{"as_of":"2026-08-09T10:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:22f82ed3cc4ac2d3db247edcd92b587ebef5b41a4cc7e4a51b55b3b8d0afcf42","coverage":[{"denominator":30,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":30,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-31T13:03:59.267985Z","state":"measured"},{"denominator":30,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":30,"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/2607.28259/citation-record","integrity":"/paper/2607.28259/integrity","json":"/paper/2607.28259/citation-record.json","paper":"/paper/2607.28259"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T13:03:59.047125Z","title":"Two stability lemmas","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:59.047125Z"},"links":{"citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:31b5c034c29b6b1774f4b0c8e19429d2e7d5e2c5185f983e6f996c4ec91dd1f0","observation_id":"36e73318-5f73-46df-8f5d-012ec701d401","resolution":{"observed_at":"2026-07-31T13:03:59.047125Z","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":"2026-07-31T13:03:59.256914Z","title":"The outputs z1, z2, and z3 are then combined through a learnable weighted sum","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:59.256914Z"},"links":{"citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:14a088dac2003d06e0f839a84bd136a34926f3fa3673c2089a511e8d6fbbada1","observation_id":"26ca36ec-c1cb-4e6e-85c1-9dbdab467445","resolution":{"observed_at":"2026-07-31T13:03:59.256914Z","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":"2026-07-31T13:03:58.985391Z","title":"For the MLP component, we employed a two-layer MLP with a hidden dimension of 200, ensuring that its output dimension matches the output dimension of the TOPOFORMERmodel","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:58.985391Z"},"links":{"citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:3f9e716d1a5d421e3b318ef73376243356ad970004b13a6cb7682a0115ef8343","observation_id":"dacfb4ae-66c3-4b19-92ef-d69a157f7452","resolution":{"observed_at":"2026-07-31T13:03:58.985391Z","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":"2026-07-31T13:03:59.267985Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:59.267985Z"},"links":{"citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:4135a13da376e3a6376f0edbfe6d69633d2f62e738582ea51720bbdaa717f49a","observation_id":"ae620162-f7dc-4c6d-8a4d-c39735248266","resolution":{"observed_at":"2026-07-31T13:03:59.267985Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-07-31T13:03:57.839231Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale.arXiv preprint arXiv:2010.11929,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:57.839231Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:86ab2b6293e093403b63c3fc8a613fac3f5217c7e34dafbba86537573854176b","observation_id":"27a4cac5-ab23-477b-8794-672749a6155b","resolution":{"observed_at":"2026-07-31T13:03:57.839231Z","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":"2026-07-31T13:03:57.983116Z","title":"Knowledge graph-enhanced molecular contrastive learning with functional prompt","venue":null,"work_id":null,"year":2083},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:57.983116Z"},"links":{"citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:d7fdbfd9565fcfbb793326620ee79bbd5ec452980cc5a8752ad6339c08360ca0","observation_id":"97aa699e-a0c1-498a-b544-02091391b933","resolution":{"observed_at":"2026-07-31T13:03:57.983116Z","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":"2026-07-31T13:03:58.060063Z","title":"Gemnet: Universal directional graph neural networks for molecules.Advances in neural information processing systems, 34:6790–6802,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:58.060063Z"},"links":{"citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:ba64784de6b63c5d3ab8c87c8697a257b908dfdf93dc58985d2fb5ddcac977e2","observation_id":"2c57d62c-eaab-4131-b8e4-d901872c29a2","resolution":{"observed_at":"2026-07-31T13:03:58.060063Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.04738","last_updated":"2019-11-12T08:44:49Z","snapshot_observed_at":"2026-07-06T08:36:19.641682Z","submitted_at":"2019-11-12T08:44:49Z","title":"SMILES Transformer: Pre-trained Molecular Fingerprint for Low Data Drug Discovery","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.04738","snapshot_observed_at":"2026-07-31T13:03:58.134871Z","title":"Smiles transformer: Pre-trained molecular fingerprint for low data drug discovery.arXiv preprint