{"as_of":"2026-08-15T22:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:59dc1302e54430dffa16db40bdae9f29cbca7490687e35722a36624079c7d296","coverage":[{"denominator":24,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":24,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-03T17:03:25.354819Z","state":"measured"},{"denominator":24,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":24,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+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/2607.02166/citation-record","integrity":"/paper/2607.02166/integrity","json":"/paper/2607.02166/citation-record.json","paper":"/paper/2607.02166"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2302.03130","last_updated":"2023-02-09T12:43:24Z","snapshot_observed_at":"2026-08-15T12:54:38.821687Z","submitted_at":"2023-02-06T21:35:44Z","title":"Spatial Functa: Scaling Functa to ImageNet Classification and Generation","version":2},"cited_work":{"arxiv_id":"2302.03130","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2302.03130","snapshot_observed_at":"2026-07-03T17:08:42.727434Z","title":"Spatial functa: Scaling functa to imagenet classifi- cation and generation","venue":null,"work_id":"6ef86319-412a-4f11-acea-d638822bbdc1","year":2023},"citing_paper":{"arxiv_id":"2607.02166","last_updated":"2026-07-02T13:36:19Z","snapshot_observed_at":"2026-08-14T16:04:34.658693Z","submitted_at":"2026-07-02T13:36:19Z","title":"Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-03T17:03:25.354819Z"},"links":{"cited_paper":"/paper/2302.03130","citing_paper":"/paper/2607.02166"},"observation_digest":"sha256:059fac58843beee1eaf20287e6aff1aba745ed317204c0be81aa059dbb78b075","observation_id":"96583d3d-92c6-4892-848d-673b608ceb83","resolution":{"observed_at":"2026-07-03T17:08:42.729152Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.05438","last_updated":"2023-02-10T18:55:49Z","snapshot_observed_at":"2026-08-13T12:47:12.784005Z","submitted_at":"2023-02-10T18:55:49Z","title":"Deep Learning on Implicit Neural Representations of Shapes","version":1},"cited_work":{"arxiv_id":"2302.05438","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2302.05438","snapshot_observed_at":"2026-07-03T17:08:42.743464Z","title":"Luca De Luigi, Adriano Cardace, Riccardo Spezialetti, Pierluigi Zama Ramirez, Samuele Salti, and Luigi Di Stefano","venue":null,"work_id":"a098057e-69d7-4416-a264-2a4cc9228f52","year":2023},"citing_paper":{"arxiv_id":"2607.02166","last_updated":"2026-07-02T13:36:19Z","snapshot_observed_at":"2026-08-14T16:04:34.658693Z","submitted_at":"2026-07-02T13:36:19Z","title":"Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-03T17:03:25.354819Z"},"links":{"cited_paper":"/paper/2302.05438","citing_paper":"/paper/2607.02166"},"observation_digest":"sha256:0f3dc32b39b78ae7062e97e416cdb09c25693081e2c14417edd601924c0aedaa","observation_id":"4d1330c8-bfea-478a-acc9-98cd981e0d82","resolution":{"observed_at":"2026-07-03T17:08:42.745387Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.12204","last_updated":"2022-11-10T13:32:44Z","snapshot_observed_at":"2026-08-13T16:51:00.574750Z","submitted_at":"2022-01-28T15:59:58Z","title":"From data to functa: Your data point is a function and you can treat it like one","version":3},"cited_work":{"arxiv_id":"2201.12204","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2201.12204","snapshot_observed_at":"2026-07-03T17:08:42.732388Z","title":"From data to functa: Your data point is a function and you can treat it like one.arXiv preprint arXiv:2201.12204","venue":null,"work_id":"0284c2c8-1587-4b02-92a6-024906aba9d2","year":2022},"citing_paper":{"arxiv_id":"2607.02166","last_updated":"2026-07-02T13:36:19Z","snapshot_observed_at":"2026-08-14T16:04:34.658693Z","submitted_at":"2026-07-02T13:36:19Z","title":"Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-03T17:03:25.354819Z"},"links":{"cited_paper":"/paper/2201.12204","citing_paper":"/paper/2607.02166"},"observation_digest":"sha256:27a2b6032f5098993c46f8bf976b6199cb102773ceb24e4e14544f478056e562","observation_id":"066bd899-5c81-46cf-ae9c-05b6527f8388","resolution":{"observed_at":"2026-07-03T17:08:42.734125Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1912.06126","last_updated":"2020-06-12T03:26:47Z","snapshot_observed_at":"2026-08-15T21:19:49.888036Z","submitted_at":"2019-12-12T18:50:46Z","title":"Local