-08-04T14:56:48.025606Z","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":"2026-08-04T14:56:48.027600Z","title":"Attention is All you Need","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.027600Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:ed1bf9cc7705120dd93a360aaf71b435cb241fafbbb82974fe72accfdbef941a","observation_id":"3374e316-dea0-494c-a915-5fcf92c638a8","resolution":{"observed_at":"2026-08-04T14:56:48.027600Z","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":"2026-08-04T14:56:48.029478Z","title":"Evaluating self-supervised learning for molecular graph embeddings","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.029478Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:a66ffe3cd25551a44eebcc1df1a4af048983083a733079479ab4e8f3d64832a6","observation_id":"dde50090-dcec-433f-aa47-8f70e6aa976c","resolution":{"observed_at":"2026-08-04T14:56:48.029478Z","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":"2026-08-04T14:56:48.031562Z","title":"Smiles-bert: large scale unsupervised pre-training for molecular property prediction","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.031562Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:89ef20f63a899fe0d321853b3e378ea23c046fbd71bb5864097a7b71fc846821","observation_id":"c20aa722-19d2-4dd3-9768-7078ac36835d","resolution":{"observed_at":"2026-08-04T14:56:48.031562Z","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":"2026-08-04T14:56:48.033474Z","title":"Automated 3d pre-training for molecular property prediction","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.033474Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:2113900f4cf20a800b12d7a7be3026298c9a22eaed06c360ba59588194772598","observation_id":"7eedfd89-1064-4c32-9301-6b66365731c9","resolution":{"observed_at":"2026-08-04T14:56:48.033474Z","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":"2026-08-04T14:56:48.035484Z","title":"Molecular contrastive learning of representations via graph neural networks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.035484Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:ad2633aad51b448a5332b0841e4932205bad9e9ffa0041c6cb02cf5d1aa8e97e","observation_id":"c8fde751-8d1e-4199-b266-485e19427a0f","resolution":{"observed_at":"2026-08-04T14:56:48.035484Z","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":"2026-08-04T14:56:48.037308Z","title":"The reduction of a graph to canonical form and the algebra which appears therein","venue":null,"work_id":null,"year":1968},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.037308Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:5680e7942ddd4927b55ad1c41cac3b547740ccb48c3ec66de0a60f7c6a881cca","observation_id":"90b8e1fb-d204-4658-9b1f-6717bdecf8d2","resolution":{"observed_at":"2026-08-04T14:56:48.037308Z","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":"2026-08-04T14:56:48.039137Z","title":"The mechanism of prediction head in non-contrastive self-supervised learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.039137Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:32d529f45a2f10c7e7cb4313bb0f1567b33d41a3c66a9288792f4de9fb3bd8ee","observation_id":"e145b4c8-8dfe-47fe-9c26-debe833a9bea","resolution":{"observed_at":"2026-08-04T14:56:48.039137Z","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":"2026-08-04T14:56:48.040974Z","title":"Wigh, Jonathan M","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.040974Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:3ad64b89240bff943c1b4cde05adc8bba84f16c8ed3d98081a02c628c5ffdd9f","observation_id":"1b8e9e95-d48b-4f2e-827c-bf67310a6000","resolution":{"observed_at":"2026-08-04T14:56:48.040974Z","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":"2026-08-04T14:56:48.042851Z","title":"a ger, Niklas Kemper, Leon Hetzel, Johanna Sommer, and Stephan G \\","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.042851Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:eb47ba4581f2604d57c8d3b91391f724b302441e10aa6d26842e0780fc9bed0d","observation_id":"9ea90ea6-1433-479d-afef-c1de1a3401cb","resolution":{"observed_at":"2026-08-04T14:56:48.042851Z","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":"2026-08-04T14:56:48.044630Z","title":"Moleculenet: a benchmark for molecular machine learning","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.044630Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:4d3b6b0b614a4d8cdf1cfb088b6a3489f930252b0ba4fda464a9c362e904ba59","observation_id":"cfad4992-5368-4693-8e5c-3044bf3749b2","resolution":{"observed_at":"2026-08-04T14:56:48.044630Z","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":"2026-08-04T14:56:48.046494Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.046494Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:9eeae5bd53be345efff23211e1faccc73084b05fa36cc2cad2e69be383269c34","observation_id":"15ed6e82-4af7-48f5-a6f8-60003b70fa4b","resolution":{"observed_at":"2026-08-04T14:56:48.046494Z","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":"2026-08-04T14:56:48.048411Z","title":"Self- Supervised Representation Learning via Latent Graph Prediction","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.048411Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:f7c8bdebec3de42a7a898769572ef29a13b833b733d4ff6bce9738fff69c46fc","observation_id":"69f9a256-42a3-4c44-b7f9-110121bbc00b","resolution":{"observed_at":"2026-08-04T14:56:48.048411Z","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":"2026-08-04T14:56:48.051219Z","title":"How Powerful are Graph Neural Networks ?, February 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.051219Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:5b97553e7233e3f45a4bd8abea220696ff266049cb76047a58f9cf5805cf38ce","observation_id":"904533d1-f78f-43e9-85f5-b3d0fbb5efea","resolution":{"observed_at":"2026-08-04T14:56:48.051219Z","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":"2026-08-04T14:56:48.053514Z","title":"Self-supervised graph-level representation learning with local and global structure","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.053514Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:45b8a15dd4f69a607f116a0e8150d48d4c127c02ecdbae8f53244c44664e3c63","observation_id":"7bb7d37f-6f4f-4b80-a113-24d6ab7116f9","resolution":{"observed_at":"2026-08-04T14:56:48.053514Z","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":"2026-08-04T14:56:48.055651Z","title":"Graph