arXiv:1911.04738,","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:58.134871Z"},"links":{"cited_paper":"/paper/1911.04738","citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:2bc41e93c565051390c88724cd68cf406d1d588212f96739fe97ac0ff5b15f0e","observation_id":"2eaa59e8-b1c0-4c98-9e94-754d07345010","resolution":{"observed_at":"2026-07-31T13:03:58.134871Z","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":"2026-07-31T13:03:58.218331Z","title":"N-gram graph: Simple unsupervised repre- sentation for graphs, with applications to molecules.Advances in neural information processing systems, 32,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:58.218331Z"},"links":{"citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:316d05a1dbda8aa4855f10407307fd6bda35da9e3e8f2d3560b92d00b8ee1d1c","observation_id":"04759d9b-ae74-4d96-aa00-41877c23942c","resolution":{"observed_at":"2026-07-31T13:03:58.218331Z","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":"2026-07-31T13:03:58.329322Z","title":"Pre- training molecular graph representation with 3d geometry","venue":null,"work_id":null,"year":2082},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:58.329322Z"},"links":{"citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:92ffa4eb1d5c798cbf6b5130edc6678db8a3352206e9a89655dd5e757e984bae","observation_id":"6038cb02-a14f-4af3-a550-dc21983a8b5a","resolution":{"observed_at":"2026-07-31T13:03:58.329322Z","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":"2026-07-31T13:03:58.392331Z","title":"Graph alignment kernels using weisfeiler and leman hierarchies","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:58.392331Z"},"links":{"citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:9a98b92d83dbc16fea547484a5630fe175efdd584aa98ab4be5e1ce7f5dc8cd7","observation_id":"1ebb8df8-4ffd-4528-b881-db41f2ddb9e4","resolution":{"observed_at":"2026-07-31T13:03:58.392331Z","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":"2026-07-31T13:03:58.733777Z","title":"Model-agnostic augmentation for accurate graph classification","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:58.733777Z"},"links":{"citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:1ecbf0838992440540a3ac7cb7ee072a3affbbd8e349dcd8012c6abef87ae56f","observation_id":"ec75895e-7682-4a1b-831e-b2f3fbef946f","resolution":{"observed_at":"2026-07-31T13:03:58.733777Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.05075","last_updated":"2024-03-08T05:59:56Z","snapshot_observed_at":"2026-07-06T17:41:27.341898Z","submitted_at":"2024-03-08T05:59:56Z","title":"Benchmarking Large Language Models for Molecule Prediction Tasks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.05075","snapshot_observed_at":"2026-07-31T13:03:58.807838Z","title":"Benchmarking large language models for molecule prediction tasks.arXiv:2403.05075,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:58.807838Z"},"links":{"cited_paper":"/paper/2403.05075","citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:d26ab31e9338c4ed2d730df65935956d5d080f527d2a810ce542f48266fb762a","observation_id":"a8a83674-d27f-441f-8051-32b201fefa98","resolution":{"observed_at":"2026-07-31T13:03:58.807838Z","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":"2026-07-31T13:03:59.113713Z","title":"Proof of Theorem 3.1.By Theorem 3.1, we have∥ bβk(G, f)− bβk(G, g)∥1 ≤C d B(M f k , Mg k )","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:59.113713Z"},"links":{"citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:2b694926538dfb1c432f12e377a8de5f48f92f967d508a0456378549491d3021","observation_id":"3d1439fc-ec3f-4990-8dd7-2259c5c0af82","resolution":{"observed_at":"2026-07-31T13:03:59.113713Z","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":"2026-07-31T13:03:59.226480Z","title":"A full expressivity comparison and formal information-loss bounds relative to complete barcodes are interesting directions for future work","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:59.226480Z"},"links":{"citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:665b3b58170b625cf1e3b67cf9038375789729cf4714340f1f2c682508b68c02","observation_id":"10dd812c-d785-4c85-8f80-fa0619408bd6","resolution":{"observed_at":"2026-07-31T13:03:59.226480Z","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":"2026-07-31T13:03:59.260788Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:59.260788Z"},"links":{"citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:22b2123f7c76e26a39ce2c1d53308e861025b8d69695caa42432c6ab7f13e165","observation_id":"dbb9ce11-f438-45e3-b2ee-24bf7742d16c","resolution":{"observed_at":"2026-07-31T13:03:59.260788Z","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":"2026-07-31T13:03:59.264497Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:59.264497Z"},"links":{"citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:29848bad2d29b347ff761debcbecff10991d986b19a9d3b523c085839fc4088f","observation_id":"fd435613-f503-4e6f-9278-7d31bf209c1b","resolution":{"observed_at":"2026-07-31T13:03:59.264497Z","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":"2026-07-31T13:03:58.908127Z","title":"They