Deep Implicit Functions for 3D Shape","version":2},"cited_work":{"arxiv_id":"1912.06126","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1912.06126","snapshot_observed_at":"2026-07-03T17:08:42.738049Z","title":"Deep structured implicit functions.arXiv preprint arXiv:1912.06126, 2:2,","venue":null,"work_id":"3622a246-00e2-4a40-8d69-03ee2d09ef4e","year":1912},"citing_paper":{"arxiv_id":"2607.02166","last_updated":"2026-07-02T13:36:19Z","snapshot_observed_at":"2026-08-14T16:04:34.658693Z","submitted_at":"2026-07-02T13:36:19Z","title":"Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-03T17:03:25.354819Z"},"links":{"cited_paper":"/paper/1912.06126","citing_paper":"/paper/2607.02166"},"observation_digest":"sha256:4e98da0c04031f96c4944a0a8f735ce855bc8bf1cbde77eca2ded159e6a69e79","observation_id":"f660bafa-bd7b-4359-a356-c7b707d069d3","resolution":{"observed_at":"2026-07-03T17:08:42.739514Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.10099","last_updated":"2020-07-09T12:32:45Z","snapshot_observed_at":"2026-08-15T13:05:42.160094Z","submitted_at":"2020-02-24T07:36:32Z","title":"Implicit Geometric Regularization for Learning Shapes","version":2},"cited_work":{"arxiv_id":"2002.10099","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2002.10099","snapshot_observed_at":"2026-07-03T17:08:42.741138Z","title":"arXiv preprint arXiv:2002.10099 (2020) 3","venue":null,"work_id":"16d5c044-b61c-4812-b413-e2a102ba218b","year":2002},"citing_paper":{"arxiv_id":"2607.02166","last_updated":"2026-07-02T13:36:19Z","snapshot_observed_at":"2026-08-14T16:04:34.658693Z","submitted_at":"2026-07-02T13:36:19Z","title":"Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-03T17:03:25.354819Z"},"links":{"cited_paper":"/paper/2002.10099","citing_paper":"/paper/2607.02166"},"observation_digest":"sha256:b5ec821c8a47b35c8b953d5a7b73f48860db98d479e69ba41e0a313bc7d59532","observation_id":"ae9f80fa-3cff-4598-99c1-9026ad6dda79","resolution":{"observed_at":"2026-07-03T17:08:42.742620Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2603.15990","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-03T17:08:42.735244Z","title":"W2t: Lora weights already know what they can do.arXiv preprint arXiv:2603.15990, 2026a","venue":null,"work_id":"a6ae0a0a-ad1f-45a9-a57c-ecfef833874c","year":2026},"citing_paper":{"arxiv_id":"2607.02166","last_updated":"2026-07-02T13:36:19Z","snapshot_observed_at":"2026-08-14T16:04:34.658693Z","submitted_at":"2026-07-02T13:36:19Z","title":"Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-03T17:03:25.354819Z"},"links":{"citing_paper":"/paper/2607.02166"},"observation_digest":"sha256:fd7c465b25cba71515532501522ba1e055c3fd854f24c00ed74ec096c470f13c","observation_id":"0b11bb70-d36d-40ae-98eb-41c9085730a4","resolution":{"observed_at":"2026-07-03T17:08:42.737009Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-07-05T05:00:42.187926Z","title":"Representation learning for dynamic graphs: A survey.Journal of Machine Learning Research, 21(70):1–73,","venue":null,"work_id":"68ae1b34-9e74-4c52-8588-8f0fcfd98fd4","year":2026},"citing_paper":{"arxiv_id":"2607.02166","last_updated":"2026-07-02T13:36:19Z","snapshot_observed_at":"2026-08-14T16:04:34.658693Z","submitted_at":"2026-07-02T13:36:19Z","title":"Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-03T17:03:25.354819Z"},"links":{"citing_paper":"/paper/2607.02166"},"observation_digest":"sha256:de593748970818b39e7a01c558f889c733ec2a82d8952390a21124f10f253bd9","observation_id":"1c0a3222-4d2d-4bec-9ec5-6d83d5d04791","resolution":{"observed_at":"2026-07-05T05:00:42.189285Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.12143","last_updated":"2024-07-23T16:30:10Z","snapshot_observed_at":"2026-08-13T00:50:58.052526Z","submitted_at":"2024-03-18T18:01:01Z","title":"Graph