{"as_of":"2026-08-23T01:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:958097ff52f65a0365ca5ff2a546d8739d61270fe0d11702d3892007b49eb539","coverage":[{"denominator":51,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":51,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T22:40:48.890066Z","state":"measured"},{"denominator":56,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":56,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+00:00","state":"measured"},{"denominator":5,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":5,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T05:19:22.557090Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-18T04:33:39.707945Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"cited_work":{"arxiv_id":"2501.01073","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.01073","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Graph generative pre-trained transformer","venue":null,"work_id":"514baaeb-3b63-46b3-b9b9-5dca2ff0feb4","year":2025},"citing_paper":{"arxiv_id":"2501.00309","last_updated":"2025-01-08T05:16:25Z","snapshot_observed_at":"2026-08-15T15:30:31.504538Z","submitted_at":"2024-12-31T06:59:35Z","title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-05-18T04:33:39.076517Z"},"links":{"cited_paper":"/paper/2501.01073","citing_paper":"/paper/2501.00309"},"observation_digest":"sha256:ae0bcc8a2f40098406f2f1e0ee3f73db19b335e3cad4273e790694c1b7169be9","observation_id":"d6b6c42f-52d2-4653-88a4-9954926f7595","resolution":{"observed_at":"2026-05-18T04:33:39.710198Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.01073","snapshot_observed_at":"2026-08-09T05:19:22.557090Z","title":"Graph Generative Pre-trained Transformer,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2502.03300","last_updated":"2026-05-31T05:26:33Z","snapshot_observed_at":"2026-08-11T02:32:49.186494Z","submitted_at":"2025-02-05T15:58:44Z","title":"Scalable Interference Graph Learning for Low-Latency Wi-Fi Networks using Hashing-based Evolution Strategy","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-09T05:19:22.557090Z"},"links":{"cited_paper":"/paper/2501.01073","citing_paper":"/paper/2502.03300"},"observation_digest":"sha256:b4c85acd59aa343c1bc3273ff6ea6e5b71a194878b0d047543bf22616f0c1a16","observation_id":"8ba94831-589c-4d53-afad-4d56b21ee336","resolution":{"observed_at":"2026-08-09T05:19:22.557090Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.01073","snapshot_observed_at":"2026-08-06T16:36:20.663823Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.13133","last_updated":"2025-07-17T13:54:42Z","snapshot_observed_at":"2026-08-17T04:17:28.450747Z","submitted_at":"2025-07-17T13:54:42Z","title":"NGTM: Substructure-based Neural Graph Topic Model for Interpretable Graph Generation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T16:36:20.663823Z"},"links":{"cited_paper":"/paper/2501.01073","citing_paper":"/paper/2507.13133"},"observation_digest":"sha256:2549671fc9ccbf2cf20d17a389c9156bbd7634d168b014c308dee860d4e875d5","observation_id":"872c7629-18d2-41f9-a0b2-08e5cd8a4d13","resolution":{"observed_at":"2026-08-06T16:36:20.663823Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.01073","snapshot_observed_at":"2026-08-06T13:08:45.370911Z","title":"Graph generative pre-trained transformer, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.20967","last_updated":"2025-07-28T16:22:50Z","snapshot_observed_at":"2026-08-20T11:17:46.398480Z","submitted_at":"2025-07-28T16:22:50Z","title":"PROVCREATOR: Synthesizing Complex Heterogenous Graphs with Node and Edge Attributes","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-06T13:08:45.370911Z"},"links":{"cited_paper":"/paper/2501.01073","citing_paper":"/paper/2507.20967"},"observation_digest":"sha256:bca38d44c10147d68a80a440149bc4ac953a69ad93d87e2e05af2a655ebec93e","observation_id":"3f37a9e1-242d-4686-88ea-e879bcb27e1a","resolution":{"observed_at":"2026-08-06T13:08:45.370911Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"cited_work":{"arxiv_id":"2501.01073","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.01073","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Graph generative pre-trained transformer","venue":null,"work_id":"514baaeb-3b63-46b3-b9b9-5dca2ff0feb4","year":2025},"citing_paper":{"arxiv_id":"2604.10332","last_updated":"2026-04-11T19:31:18Z","snapshot_observed_at":"2026-08-15T15:11:45.305317Z","submitted_at":"2026-04-11T19:31:18Z","title":"From GPT-3 to GPT-5: Mapping their capabilities, scope, limitations, and consequences","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-10T15:16:06.526626Z"},"links":{"cited_paper":"/paper/2501.01073","citing_paper":"/paper/2604.10332"},"observation_digest":"sha256:878882786f3646102df9857fdd3fc6903253f1d2a7fc1a3c13b0395eafe19c61","observation_id":"aad9949d-f8a7-4d1b-9944-8563c10a8c7c","resolution":{"observed_at":"2026-05-11T10:56:04.601347Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2501.01073/citation-record","integrity":"/paper/2501.01073/integrity","json":"/paper/2501.01073/citation-record.json","paper":"/paper/2501.01073"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-17T09:58:46.058102Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-10T22:40:48.695114Z","title":"L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S., et