encode features such as atomic connectivity and substructural patterns, enabling efficient similarity search and predictive modeling","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":2005,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:58.908127Z"},"links":{"citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:a48fc089102c34cf64b8f0ed8e22332e5e5784eec6aabf9755a272eaa15af4c4","observation_id":"43b5177b-59bf-4f69-98cb-d0be611cacfa","resolution":{"observed_at":"2026-07-31T13:03:58.908127Z","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":"2026-07-31T13:03:57.549048Z","title":"Gabriele Corso, Luca Cavalleri, Dominique Beaini, Pietro Liò, and Petar Veli ˇckovi´c","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":2007,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:57.549048Z"},"links":{"citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:419f8a93387d7136a5404cbfe7f0c6186be7f7e361418952d075983b9b289e57","observation_id":"13c8c139-8db3-494f-9ce5-24c015c38f35","resolution":{"observed_at":"2026-07-31T13:03:57.549048Z","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":"2026-07-31T13:03:58.471544Z","title":"Self-supervised graph transformer on large-scale molecular data.Advances in neural information processing systems, 33:12559–12571,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":2010,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:58.471544Z"},"links":{"citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:942969297b008a81022266fad4398933e13acd295fba622ceb2f3bef4066e643","observation_id":"d50fe3c5-3adf-45ad-b1af-99a313fad336","resolution":{"observed_at":"2026-07-31T13:03:58.471544Z","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":"2026-07-31T13:03:57.467766Z","title":"Topogcl: Topological graph contrastive learning","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:57.467766Z"},"links":{"citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:4df1b4f356b9d1ef391e46bd423bd4c20a0988b258e86b1a06f9de95440958b3","observation_id":"f83e0b33-2095-4bdd-9305-06a1f9fe08c1","resolution":{"observed_at":"2026-07-31T13:03:57.467766Z","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":"2026-07-31T13:03:57.102684Z","title":"Persistence homology of networks: methods and applications.Applied Network Science, 4(1):1–28,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:57.102684Z"},"links":{"citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:d544a66786d2ac8f3e49bc47fe62305ccc532b82a3c693c75e589943ea328278","observation_id":"1a9afb99-1617-4407-b484-c15c43281efe","resolution":{"observed_at":"2026-07-31T13:03:57.102684Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.12712","last_updated":"2023-04-13T20:41:31Z","snapshot_observed_at":"2026-08-03T04:49:15.195814Z","submitted_at":"2023-03-22T16:51:28Z","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.12712","snapshot_observed_at":"2026-07-31T13:03:57.320195Z","title":"Sparks of artificial general intelligence: Early experiments with gpt-4.arXiv preprint arXiv:2303.12712,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:57.320195Z"},"links":{"cited_paper":"/paper/2303.12712","citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:9fdcc213fdd04cd7becf877aea820ceaa88b00ac70eaf78a214ab82e2e343633","observation_id":"8f6c591b-c469-4f51-a2ea-57790bffb2ca","resolution":{"observed_at":"2026-07-31T13:03:57.320195Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09703","last_updated":"2022-12-19T18:31:00Z","snapshot_observed_at":"2026-08-05T21:12:55.079779Z","submitted_at":"2022-12-19T18:31:00Z","title":"A Survey of Vectorization Methods in Topological Data Analysis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.09703","snapshot_observed_at":"2026-07-31T13:03:57.180296Z","title":"A survey of vectorization methods in topological data analysis.arXiv preprint