Neural Networks for Learning Equivariant Representations of Neural Networks","version":3},"cited_work":{"arxiv_id":"2403.12143","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.12143","snapshot_observed_at":"2026-07-03T17:08:42.740606Z","title":"J., Gavves, E., Snoek, C","venue":null,"work_id":"c978cc9c-960c-4190-9d42-892ea1286192","year":null},"citing_paper":{"arxiv_id":"2607.02166","last_updated":"2026-07-02T13:36:19Z","snapshot_observed_at":"2026-08-14T16:04:34.658693Z","submitted_at":"2026-07-02T13:36:19Z","title":"Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-03T17:03:25.354819Z"},"links":{"cited_paper":"/paper/2403.12143","citing_paper":"/paper/2607.02166"},"observation_digest":"sha256:318fda44f924cc1c265f32c9dd5647574172dd5dd3354253b06256c13770b191","observation_id":"d6094792-5576-410c-bbf7-64927b7129e0","resolution":{"observed_at":"2026-07-03T17:08:42.742350Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2211.09760","last_updated":"2022-11-17T18:39:07Z","snapshot_observed_at":"2026-08-13T13:40:11.559725Z","submitted_at":"2022-11-17T18:39:07Z","title":"VeLO: Training Versatile Learned Optimizers by Scaling Up","version":1},"cited_work":{"arxiv_id":"2211.09760","doi":null,"metadata_source":"pith","pith_arxiv_id":"2211.09760","snapshot_observed_at":"2026-07-10T21:47:36.423685Z","title":"arXiv:2211.09760 (2022) 4","venue":"cs.LG","work_id":"a1254e41-e26e-46e4-9c1b-16bcd3310ace","year":2022},"citing_paper":{"arxiv_id":"2607.02166","last_updated":"2026-07-02T13:36:19Z","snapshot_observed_at":"2026-08-14T16:04:34.658693Z","submitted_at":"2026-07-02T13:36:19Z","title":"Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-03T17:03:25.354819Z"},"links":{"cited_paper":"/paper/2211.09760","citing_paper":"/paper/2607.02166"},"observation_digest":"sha256:39b6d05ca9994fcc3bbf86f69df0b70309a38d0fde0ec04bc8a5d0b72d406c7a","observation_id":"945edc38-9b24-431d-beb2-b9081a16eb09","resolution":{"observed_at":"2026-07-03T17:08:42.740013Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10637","last_updated":"2020-10-09T11:39:32Z","snapshot_observed_at":"2026-08-07T10:11:23.671536Z","submitted_at":"2020-06-18T16:06:18Z","title":"Temporal Graph Networks for Deep Learning on Dynamic Graphs","version":3},"cited_work":{"arxiv_id":"2006.10637","doi":"10.48550/arxiv.2006.10637","metadata_source":"pith","pith_arxiv_id":"2006.10637","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Temporal Graph Networks for Deep Learning on Dynamic Graphs","venue":"cs.LG","work_id":"148caacb-5e39-4b83-8a6b-07b844a00d64","year":2020},"citing_paper":{"arxiv_id":"2607.02166","last_updated":"2026-07-02T13:36:19Z","snapshot_observed_at":"2026-08-14T16:04:34.658693Z","submitted_at":"2026-07-02T13:36:19Z","title":"Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-03T17:03:25.354819Z"},"links":{"cited_paper":"/paper/2006.10637","citing_paper":"/paper/2607.02166"},"observation_digest":"sha256:77e93b9606ece2faf17250b42f38edc0086529eb1c5c05ce990fd32574328a34","observation_id":"b5db805a-3598-482c-b520-aa8a1c167a93","resolution":{"observed_at":"2026-07-03T17:08:42.731073Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-07-05T05:00:42.185959Z","title":"Structured sequence model- ing with graph convolutional recurrent networks","venue":null,"work_id":"ded8528c-ae0a-45b4-8468-8d0765b559ec","year":2018},"citing_paper":{"arxiv_id":"2607.02166","last_updated":"2026-07-02T13:36:19Z","snapshot_observed_at":"2026-08-14T16:04:34.658693Z","submitted_at":"2026-07-02T13:36:19Z","title":"Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-03T17:03:25.354819Z"},"links":{"citing_paper":"/paper/2607.02166"},"observation_digest":"sha256:26a7f05939aa473a8be6f7e1f5c3a462257cd7ddfb8afa0ac6e946287b0f5e31","observation_id":"2559219f-0b0a-439d-9c9d-b4707a653d22","resolution":{"observed_at":"2026-07-05T05:00:42.187313Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04081","last_updated":"2024-11-09T22:09:13Z","snapshot_observed_at":"2026-08-13T04:25:05.026742Z","submitted_at":"2024-02-06T15:34:44Z","title":"Improved