{"as_of":"2026-08-20T04:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6200e49f8610336c647566233dc302df138d05c8c47a24b833d1edd95507fabe","coverage":[{"denominator":43,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":43,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T16:37:56.659938Z","state":"measured"},{"denominator":43,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":43,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2509.03056/citation-record","integrity":"/paper/2509.03056/integrity","json":"/paper/2509.03056/citation-record.json","paper":"/paper/2509.03056"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:37:57.294201Z","title":null,"venue":null,"work_id":"d78749c9-9fb5-47bc-985f-0b2855706da7","year":2010},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.505403Z"},"links":{"citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:2ae053dc695921944ee64f1657d6febc43c183253f153c36064c33555d7f5b08","observation_id":"a73aec0a-4534-46bf-b3ad-8b3199908af3","resolution":{"observed_at":"2026-08-15T16:37:57.297851Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1402.1869","last_updated":"2014-06-07T19:56:14Z","snapshot_observed_at":"2026-08-14T23:45:22.999762Z","submitted_at":"2014-02-08T17:16:27Z","title":"On the Number of Linear Regions of Deep Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1402.1869","snapshot_observed_at":"2026-08-15T16:37:56.509632Z","title":"On the number of linear regions of deep neural networks,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.509632Z"},"links":{"cited_paper":"/paper/1402.1869","citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:3a269e77e8bff3a87739827da0fe4699d0f09be362271dc7dd60c246df0f33ba","observation_id":"62d4b188-3130-4576-919c-89bf78738aa1","resolution":{"observed_at":"2026-08-15T16:37:56.509632Z","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":"2026-08-15T16:37:57.283858Z","title":"Deep ReLU networks have surprisingly few activation patterns,","venue":null,"work_id":"943f0f4f-cc1d-484e-8256-a359a9fc42f3","year":2019},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.513823Z"},"links":{"citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:66cb4f50d92f3312f103dfa4783e560c166f5acf6ff08654878ea010b5a95f56","observation_id":"e275e413-768d-4cf2-94f5-00f338f03761","resolution":{"observed_at":"2026-08-15T16:37:57.287341Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:37:57.273963Z","title":"Bounding and counting linear regions of deep neural networks,","venue":null,"work_id":"7f2e1b36-14c9-4eaa-b7b4-dc70b4f4c7ae","year":2018},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.517634Z"},"links":{"citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:3e63ec7fed18c0f312551273c836bb7ae1855ca82f65fa35e78e67f01c36c48d","observation_id":"0e396884-04bf-4af9-a349-d5829f521a2b","resolution":{"observed_at":"2026-08-15T16:37:57.277499Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.11692","last_updated":"2025-05-28T21:46:04Z","snapshot_observed_at":"2026-08-17T09:23:20.477063Z","submitted_at":"2025-05-16T21:00:56Z","title":"The Geometry of ReLU Networks through the ReLU Transition Graph","version":2},"cited_work":{"arxiv_id":"2505.11692","doi":"10.48550/arxiv.2505.11692","metadata_source":"pith","pith_arxiv_id":"2505.11692","snapshot_observed_at":"2026-08-15T18:16:14.067578Z","title":"The Geometry of ReLU Networks through the ReLU Transition Graph","venue":"cs.LG","work_id":"0d4f05a8-35e6-4d9a-942b-c7006d1c7bda","year":2025},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.522303Z"},"links":{"cited_paper":"/paper/2505.11692","citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:9d0a6c0531492c95c1c29f0f762a3aa81804c7208fe1fc69d5369288331be5aa","observation_id":"a0c98cc1-eee2-4757-9ae4-bff2e0102c37","resolution":{"observed_at":"2026-08-15T16:37:56.702935Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:37:57.263882Z","title":"On the second eigenvalue of a graph and a network flow problem,","venue":null,"work_id":"56987f0c-282a-4d3d-93d4-fbd1d68debb7","year":1991},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.526720Z"},"links":{"citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:2671a0036f4134ed68eb0374aba7149831faec655761167db19acebb478e85f2","observation_id":"acf8f92b-2181-4ed7-addd-4b88595f0341","resolution":{"observed_at":"2026-08-15T16:37:57.267327Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:37:57.254733Z","title":"Expander