al","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.695114Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:19abf40bc831c4f1f4c52b35e521cf1e6edbe52b12ad52100a6a34343568ec0d","observation_id":"25b99da7-9f04-46fa-8f9f-9456730d3cf5","resolution":{"observed_at":"2026-08-10T22:40:48.695114Z","resolver_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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:40:49.384999Z","title":"Among them, GRAN (Liao et al., 2019), BiGG (Dai et al., 2020), and BwR (Diamant et al.,","venue":null,"work_id":"9b3ba06b-6cea-422f-a8fe-33336df61208","year":2019},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.862939Z"},"links":{"citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:cadfebd4a9dab0f546dca5a0816550c5dd779716dbc1aca64b644354b89275ea","observation_id":"2aaf97d5-781c-4aa9-8bfa-af71a8f1d69e","resolution":{"observed_at":"2026-08-10T22:40:49.388932Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.06189","last_updated":"2021-06-14T09:51:52Z","snapshot_observed_at":"2026-08-16T18:17:53.666351Z","submitted_at":"2021-06-11T06:37:52Z","title":"Order Matters: Probabilistic Modeling of Node Sequence for Graph Generation","version":2},"cited_work":{"arxiv_id":"2106.06189","doi":null,"metadata_source":"pith","pith_arxiv_id":"2106.06189","snapshot_observed_at":"2026-08-10T22:40:49.250282Z","title":"Order Matters: Probabilistic Modeling of Node Sequence for Graph Generation","venue":"stat.ML","work_id":"2eb1b98e-8172-4bb6-8bfb-caa68d29d231","year":2021},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.716145Z"},"links":{"cited_paper":"/paper/2106.06189","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:7a63c034c6a9dfa1ccae8dd5780812a7d2d3101c7a3a5b21c93eb84ad1198b97","observation_id":"fb8377de-b8f5-4c12-a075-71f074135b4d","resolution":{"observed_at":"2026-08-10T22:40:49.254845Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1805.11973","last_updated":"2022-09-27T10:04:29Z","snapshot_observed_at":"2026-08-18T21:41:18.108090Z","submitted_at":"2018-05-30T13:56:06Z","title":"MolGAN: An implicit generative model for small molecular graphs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.11973","snapshot_observed_at":"2026-08-10T22:40:48.726135Z","title":"and Kipf, T","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.726135Z"},"links":{"cited_paper":"/paper/1805.11973","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:9a3c8685119ef312ba3affabd2d7d899afb65f9b1b782598e2e0694a373bd12b","observation_id":"93f5b092-0c62-407f-b0a3-86903de4bbe8","resolution":{"observed_at":"2026-08-10T22:40:48.726135Z","resolver_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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:40:49.310844Z","title":"2024; Xu et al., 2024; Wang et al.,","venue":null,"work_id":"34b1a3a8-663c-40ca-b89c-73e73c1daa44","year":2024},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.886079Z"},"links":{"citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:82de0142e83d450d28d23b4dc4aec7fe0ed55d4b43a9745478172d8015b2dbc5","observation_id":"fe5d4c77-8f04-4f44-8136-9be5457de179","resolution":{"observed_at":"2026-08-10T22:40:49.315086Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-08-13T17:20:44.002518Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-10T22:40:48.737524Z","title":"The llama 3 herd of models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.737524Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:9c027ca2456742b2f2af365a0c425d59054ebb3e95df3f752621bcd4607c15cc","observation_id":"c3b66e5c-e7fd-49c1-9334-1eb240b2cbfa","resolution":{"observed_at":"2026-08-10T22:40:48.737524Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.09699","last_updated":"2021-01-24T09:38:54Z","snapshot_observed_at":"2026-08-17T09:51:04.568396Z","submitted_at":"2020-12-17T16:11:47Z","title":"A Generalization of Transformer Networks to Graphs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.09699","snapshot_observed_at":"2026-08-10T22:40:48.740743Z","title":null,"venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.740743Z"},"links":{"cited_paper":"/paper/2012.09699","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:eff007e0e61ffba8e16fe1e3fd37620e198db1aae0fc6d0c3cf5538e231f26c5","observation_id":"09ecd560-f9cc-4358-8800-978cedcfab5e","resolution":{"observed_at":"2026-08-10T22:40:48.740743Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04843","last_updated":"2025-08-15T21:12:02Z","snapshot_observed_at":"2026-08-21T13:42:56.699433Z","submitted_at":"2024-06-07T11:16:17Z","title":"Variational Flow Matching for Graph Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04843","snapshot_observed_at":"2026-08-10T22:40:48.744137Z","title":"A., Welling, M., and van de Meent, J.