Generalization of Weight Space Networks via Augmentations","version":2},"cited_work":{"arxiv_id":"2402.04081","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.04081","snapshot_observed_at":"2026-07-03T17:08:42.730283Z","title":"Improved generalization of weight space networks via augmentations.arXiv preprint arXiv:2402.04081,","venue":null,"work_id":"c243eb35-16cc-4f8f-bb30-ab3d5022ab15","year":null},"citing_paper":{"arxiv_id":"2607.02166","last_updated":"2026-07-02T13:36:19Z","snapshot_observed_at":"2026-08-14T16:04:34.658693Z","submitted_at":"2026-07-02T13:36:19Z","title":"Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-03T17:03:25.354819Z"},"links":{"cited_paper":"/paper/2402.04081","citing_paper":"/paper/2607.02166"},"observation_digest":"sha256:e996b350581b0780fd4109909e2a55e1eefd4ac2a5e9de06274ba0233088f6fc","observation_id":"a3ae3bd1-bdf1-4e10-931c-bdb64bc576ec","resolution":{"observed_at":"2026-07-03T17:08:42.731971Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.07965","last_updated":"2021-02-02T18:45:44Z","snapshot_observed_at":"2026-08-09T18:34:39.958199Z","submitted_at":"2021-01-20T04:50:16Z","title":"Directed Acyclic Graph Neural Networks","version":3},"cited_work":{"arxiv_id":"2101.07965","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2101.07965","snapshot_observed_at":"2026-07-03T17:08:42.735793Z","title":"arXiv preprint arXiv:2101.07965 , year=","venue":null,"work_id":"9117995e-cf75-4a80-8f64-2c2979217134","year":null},"citing_paper":{"arxiv_id":"2607.02166","last_updated":"2026-07-02T13:36:19Z","snapshot_observed_at":"2026-08-14T16:04:34.658693Z","submitted_at":"2026-07-02T13:36:19Z","title":"Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-03T17:03:25.354819Z"},"links":{"cited_paper":"/paper/2101.07965","citing_paper":"/paper/2607.02166"},"observation_digest":"sha256:3670fde0b855911ea38e88a5f30597dd048571c13eb32688a3a2c41c9a2499d6","observation_id":"68c14cbb-eea6-4681-846e-39578cd51e9c","resolution":{"observed_at":"2026-07-03T17:08:42.737409Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.11448","last_updated":"2021-04-09T10:38:15Z","snapshot_observed_at":"2026-08-15T07:27:36.358481Z","submitted_at":"2020-02-26T13:06:14Z","title":"Predicting Neural Network Accuracy from Weights","version":4},"cited_work":{"arxiv_id":"2002.11448","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2002.11448","snapshot_observed_at":"2026-07-03T20:58:57.267130Z","title":"arXiv preprint arXiv:2002.11448 , year=","venue":null,"work_id":"4c672574-1151-4b37-8766-f622bc3d6f7c","year":2002},"citing_paper":{"arxiv_id":"2607.02166","last_updated":"2026-07-02T13:36:19Z","snapshot_observed_at":"2026-08-14T16:04:34.658693Z","submitted_at":"2026-07-02T13:36:19Z","title":"Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-03T17:03:25.354819Z"},"links":{"cited_paper":"/paper/2002.11448","citing_paper":"/paper/2607.02166"},"observation_digest":"sha256:539d49b1ef5e3f1b77bede7c1d36c6c91295cf2fc8d8dc5b0c86af67ba23e521","observation_id":"a60b66a9-63f4-4b1c-9e2c-2d413cbf885c","resolution":{"observed_at":"2026-07-03T17:08:42.728472Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.05749","last_updated":"2020-12-18T18:01:04Z","snapshot_observed_at":"2026-08-14T18:15:23.434821Z","submitted_at":"2018-10-12T22:21:05Z","title":"Graph HyperNetworks for Neural Architecture Search","version":3},"cited_work":{"arxiv_id":"1810.05749","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1810.05749","snapshot_observed_at":"2026-07-03T17:08:42.719536Z","title":"Graph hypernet- works for neural architecture