graphs,","venue":null,"work_id":"bdffd91a-5a18-4ee2-855b-a63020749239","year":2006},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.530710Z"},"links":{"citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:59bc7166f4f1e365a2c56fc4fd522ca3d10c688b025587822ac39122e38b2383","observation_id":"60987502-3ec2-46a4-985a-2d2bfa1e4bb0","resolution":{"observed_at":"2026-08-15T16:37:57.258097Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1806.07572","last_updated":"2020-02-10T08:39:09Z","snapshot_observed_at":"2026-08-14T19:01:37.246770Z","submitted_at":"2018-06-20T06:35:46Z","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.07572","snapshot_observed_at":"2026-08-15T16:37:56.534287Z","title":"Neural tangent kernel: Con- vergence and generalization in neural networks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.534287Z"},"links":{"cited_paper":"/paper/1806.07572","citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:ba607f185e072ccb2537c9397ec3a4a713144bb6722bfc06389a8cc432a7b8cb","observation_id":"33dda763-0c27-4324-876b-f22e75a06b6a","resolution":{"observed_at":"2026-08-15T16:37:56.534287Z","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":"2026-08-15T16:37:57.244423Z","title":"Facing Up to Arrangements: Face-Count Formulas for Partitions of Space by Hyperplanes","venue":null,"work_id":"eefe3a40-4f1f-41a1-8ba8-639a5b39cf72","year":1975},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.538173Z"},"links":{"citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:2eab3b3889879459cb831724ac3d6fab919ec5f88fb741f87b111a54bfe74422","observation_id":"1f6544aa-b484-4e9d-81cc-906a94b66e98","resolution":{"observed_at":"2026-08-15T16:37:57.247986Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1611.01491","last_updated":"2018-02-28T02:23:47Z","snapshot_observed_at":"2026-08-15T05:08:05.120780Z","submitted_at":"2016-11-04T18:54:50Z","title":"Understanding Deep Neural Networks with Rectified Linear Units","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.01491","snapshot_observed_at":"2026-08-15T16:37:56.541763Z","title":"Understand- ing deep neural networks with rectified linear units,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.541763Z"},"links":{"cited_paper":"/paper/1611.01491","citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:9286dfd2906132bc7535c9f11a276932751f3ae8aa7a27220db654b514734050","observation_id":"ef7b5cc2-0635-420e-94e8-116014d836db","resolution":{"observed_at":"2026-08-15T16:37:56.541763Z","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":"2026-08-15T16:37:57.233831Z","title":"Complexity of linear regions in deep networks,","venue":null,"work_id":"bb3c731e-cd73-4476-b795-16275e5d4cb6","year":2019},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.545542Z"},"links":{"citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:678496bc022c7f43c91dd248b0fa536873cd2a08ec944b537834d5b466f002b5","observation_id":"e218984a-e1d9-4728-b382-abf00f55e2a0","resolution":{"observed_at":"2026-08-15T16:37:57.237443Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:37:57.221618Z","title":"On the expressive power of deep neural networks,","venue":null,"work_id":"c9225e2c-d889-4d69-a85d-4b10ff8ec7e1","year":2017},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.549126Z"},"links":{"citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:e6276a2d80fbbc2a92ed0a15af8c314585564e4eb46312b6e27f3622ee2e1e2c","observation_id":"3eeab581-6f01-4a9c-8f49-c016f53e3759","resolution":{"observed_at":"2026-08-15T16:37:57.225718Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1602.04485","last_updated":"2016-05-27T22:11:26Z","snapshot_observed_at":"2026-08-16T17:04:23.592147Z","submitted_at":"2016-02-14T18:36:59Z","title":"Benefits of depth in neural networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1602.04485","snapshot_observed_at":"2026-08-15T16:37:56.552559Z","title":"Benefits of depth in neural networks,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.552559Z"},"links":{"cited_paper":"/paper/1602.04485","citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:a9f991a3bc75a41225962c12f4d72e921700ba0a6413fdfac4a495235ca740f7","observation_id":"b66e8934-1c72-4443-b9f7-cfc4527a0202","resolution":{"observed_at":"2026-08-15T16:37:56.552559Z","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":"2026-08-15T16:37:57.208318Z","title":"Notes on the number of linear regions of deep neural