-W","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.744137Z"},"links":{"cited_paper":"/paper/2406.04843","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:dc90b7edc11161c9fc9118b7e674106dc0f9908886cbc14d66a5f64821fdab4e","observation_id":"1db7f8be-f44b-4c24-b8d6-0015c7bc6705","resolution":{"observed_at":"2026-08-10T22:40:48.744137Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.02464","last_updated":"2024-05-29T05:40:35Z","snapshot_observed_at":"2026-08-16T14:21:43.381852Z","submitted_at":"2024-02-04T12:29:40Z","title":"A Graph is Worth $K$ Words: Euclideanizing Graph using Pure Transformer","version":3},"cited_work":{"arxiv_id":"2402.02464","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.02464","snapshot_observed_at":"2026-08-10T22:40:49.161193Z","title":"A Graph is Worth $K$ Words: Euclideanizing Graph using Pure Transformer","venue":"cs.LG","work_id":"038a6df1-58bf-495a-82cb-2910dbe9fad5","year":2024},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.747068Z"},"links":{"cited_paper":"/paper/2402.02464","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:0c855999a7db0ab22a30158a757113a6fac883a0883e6185fc128be91b58caa3","observation_id":"4533980d-781c-4596-b441-e27057a2362c","resolution":{"observed_at":"2026-08-10T22:40:49.164567Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.15595","last_updated":"2024-11-05T10:02:42Z","snapshot_observed_at":"2026-08-18T16:00:48.631131Z","submitted_at":"2024-07-22T12:33:27Z","title":"Discrete Flow Matching","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.15595","snapshot_observed_at":"2026-08-10T22:40:48.750268Z","title":"T., Syn- naeve, G., Adi, Y ., and Lipman, Y","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.750268Z"},"links":{"cited_paper":"/paper/2407.15595","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:14a39dd18187e4da732b329d15030831f28aa7bb217110f879d2283a000c3c63","observation_id":"61b63783-4eb6-4155-9549-dc8438549a51","resolution":{"observed_at":"2026-08-10T22:40:48.750268Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.01549","last_updated":"2023-08-15T23:10:57Z","snapshot_observed_at":"2026-08-16T16:27:03.272185Z","submitted_at":"2022-10-04T12:20:21Z","title":"Diffusion Models for Graphs Benefit From Discrete State Spaces","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.01549","snapshot_observed_at":"2026-08-10T22:40:48.753126Z","title":"K., Martinkus, K., Perraudin, N., and Wat- tenhofer, R","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.753126Z"},"links":{"cited_paper":"/paper/2210.01549","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:dc0216247cc1c7229be5fb5a42e87c2c5fa09f323f51e4c5096ff6da227c718b","observation_id":"cd5057d6-dc73-476c-b1d3-00b5e75e7ab4","resolution":{"observed_at":"2026-08-10T22:40:48.753126Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.10803","last_updated":"2022-07-13T13:53:31Z","snapshot_observed_at":"2026-08-20T03:46:06.803837Z","submitted_at":"2022-05-22T11:57:08Z","title":"GraphMAE: Self-Supervised Masked Graph Autoencoders","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.10803","snapshot_observed_at":"2026-08-10T22:40:48.756403Z","title":"Graphmae: Self-supervised masked graph autoencoders","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.756403Z"},"links":{"cited_paper":"/paper/2205.10803","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:ff4e8d75f9940535f9706d6047b51a443d190e903c50aa2379e61a57e4b5e4c8","observation_id":"81b47bd7-9d2f-45f5-9461-8bb1934de629","resolution":{"observed_at":"2026-08-10T22:40:48.756403Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.02230","last_updated":"2024-07-30T00:56:40Z","snapshot_observed_at":"2026-08-16T14:38:00.657671Z","submitted_at":"2023-12-04T03:43:26Z","title":"A Simple and Scalable Representation for Graph Generation","version":3},"cited_work":{"arxiv_id":"2312.02230","doi":null,"metadata_source":"pith","pith_arxiv_id":"2312.02230","snapshot_observed_at":"2026-08-10T22:40:49.119787Z","title":"A Simple and Scalable Representation for Graph Generation","venue":"cs.LG","work_id":"0ff156bb-ce79-4d7a-b392-1ddefc81d6cf","year":2023},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.760269Z"},"links":{"cited_paper":"/paper/2312.02230","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:90d99299abac02c598f8374675277e2b4c9bff3f63b06f1ca92feb47c056c0f1","observation_id":"3755a571-ad2a-40ec-a708-d3d4f204eee3","resolution":{"observed_at":"2026-08-10T22:40:49.123720Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.02514","last_updated":"2022-06-15T07:50:10Z","snapshot_observed_at":"2026-08-19T19:04:39.883272Z","submitted_at":"2022-02-05T08:21:04Z","title":"Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.02514","snapshot_observed_at":"2026-08-10T22:40:48.763395Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.763395Z"},"links":{"cited_paper":"/paper/2202.02514","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:5a8a10242e413925894ad5f70912de013aabe651a4d6706197026524d933034c","observation_id":"9d269ea7-d74f-433d-83ea-7f3c1ccb56c6","resolution":{"observed_at":"2026-08-10T22:40:48.763395Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.03324","last_updated":"2018-03-08T22:20:00Z","snapshot_observed_at":"2026-08-14T19:37:59.979230Z","submitted_at":"2018-03-08T22:20:00Z","title":"Learning