search","venue":null,"work_id":"eb9792cf-eb5e-4d08-a26d-d330dcf603f4","year":2026},"citing_paper":{"arxiv_id":"2607.02166","last_updated":"2026-07-02T13:36:19Z","snapshot_observed_at":"2026-08-14T16:04:34.658693Z","submitted_at":"2026-07-02T13:36:19Z","title":"Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-03T17:03:25.354819Z"},"links":{"cited_paper":"/paper/1810.05749","citing_paper":"/paper/2607.02166"},"observation_digest":"sha256:5f543944a435a7f6ca7788b023a319383e8e9f51871d43285d7ccc19d584ad1e","observation_id":"445b7307-4c5b-4804-b347-6fb79c3f0463","resolution":{"observed_at":"2026-07-03T17:08:42.721164Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-07-05T05:00:42.179221Z","title":"Permutation equivariant neural functionals.Advances in Neural Information Processing Systems, 36, 2024a","venue":null,"work_id":"2fba67d3-6bcc-47fe-a20c-e81248464c5e","year":2026},"citing_paper":{"arxiv_id":"2607.02166","last_updated":"2026-07-02T13:36:19Z","snapshot_observed_at":"2026-08-14T16:04:34.658693Z","submitted_at":"2026-07-02T13:36:19Z","title":"Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-03T17:03:25.354819Z"},"links":{"citing_paper":"/paper/2607.02166"},"observation_digest":"sha256:53b5173ff34785c78426742b76c469643e13e7ee96f97685084a074a6d0cfa75","observation_id":"19abf8a0-fde8-4fb5-8907-d6e7b310a61b","resolution":{"observed_at":"2026-07-05T05:00:42.180951Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-07-05T05:00:42.181711Z","title":"inverse problem","venue":null,"work_id":"cac4c139-9027-45d8-a8b9-d2acf003d32b","year":2026},"citing_paper":{"arxiv_id":"2607.02166","last_updated":"2026-07-02T13:36:19Z","snapshot_observed_at":"2026-08-14T16:04:34.658693Z","submitted_at":"2026-07-02T13:36:19Z","title":"Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-03T17:03:25.354819Z"},"links":{"citing_paper":"/paper/2607.02166"},"observation_digest":"sha256:db817f5def748d41e6efcfc510f738822f510df96d2757f3d035a5ff26479545","observation_id":"6a7e0650-9ea6-43b3-9e38-d7cddb385d05","resolution":{"observed_at":"2026-07-05T05:00:42.183194Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-07-05T05:00:42.177101Z","title":null,"venue":null,"work_id":"1ee69a84-a7aa-4d5e-b39b-371806d2d8c5","year":2024},"citing_paper":{"arxiv_id":"2607.02166","last_updated":"2026-07-02T13:36:19Z","snapshot_observed_at":"2026-08-14T16:04:34.658693Z","submitted_at":"2026-07-02T13:36:19Z","title":"Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-03T17:03:25.354819Z"},"links":{"citing_paper":"/paper/2607.02166"},"observation_digest":"sha256:cfd70e5ff29ed347e3cf8f77588720c4ac824cf31e1655deeb358d83f44546be","observation_id":"a176939e-8540-4f6e-9ec6-60752a443bf8","resolution":{"observed_at":"2026-07-05T05:00:42.178525Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-07-05T05:00:42.183769Z","title":"Under this convention, πl acts on the nodesvl and edgesel as follows: •Nodes:The permuted nodes satisfy ˜vl =P πl vl","venue":null,"work_id":"454f0556-494c-4709-8a95-91bd0f43ef3d","year":2026},"citing_paper":{"arxiv_id":"2607.02166","last_updated":"2026-07-02T13:36:19Z","snapshot_observed_at":"2026-08-14T16:04:34.658693Z","submitted_at":"2026-07-02T13:36:19Z","title":"Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-03T17:03:25.354819Z"},"links":{"citing_paper":"/paper/2607.02166"},"observation_digest":"sha256:0d5a764620061cd3c53cd54c4cca2b367f8c1ac33fbcebc2dee35f955372f40a","observation_id":"757ed599-557c-491f-a3a0-5c7a0688027d","resolution":{"observed_at":"2026-07-05T05:00:42.185295Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-07-05T05:00:42.177261Z","title":"By induction,GT is equivariant under neuron permutations at each