arXiv:2212.09703,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:57.180296Z"},"links":{"cited_paper":"/paper/2212.09703","citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:bfecb72614dae78d553f605dd3cab027b5038af499c8f85dcd7a6ff6040157a5","observation_id":"f83b6bfd-d236-4c63-9180-20215016f354","resolution":{"observed_at":"2026-07-31T13:03:57.180296Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.02901","last_updated":"2024-09-04T17:44:52Z","snapshot_observed_at":"2026-08-05T19:05:38.901392Z","submitted_at":"2024-09-04T17:44:52Z","title":"Topological Methods in Machine Learning: A Tutorial for Practitioners","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.02901","snapshot_observed_at":"2026-07-31T13:03:57.649989Z","title":"Topological methods in machine learning: A tutorial for practitioners.arXiv preprint arXiv:2409.02901,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:57.649989Z"},"links":{"cited_paper":"/paper/2409.02901","citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:a5cede489e38ea06009e885f0163114de17deecf0c916956dcce8d4f9ee6f3f8","observation_id":"fe88b643-8279-4b1a-a692-27778b178665","resolution":{"observed_at":"2026-07-31T13:03:57.649989Z","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":"2026-07-31T13:03:58.652971Z","title":"Moleculenet: a benchmark for molecular machine learning","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:58.652971Z"},"links":{"citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:6462bbc99d20709aa3598e3c0283db669bdff93ff7c1a688459903d2b8f8fb1b","observation_id":"468d2223-3f77-4827-a6e1-53cb2fa0fe3a","resolution":{"observed_at":"2026-07-31T13:03:58.652971Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.04805","last_updated":"2019-05-24T20:37:26Z","snapshot_observed_at":"2026-07-30T09:12:38.100527Z","submitted_at":"2018-10-11T00:50:01Z","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.04805","snapshot_observed_at":"2026-07-31T13:03:57.769769Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding.arXiv preprint arXiv:1810.04805,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:57.769769Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:62fb93d7aef69825ecfa3b883fca41155ec384dffdebb389e97def353690b5a5","observation_id":"07895a90-a6fa-4741-9bb8-f9632435a00c","resolution":{"observed_at":"2026-07-31T13:03:57.769769Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.06058","last_updated":"2020-01-16T20:13:20Z","snapshot_observed_at":"2026-08-05T10:57:39.822514Z","submitted_at":"2020-01-16T20:13:20Z","title":"Understanding the Power of Persistence Pairing via Permutation Test","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.06058","snapshot_observed_at":"2026-07-31T13:03:57.391927Z","title":"Understanding the power of persistence pairing via permutation test.arXiv preprint arXiv:2001.06058,","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:57.391927Z"},"links":{"cited_paper":"/paper/2001.06058","citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:ebef0ecb5309d3e8dac80fc39546836f772655c5dd4e01a8764065422463ae7d","observation_id":"de461a17-c40a-429e-bad5-bce6072b383e","resolution":{"observed_at":"2026-07-31T13:03:57.391927Z","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":"2026-07-31T13:03:57.712185Z","title":"Ripsnet: a general architecture for fast and robust estimation of the persistent homology of point clouds","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:57.712185Z"},"links":{"citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:8913c9338e891e396704fb44da26774b8272830125ba6ed78038ef3bb774b8aa","observation_id":"44281ec1-6e16-47ce-89b2-4c0072140766","resolution":{"observed_at":"2026-07-31T13:03:57.712185Z","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":"2026-07-31T13:03:58.576970Z","title":"Communicative representation learning on attributed molecular graphs","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-07-31T13:03:58.576970Z"},"links":{"citing_paper":"/paper/2607.28259"},"observation_digest":"sha256:2174f4fb15cce8223244658a2ab462cec94f78152ab8158a936bab0e8dc44bf0","observation_id":"f0b29cb3-7a0f-4663-824b-e55d60145314","resolution":{"observed_at":"2026-07-31T13:03:58.576970Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.28259","last_updated":"2026-07-30T14:18:17Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T09:17:00.360416Z","submitted_at":"2026-07-30T14:18:17Z","title":"TopoFormer: Topology Meets Attention for Graph Learning"},"reference_resolution":{"displayed":30,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":30,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":30},"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 30 of 30 outbound references and 0 inbound Pith citation observations for arXiv:2607.28259."}