Deep Generative Models of Graphs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.03324","snapshot_observed_at":"2026-08-10T22:40:48.766871Z","title":"Learning deep generative models of graphs","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.766871Z"},"links":{"cited_paper":"/paper/1803.03324","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:4a7f2aad547e299289f84d96a2549e6c47d0c0849c06f1755583b33cfb22f453","observation_id":"706279e6-4e0b-4898-bb97-b00b6d86e0ce","resolution":{"observed_at":"2026-08-10T22:40:48.766871Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.02747","last_updated":"2023-02-08T15:46:05Z","snapshot_observed_at":"2026-08-16T02:30:42.660030Z","submitted_at":"2022-10-06T08:32:20Z","title":"Flow Matching for Generative Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.02747","snapshot_observed_at":"2026-08-10T22:40:48.770585Z","title":"T., Ben-Hamu, H., Nickel, M., and Le, M","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.770585Z"},"links":{"cited_paper":"/paper/2210.02747","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:f338ebf1bec3cbff6504c94b64ea8ea4545641c400dc0091d121e6691d755ee0","observation_id":"3eb34eae-54b7-4228-b0e4-15978832622c","resolution":{"observed_at":"2026-08-10T22:40:48.770585Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.07728","last_updated":"2022-05-29T13:01:37Z","snapshot_observed_at":"2026-08-20T14:06:16.950698Z","submitted_at":"2021-10-07T17:48:57Z","title":"Pre-training Molecular Graph Representation with 3D Geometry","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.07728","snapshot_observed_at":"2026-08-10T22:40:48.774312Z","title":"Pre-training molecular graph representation with 3d geometry, 2022a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.774312Z"},"links":{"cited_paper":"/paper/2110.07728","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:784ddcf4734671ba3333d163fdf7995a294922d4317eb2197dd7f1e13c528948","observation_id":"8f9c6fd4-8105-4b9a-aadd-6a5a19d6e4b4","resolution":{"observed_at":"2026-08-10T22:40:48.774312Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-14T20:13:52.872565Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-10T22:40:48.778033Z","title":"Luo, Y ., Yan, K., and Ji, S","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.778033Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:4c2250d9cdd2ce663b160ae427edf007794e52478e5cb1a5d6eaaa53a570d1dc","observation_id":"a11d659e-d222-4924-8468-53926bf8cd5c","resolution":{"observed_at":"2026-08-10T22:40:48.778033Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1905.11600","last_updated":"2019-05-28T04:13:23Z","snapshot_observed_at":"2026-08-14T16:25:29.394963Z","submitted_at":"2019-05-28T04:13:23Z","title":"GraphNVP: An Invertible Flow Model for Generating Molecular Graphs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.11600","snapshot_observed_at":"2026-08-10T22:40:48.782009Z","title":"Graph- nvp: An invertible flow model for generating molecular graphs","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.782009Z"},"links":{"cited_paper":"/paper/1905.11600","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:5950768422b105e4c253f9e60ab5c93726c82df82258b1fe20dd56435fe91413","observation_id":"53740c6a-169b-4d56-9b00-dcb9c977d99d","resolution":{"observed_at":"2026-08-10T22:40:48.782009Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.01613","last_updated":"2022-06-18T20:12:16Z","snapshot_observed_at":"2026-08-16T17:09:25.582136Z","submitted_at":"2022-04-04T16:08:17Z","title":"SPECTRE: Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generators","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.01613","snapshot_observed_at":"2026-08-10T22:40:48.785954Z","title":"Min, E., Chen, R., Bian, Y ., Xu, T., Zhao, K., Huang, W., Zhao, P., Huang, J., Ananiadou, S., and Rong, Y","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.785954Z"},"links":{"cited_paper":"/paper/2204.01613","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:f53c0145a512aece6b20dbe1034c357fccf6a3d449009c818d8e1ceb87900b96","observation_id":"287f9687-485f-4e53-ab5b-faef77f6fc2d","resolution":{"observed_at":"2026-08-10T22:40:48.785954Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1811.12823","last_updated":"2020-10-28T14:11:16Z","snapshot_observed_at":"2026-08-21T08:24:48.559085Z","submitted_at":"2018-11-29T08:48:20Z","title":"Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.12823","snapshot_observed_at":"2026-08-10T22:40:48.790015Z","title":"Preuer, K., Renz, P., Unterthiner, T., Hochreiter, S., and