layer","venue":null,"work_id":"86949fda-9568-4b84-9572-794ec75bb474","year":2026},"citing_paper":{"arxiv_id":"2607.02166","last_updated":"2026-07-02T13:36:19Z","snapshot_observed_at":"2026-08-14T16:04:34.658693Z","submitted_at":"2026-07-02T13:36:19Z","title":"Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-03T17:03:25.354819Z"},"links":{"citing_paper":"/paper/2607.02166"},"observation_digest":"sha256:44f6ba379413aadeb03190f3be1d8250a19e7aa10cc36b95c57699e307eddd09","observation_id":"cf3a78a9-3ac2-4ff5-b733-7af4d5f85536","resolution":{"observed_at":"2026-07-05T05:00:42.178711Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-07-05T05:00:42.174827Z","title":"Under permutationπ: •Added nodesv l becomev l′={π(i)|vl i∈vl}","venue":null,"work_id":"8911ffaa-e9df-465c-82d6-3bbe168cb7e7","year":2026},"citing_paper":{"arxiv_id":"2607.02166","last_updated":"2026-07-02T13:36:19Z","snapshot_observed_at":"2026-08-14T16:04:34.658693Z","submitted_at":"2026-07-02T13:36:19Z","title":"Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-03T17:03:25.354819Z"},"links":{"citing_paper":"/paper/2607.02166"},"observation_digest":"sha256:9358547bd95ce789b1edb4062900a5b68096532f3b6390f451098a896a25b7cf","observation_id":"81d553a0-579b-4a3c-9159-c767cc68de37","resolution":{"observed_at":"2026-07-05T05:00:42.176468Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-07-05T05:00:42.175210Z","title":"Specifically, a residual connection in a neural network allows the input to bypass one or more layers and be added directly to the output","venue":null,"work_id":"b43bc254-3c91-40c4-9fc7-582d7c2f067e","year":2026},"citing_paper":{"arxiv_id":"2607.02166","last_updated":"2026-07-02T13:36:19Z","snapshot_observed_at":"2026-08-14T16:04:34.658693Z","submitted_at":"2026-07-02T13:36:19Z","title":"Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-03T17:03:25.354819Z"},"links":{"citing_paper":"/paper/2607.02166"},"observation_digest":"sha256:19ae58819a58367f9d0076ecafd22cade299eb3feaade1416d3b1bc951bac282","observation_id":"75ca72a4-e1da-47bd-a53c-90dc38a81c5a","resolution":{"observed_at":"2026-07-05T05:00:42.176652Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-07-05T05:00:42.165473Z","title":null,"venue":null,"work_id":"5d754b38-9f15-4e9b-a0e0-aebe80aa69e7","year":2020},"citing_paper":{"arxiv_id":"2607.02166","last_updated":"2026-07-02T13:36:19Z","snapshot_observed_at":"2026-08-14T16:04:34.658693Z","submitted_at":"2026-07-02T13:36:19Z","title":"Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-03T17:03:25.354819Z"},"links":{"citing_paper":"/paper/2607.02166"},"observation_digest":"sha256:e5f0d643e78be2c1690e70a985376f15f12dc20e656cfe921a6198348cb03588","observation_id":"ffbe92ea-79e1-453e-b817-cb3186bbb7a9","resolution":{"observed_at":"2026-07-05T05:00:42.166618Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-07-05T05:00:42.169968Z","title":"We set the training batch size to 128, use Adam as the optimizer with learning rate of 1e-4, train for 200 epochs, and use early stopping","venue":null,"work_id":"e9f8df3f-712f-45f1-bbde-c0564279c502","year":2026},"citing_paper":{"arxiv_id":"2607.02166","last_updated":"2026-07-02T13:36:19Z","snapshot_observed_at":"2026-08-14T16:04:34.658693Z","submitted_at":"2026-07-02T13:36:19Z","title":"Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-03T17:03:25.354819Z"},"links":{"citing_paper":"/paper/2607.02166"},"observation_digest":"sha256:d2ebec4d438c34b17c43ffd75f3a5698bb845b3801f3c8e1690a6b0230f20d12","observation_id":"02751353-c02f-4d81-90d9-13a325c53eaa","resolution":{"observed_at":"2026-07-05T05:00:42.171727Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2607.02166","last_updated":"2026-07-02T13:36:19Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-14T16:04:34.658693Z","submitted_at":"2026-07-02T13:36:19Z","title":"Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space"},"reference_resolution":{"displayed":24,"state_counts":{"malformed_identifier":0,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":2,"verified_exact":11,"verified_fuzzy":9},"total_outbound_references":24},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 0 inbound Pith citation observations for arXiv:2607.02166."}