contrastive learning automated","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.055651Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:912480e13647a8a4091f03efc9fbaf7373909727ccbe15504fa605e7412d3c74","observation_id":"f38c8e33-49f9-4163-89fa-036cb48f4023","resolution":{"observed_at":"2026-08-04T14:56:48.055651Z","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":"2026-08-04T14:56:48.057658Z","title":"Graph Contrastive Learning with Augmentations , April 2021 b","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.057658Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:9621fcf86f86208ce41fb5d7879ff5afb795942e3c8fcec4257fdc795b579979","observation_id":"b054b847-c84c-4d99-bb9d-fd4df5d79497","resolution":{"observed_at":"2026-08-04T14:56:48.057658Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.06235","last_updated":"2023-10-08T13:58:18Z","snapshot_observed_at":"2026-08-01T15:31:41.523035Z","submitted_at":"2023-07-12T15:27:06Z","title":"Multimodal Molecular Pretraining via Modality Blending","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.06235","snapshot_observed_at":"2026-08-04T14:56:48.059534Z","title":"Multimodal molecular pretraining via modality blending","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.059534Z"},"links":{"cited_paper":"/paper/2307.06235","citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:ff05ed8c5f571e96bbfea9cc51fb07b51edaa43256b333f63a13adee1477cb3b","observation_id":"dac46131-b7b9-4d4f-962d-2b169795ff63","resolution":{"observed_at":"2026-08-04T14:56:48.059534Z","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":"2026-08-04T14:56:48.061903Z","title":"Deep sets","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.061903Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:156b7fbde1d3dada9aa30444d194293087794612c1c5c9dd13662412943a7973","observation_id":"3922b3cf-8ed7-4d2f-92ad-3f4767b96f95","resolution":{"observed_at":"2026-08-04T14:56:48.061903Z","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":"2026-08-04T14:56:48.063889Z","title":"From Canonical Correlation Analysis to Self-supervised Graph Neural Networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.063889Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:6e49f3b315e75ab2df02387363d2d1c31f03040e3d26e10ad3b536b3f42cdc29","observation_id":"0a7fdec4-c398-480c-83ea-f9d920737c64","resolution":{"observed_at":"2026-08-04T14:56:48.063889Z","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":"2026-08-04T14:56:48.066329Z","title":"Motif-based Graph Self-Supervised Learning for Molecular Property Prediction","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.066329Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:f952631f8ae52d69b39899356ee2e7f36551c1ead12ea61e2d9d2a7904c4f5c1","observation_id":"a16f8fe3-e9b3-4043-b02b-c3025ced47eb","resolution":{"observed_at":"2026-08-04T14:56:48.066329Z","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":"2026-08-04T14:56:48.169870Z","title":"Unified 2d and 3d pre-training of molecular representations","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.169870Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:34bfaae1228e9b320d9326475692af61cc13e6256d8bb725665933f2a252a531","observation_id":"657232e9-0d1c-421b-a8a0-c09f9d1fc2f5","resolution":{"observed_at":"2026-08-04T14:56:48.169870Z","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":"2026-08-04T14:56:48.175961Z","title":"Coley, Yizhou Sun, and Wei Wang","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.175961Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:916bf0a39d007f1400886bac0df554587a6ed45782edfdd91d2928ed62f38700","observation_id":"0319f1a0-e1f3-4df5-8ff2-f9e87c1887ac","resolution":{"observed_at":"2026-08-04T14:56:48.175961Z","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":"2026-08-04T14:56:48.178068Z","title":"@esa (Ref","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.178068Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:80ab4cac645cfc8184ec42dfe76372879343510e845beec68efe82f356bd866e","observation_id":"50970bdb-328c-4ad3-910e-1d5aba25aef5","resolution":{"observed_at":"2026-08-04T14:56:48.178068Z","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":"2026-08-04T14:56:48.180311Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.180311Z"},"links":{"citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:f4528b9b0f456e009d0b203d29352a7cbd35b2407b133b50239f99fabd9419f5","observation_id":"33a89c30-a6d6-49b1-8d7f-177cdeb02837","resolution":{"observed_at":"2026-08-04T14:56:48.180311Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.17366","last_updated":"2024-06-28T02:56:10Z","snapshot_observed_at":"2026-07-06T16:25:34.527871Z","submitted_at":"2023-09-28T10:05:37Z","title":"3D-Mol: A Novel Contrastive Learning Framework for Molecular Property Prediction with 3D Information","version":3},"cited_work":{"arxiv_id":"2309.17366","doi":"10.48550/arxiv.2309.17366","metadata_source":"pith","pith_arxiv_id":"2309.17366","snapshot_observed_at":"2026-08-05T02:49:54.815029Z","title":"3D-Mol: A Novel Contrastive Learning Framework for Molecular Property Prediction with 3D Information","venue":"q-bio.BM","work_id":"52c44216-0e7d-4343-93eb-06c3969889b4","year":2023},"citing_paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","version":2},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-08-04T14:56:48.182251Z"},"links":{"cited_paper":"/paper/2309.17366","citing_paper":"/paper/2509.22468"},"observation_digest":"sha256:208c15726257dab9ec0b987b0584f21b8e4512c0bf70017bba706906c9d463b7","observation_id":"834164cd-ad22-4966-8a88-413d27de729b","resolution":{"observed_at":"2026-08-04T14:58:52.328843Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2509.22468","last_updated":"2026-06-02T10:51:32Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T03:52:18.851570Z","submitted_at":"2025-09-26T15:16:20Z","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining"},"reference_resolution":{"displayed":72,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":71,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":72},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 72 of 72 outbound references and 0 inbound Pith citation observations for arXiv:2509.22468."}