Klambauer, G","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.790015Z"},"links":{"cited_paper":"/paper/1811.12823","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:121367cce7c74ee54c7340bbabab96ffc55642e43e905905d50bda9de20e2886","observation_id":"020825da-7d3c-4489-a5bc-d35886933443","resolution":{"observed_at":"2026-08-10T22:40:48.790015Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.09518","last_updated":"2018-08-01T14:20:53Z","snapshot_observed_at":"2026-08-18T18:18:25.352476Z","submitted_at":"2018-03-26T11:36:24Z","title":"Fr\\'echet ChemNet Distance: A metric for generative models for molecules in drug discovery","version":3},"cited_work":{"arxiv_id":"1803.09518","doi":null,"metadata_source":"pith","pith_arxiv_id":"1803.09518","snapshot_observed_at":"2026-08-10T22:40:49.025480Z","title":"Fr\\'echet ChemNet Distance: A metric for generative models for molecules in drug discovery","venue":"cs.LG","work_id":"a15029fb-e690-4915-8b80-3462fad8f164","year":2018},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.793832Z"},"links":{"cited_paper":"/paper/1803.09518","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:c50371e437be5d2ffa066c9c7561f79399ae578a15640216300757590a1c9450","observation_id":"6affaa0b-1d1a-4109-a0ba-0348ea5e3451","resolution":{"observed_at":"2026-08-10T22:40:49.031481Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.04263","last_updated":"2025-06-15T21:08:59Z","snapshot_observed_at":"2026-08-16T13:12:16.692775Z","submitted_at":"2024-10-05T18:52:54Z","title":"DeFoG: Discrete Flow Matching for Graph Generation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.04263","snapshot_observed_at":"2026-08-10T22:40:48.797314Z","title":"Radford, A","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.797314Z"},"links":{"cited_paper":"/paper/2410.04263","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:ba55ca15badd4b13d97e6ba9f81263b857f4ea93b88ca37545015b040f11a1cb","observation_id":"26ef5aa0-539c-4f1b-9357-68e0e3153ed6","resolution":{"observed_at":"2026-08-10T22:40:48.797314Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1506.02438","last_updated":"2018-10-20T18:55:07Z","snapshot_observed_at":"2026-08-15T05:06:05.489107Z","submitted_at":"2015-06-08T11:12:48Z","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1506.02438","snapshot_observed_at":"2026-08-10T22:40:48.801291Z","title":"High-dimensional continuous control using generalized advantage estimation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.801291Z"},"links":{"cited_paper":"/paper/1506.02438","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:6b6cf269f4ae8624de6b043e37a8d2575f5c65012e31e2d6c48bd78dec7e1727","observation_id":"ecb31092-e840-4a34-8854-1d655b1f8be9","resolution":{"observed_at":"2026-08-10T22:40:48.801291Z","resolver_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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:40:49.469297Z","title":"and Komodakis, N","venue":null,"work_id":"a1e17026-289b-4f14-a8ef-0f3a3e8fc6fd","year":2018},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.809377Z"},"links":{"citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:e584112d749cf745866e345acb3baadec257ec1bbef2729dfd7ae18bbf2ff416","observation_id":"804966e8-c8e8-428a-bf15-db9f09bb2602","resolution":{"observed_at":"2026-08-10T22:40:49.473319Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.06449","last_updated":"2024-10-04T09:45:39Z","snapshot_observed_at":"2026-08-19T21:05:10.811449Z","submitted_at":"2024-06-10T16:39:39Z","title":"Cometh: A continuous-time discrete-state graph diffusion model","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.06449","snapshot_observed_at":"2026-08-10T22:40:48.812700Z","title":"D., and Morris, C","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.812700Z"},"links":{"cited_paper":"/paper/2406.06449","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:e3be7ed1f0cbdc19391c6a1b46fada9de786acd66bf84dbbfdafef1ddd2a9dea","observation_id":"f7db2c65-4c29-4b69-b643-b7ff1138b7a1","resolution":{"observed_at":"2026-08-10T22:40:48.812700Z","resolver_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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:40:49.457803Z","title":null,"venue":null,"work_id":"f8d4c543-6307-45ef-88f6-7a3723ded8c4","year":1908},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.816760Z"},"links":{"citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:ed36354f4813e415ea3ded599aac4370ebf42ae3cab7a1b3303e8617cc4ceeb3","observation_id":"79492091-46d7-4ea6-90da-6cb618fef51d","resolution":{"observed_at":"2026-08-10T22:40:49.461719Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.00564","last_updated":"2018-10-26T00:52:38Z","snapshot_observed_at":"2026-08-19T04:02:14.412485Z","submitted_at":"2017-03-02T00:39:53Z","title":"MoleculeNet: A Benchmark for Molecular Machine Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.00564","snapshot_observed_at":"2026-08-10T22:40:48.828788Z","title":"N., Gomes, J., Ge- niesse, C., Pappu, A","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.828788Z"},"links":{"cited_paper":"/paper/1703.00564","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:c425ed9b92d1ba47579e1fe6d81fc08851bdcf8a6b81c97275292076437eb97a","observation_id":"07653694-7029-4ae4-84d7-0978f1c0e1a7","resolution":{"observed_at":"2026-08-10T22:40:48.828788Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.11416","last_updated":"2024-11-04T02:19:26Z","snapshot_observed_at":"2026-08-19T16:34:41.319281Z","submitted_at":"2024-05-19T00:09:42Z","title":"Discrete-state Continuous-time Diffusion for Graph Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.11416","snapshot_observed_at":"2026-08-10T22:40:48.832953Z","title":"Discrete-state continuous- time diffusion for graph generation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.832953Z"},"links":{"cited_paper":"/paper/2405.11416","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:de22b1a45801d2ec76471316724a438c3afd851a67125a36b341257895a07337","observation_id":"d469a268-fc16-4ccd-84d1-8f450740a246","resolution":{"observed_at":"2026-08-10T22:40:48.832953Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.13902","last_updated":"2021-04-03T15:34:00Z","snapshot_observed_at":"2026-08-17T01:29:59.811413Z","submitted_at":"2020-10-22T20:13:43Z","title":"Graph Contrastive Learning with Augmentations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.13902","snapshot_observed_at":"2026-08-10T22:40:48.836636Z","title":null,"venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.836636Z"},"links":{"cited_paper":"/paper/2010.13902","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:50f31821d8438e08d9eea68a9f7f7259b5c037087aaa39954c2714958be02cc7","observation_id":"71032502-6f1f-46d5-81e1-33d6559571bb","resolution":{"observed_at":"2026-08-10T22:40:48.836636Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.04964","last_updated":"2023-07-18T08:44:47Z","snapshot_observed_at":"2026-08-16T10:37:13.463130Z","submitted_at":"2023-07-11T01:55:24Z","title":"Secrets of RLHF in Large Language Models Part I: PPO","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.04964","snapshot_observed_at":"2026-08-10T22:40:48.840262Z","title":"Secrets of rlhf in large language models part i: Ppo","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.840262Z"},"links":{"cited_paper":"/paper/2307.04964","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:ab92a1dd51aa03fb22bbad61e7ec2549154cc068f65d416e4b4bfdc7f267aaad","observation_id":"f044fccd-72fc-4a91-a2c2-9fb108d29807","resolution":{"observed_at":"2026-08-10T22:40:48.840262Z","resolver_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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:40:49.445112Z","title":"falls off the grid","venue":null,"work_id":"463524a0-2e2a-4dd2-abcb-44271066bda6","year":2023},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.843982Z"},"links":{"citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:79d8720adf853f1b5decc0aebdf66baaa6652fac9e3bebf6e8f7c4115d8c49e2","observation_id":"f836c5ef-7abd-464f-b1f5-bad922cc63db","resolution":{"observed_at":"2026-08-10T22:40:49.449104Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:40:49.432521Z","title":null,"venue":null,"work_id":"82321c5d-f8c5-4d7d-b575-935309bc9b62","year":2000},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.847990Z"},"links":{"citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:797d7215d3bb295c1b90dbbb9298bfb825661560e2858e3fe8d0b0e70f4d62ae","observation_id":"4ef26080-1b52-40cc-afe2-5b741d73f991","resolution":{"observed_at":"2026-08-10T22:40:49.436014Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:40:49.421745Z","title":"Training transformers on adjacency matrices","venue":null,"work_id":"6a5f15d5-e78c-4d8b-b651-4b37c0513c8d","year":2021},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.852103Z"},"links":{"citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:fa88b7d266827406580dd911e8f4f2fac3d0c9769864393866d48f608e7b5045","observation_id":"dea675d3-d91b-46f4-aee6-2524d1b62afa","resolution":{"observed_at":"2026-08-10T22:40:49.425208Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:40:49.410006Z","title":null,"venue":null,"work_id":"e718f4f6-4e4f-4798-8fdb-e9577d712596","year":2022},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.856096Z"},"links":{"citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:a58466fc1d512f237f974cc6b5653eed5981eab8cc8658d6007fb316eceb7308","observation_id":"4a405e4f-7053-4fae-89ca-a8c26476cc2b","resolution":{"observed_at":"2026-08-10T22:40:49.413908Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:40:49.397233Z","title":"Fine-tuning G2PT for Graph Property Prediction Datasets","venue":null,"work_id":"ae5ede57-df5a-405f-848c-c760fc4fda28","year":2024},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.859546Z"},"links":{"citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:fa9a55ed7e415a8e5e89b6ba18d729e4bfa2a4fdf99433ab5a6177d7e26af48a","observation_id":"853a68df-9038-4a6f-bab5-9c193746d8eb","resolution":{"observed_at":"2026-08-10T22:40:49.401367Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:40:49.373084Z","title":null,"venue":null,"work_id":"60403ae8-da34-4bcd-abf1-b430937b5c4a","year":2022},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.867432Z"},"links":{"citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:08bf551c7a3eb93fa5530503713d1e776f750f829a19ff023df5578cf6a9d597","observation_id":"9318ddc5-5300-4b42-9d27-5e4700be6367","resolution":{"observed_at":"2026-08-10T22:40:49.377245Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:40:49.360170Z","title":"The dataset-agnostic metrics evaluate the alignment between the distributions of the generated graphs and the training data by analyzing general graph properties","venue":null,"work_id":"f534418a-3cb4-4b66-a71a-77043fb4d473","year":2024},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.871007Z"},"links":{"citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:197d70cdfb465331c1043e5e1e89d074802edc5897dad412e33f5db60d5aba81","observation_id":"a81baf9e-93de-48d9-84cf-9b8844223778","resolution":{"observed_at":"2026-08-10T22:40:49.364873Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:40:49.347106Z","title":"On the contrary, 19 Graph Generative Pre-trained Transformer Algorithm 4 Depth-First search edge order generation Input: Graph G = (V, E), neighborhood function Nei.(·)","venue":null,"work_id":"6a930521-ba50-4ebf-a578-0fbcc565bbc3","year":2020},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.874714Z"},"links":{"citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:b6a2768de55aa629bace170ef2d3ec56bc9bbc0d0f4a44ec39825e084afa1fda","observation_id":"37d538d2-3e0b-4df1-a169-7fcbfe3e4543","resolution":{"observed_at":"2026-08-10T22:40:49.351320Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:40:49.335246Z","title":null,"venue":null,"work_id":"724f5581-af9e-4a0a-aaa5-71640e38057e","year":2018},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.878258Z"},"links":{"citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:8f70b0d0b25581c4e7263129cb582837c71d15561cd68c00b004403020db25b4","observation_id":"484a5310-25f8-4a53-82f0-4d3d46026d02","resolution":{"observed_at":"2026-08-10T22:40:49.339134Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:40:49.322822Z","title":"Nevertheless, one-shot graph generative models often suffer from the decoding strategies such that it requires an expressive decoder to map from latent vectors to graphs","venue":null,"work_id":"847b82ae-ffd0-4d88-895c-fea8418f5864","year":2019},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.881780Z"},"links":{"citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:fcb3a79091b75b1a88b774622aee9b2c84a57a7146a543067be9a93e56f90bcb","observation_id":"0ad6128d-49a6-4065-8033-fbba20b60558","resolution":{"observed_at":"2026-08-10T22:40:49.327282Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:40:49.298455Z","title":"As discussed in ??, they often require a prefixed number of refinement steps and they need to maintain an adjacency matrix over the trajectory which is computationally intensive","venue":null,"work_id":"7f9f1706-cd59-4ac9-a35c-0f83eef2fae7","year":2022},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.890066Z"},"links":{"citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:3f555505b8dd953dcb52d282c7a83e8131e3d34ee8773157eedfa6b044ba2e98","observation_id":"8b14de12-47ee-43c6-963d-d97a70608801","resolution":{"observed_at":"2026-08-10T22:40:49.302837Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1707.06347","last_updated":"2017-08-28T09:20:06Z","snapshot_observed_at":"2026-08-20T07:04:06.309989Z","submitted_at":"2017-07-20T02:32:33Z","title":"Proximal Policy Optimization Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.06347","snapshot_observed_at":"2026-08-10T22:40:48.805012Z","title":"Proximal policy optimization algorithms","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.805012Z"},"links":{"cited_paper":"/paper/1707.06347","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:6c8eca400d779378213d12a70a3386fe0e3325fa7c90eb0e60235196539513e3","observation_id":"6faf5744-2260-4448-9d07-be16af9db3f4","resolution":{"observed_at":"2026-08-10T22:40:48.805012Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.14734","last_updated":"2023-05-23T10:32:08Z","snapshot_observed_at":"2026-08-20T09:43:26.374154Z","submitted_at":"2022-09-29T12:55:03Z","title":"DiGress: Discrete Denoising diffusion for graph generation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.14734","snapshot_observed_at":"2026-08-10T22:40:48.820863Z","title":"Digress: Discrete denoising diffusion for graph generation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.820863Z"},"links":{"cited_paper":"/paper/2209.14734","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:644a5d6ca3921cc9e4b4e2088c7fb43f6c03187b65e0f0fb564b73b31dfe07b8","observation_id":"3b19083e-3c99-4a35-bf3a-98fc9101d4d1","resolution":{"observed_at":"2026-08-10T22:40:48.820863Z","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":"2026-08-14T18:16:28.847993Z","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":"2026-08-10T22:40:48.730274Z","title":"Bert: Pre-training of deep bidirectional trans- formers for language understanding","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.730274Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:bf040aa074b134ef9cfa6202423e9cfe4f96efcbfddf4c133ec9751d922bc5ed","observation_id":"3b784f16-971d-4fa7-8c94-cea63693a093","resolution":{"observed_at":"2026-08-10T22:40:48.730274Z","resolver_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":"2026-08-10T22:40:48.706765Z","title":"doi: 10.1021/acs.jcim.8b00839","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.706765Z"},"links":{"citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:5bbdea1060f5a5871d5a64d1a6ad87755bcf411d81600d97b506443288e8b7ef","observation_id":"cc444100-0b33-48cc-9c39-7f967e15ef64","resolution":{"observed_at":"2026-08-10T22:40:48.706765Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.10794","last_updated":"2023-06-20T02:25:58Z","snapshot_observed_at":"2026-08-21T05:06:45.206740Z","submitted_at":"2022-11-19T20:43:39Z","title":"NVDiff: Graph Generation through the Diffusion of Node Vectors","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.10794","snapshot_observed_at":"2026-08-10T22:40:48.721620Z","title":"Nvdiff: Graph generation through the diffusion of node vectors","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.721620Z"},"links":{"cited_paper":"/paper/2211.10794","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:937b79f5cd70888a80575df19ff588921597a7d5cfde86ad19548b20c9c1cf7a","observation_id":"1e413192-b68b-400a-8815-a06382b4217a","resolution":{"observed_at":"2026-08-10T22:40:48.721620Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04997","last_updated":"2024-06-05T20:31:17Z","snapshot_observed_at":"2026-08-18T16:01:16.556024Z","submitted_at":"2024-02-07T16:15:36Z","title":"Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Design","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.04997","snapshot_observed_at":"2026-08-10T22:40:48.710470Z","title":"Generative flows on discrete state-spaces: Enabling multimodal flows with applications to protein co-design","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.710470Z"},"links":{"cited_paper":"/paper/2402.04997","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:8276b594258b74a334775504fd92356a70be5231402ae05f17d9bc40621abeab","observation_id":"14e88c52-99f8-4248-81d8-a8c9350b98ca","resolution":{"observed_at":"2026-08-10T22:40:48.710470Z","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":"2026-08-16T09:25:53.087782Z","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":"2026-08-10T22:40:48.734078Z","title":"An image is worth 16x16 words: Trans- formers for image recognition at scale","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.734078Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:d437fb2d14abb22753f1f2c89111128e40954e2e684c3ae8cb6985a128f8392f","observation_id":"d9e28dd6-2c09-4529-b547-0543432f4aaf","resolution":{"observed_at":"2026-08-10T22:40:48.734078Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.11529","last_updated":"2024-05-14T10:59:05Z","snapshot_observed_at":"2026-08-19T23:33:33.453320Z","submitted_at":"2023-12-14T10:42:42Z","title":"Efficient and Scalable Graph Generation through Iterative Local Expansion","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.11529","snapshot_observed_at":"2026-08-10T22:40:48.703455Z","title":"Brown, N., Fiscato, M., Segler, M","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.703455Z"},"links":{"cited_paper":"/paper/2312.11529","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:2f0f70b5753b010a5109936b6fb50d350f1643b97e7e87ccf62335942d253bb8","observation_id":"2f3d802a-7851-4455-9b5a-3be114797785","resolution":{"observed_at":"2026-08-10T22:40:48.703455Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.01950","last_updated":"2025-04-29T16:27:32Z","snapshot_observed_at":"2026-08-18T21:51:34.588159Z","submitted_at":"2025-01-03T18:54:26Z","title":"MADGEN: Mass-Spec attends to De Novo Molecular generation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.01950","snapshot_observed_at":"2026-08-10T22:40:48.824815Z","title":"Wu, M., Chen, X., and Liu, L.-P","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer","version":2},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-10T22:40:48.824815Z"},"links":{"cited_paper":"/paper/2501.01950","citing_paper":"/paper/2501.01073"},"observation_digest":"sha256:08446114959a0ee8333ddc889a41befa5bbee96de9b40ce238435e0c736cf19e","observation_id":"41e1fa4a-8fc1-48f2-9dd4-31d43923a8cb","resolution":{"observed_at":"2026-08-10T22:40:48.824815Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2501.01073","last_updated":"2025-06-03T16:53:33Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T15:11:09.002273Z","submitted_at":"2025-01-02T05:44:11Z","title":"Graph Generative Pre-trained Transformer"},"reference_resolution":{"displayed":51,"state_counts":{"malformed_identifier":1,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":37,"verified_exact":3,"verified_fuzzy":9},"total_outbound_references":51},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 51 of 51 outbound references and 5 inbound Pith citation observations for arXiv:2501.01073."}