networks,","venue":null,"work_id":"a6f5d076-d68d-42dd-a68b-233ea3362b47","year":2017},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.556536Z"},"links":{"citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:d2323d390047bbd5f96d07cf0bfe2b6709aa7306f48b2306a91eab38798109d5","observation_id":"e7e8d244-513d-45df-b188-bb99053305fa","resolution":{"observed_at":"2026-08-15T16:37:57.213444Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:37:57.195802Z","title":null,"venue":null,"work_id":"d06c7a40-7a54-4cd0-8515-7fbcf484ccf9","year":2021},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.559829Z"},"links":{"citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:5a93e8521beae35d52d69737dcea84183f54eb9de261f895889250eb786ea72d","observation_id":"589792aa-01ee-4300-a218-6401d0e95657","resolution":{"observed_at":"2026-08-15T16:37:57.199720Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:37:56.563180Z","title":"Belkin, D","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.563180Z"},"links":{"citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:710cb25b94911549be77f46951184c85042d7e58a16df3e72c2bdcab75155e6f","observation_id":"c4fa7e6e-8843-4a47-ad67-731b06aaca76","resolution":{"observed_at":"2026-08-15T16:37:56.563180Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.00065","last_updated":"2022-11-23T18:09:57Z","snapshot_observed_at":"2026-08-16T18:42:37.696014Z","submitted_at":"2021-02-26T22:08:19Z","title":"Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.00065","snapshot_observed_at":"2026-08-15T16:37:56.566744Z","title":"Gradient descent on neural networks typically occurs at the edge of stability,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.566744Z"},"links":{"cited_paper":"/paper/2103.00065","citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:b28e843be518ffe25a6e897fddb6aaa545558e182374b549d37b526add11be60","observation_id":"07566956-72d1-4803-a7fe-927f41878665","resolution":{"observed_at":"2026-08-15T16:37:56.566744Z","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":"2026-08-15T16:37:56.570378Z","title":"Ongie, A","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.570378Z"},"links":{"citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:d56dbc268e1a83f8c24a4c8bed1fac10456dc98e2219710405436f4c3b5de80f","observation_id":"41382ba8-6c5d-44a1-b104-fb0e5740ebf9","resolution":{"observed_at":"2026-08-15T16:37:56.570378Z","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":"2026-08-15T16:37:57.184673Z","title":"On the information bottleneck theory of deep learning,","venue":null,"work_id":"492cc38c-355a-44f6-aece-c6869500c5bf","year":2018},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.573654Z"},"links":{"citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:27fa9fdaeb9fd5ff28d481c4475f9396ad5184e65b7cea3f852a509943af73bc","observation_id":"1fa1880f-9b38-4eb3-975f-ba406e287421","resolution":{"observed_at":"2026-08-15T16:37:57.188309Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:37:56.576948Z","title":"Bianchini and F","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.576948Z"},"links":{"citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:101f1b64c78471fa5eb0a765810187cce307df5798d93dbfabf41fb5be9e34b4","observation_id":"ce7b5607-f234-419c-bd07-e274267aa9eb","resolution":{"observed_at":"2026-08-15T16:37:56.576948Z","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":"2026-08-15T16:37:57.173023Z","title":"Ramanujan graphs,","venue":null,"work_id":"faf54f97-473e-48db-9855-ba051030a106","year":1988},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.580277Z"},"links":{"citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:54adc4a6c404d53b2144029ff88d77b9530fe213583fe92859031e0e0d8d037f","observation_id":"cb3db685-8a3c-45c5-9770-547358d465ec","resolution":{"observed_at":"2026-08-15T16:37:57.177103Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:37:57.160993Z","title":"The secret sharer: Evaluating and testing unintended memorization in neural networks,","venue":null,"work_id":"3687c1f7-ba11-46a0-b09d-b60071978309","year":2019},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.583726Z"},"links":{"citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:806eaf0742674efaf3331e852bff0956be10d882f0b276fd30600891ef4c2267","observation_id":"c67e21e3-254c-4b8c-92c3-099577ce7eca","resolution":{"observed_at":"2026-08-15T16:37:57.165463Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.14762","last_updated":"2025-05-28T21:33:01Z","snapshot_observed_at":"2026-08-17T23:23:10.073992Z","submitted_at":"2025-04-20T23:09:20Z","title":"A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization","version":2},"cited_work":{"arxiv_id":"2504.14762","doi":null,"metadata_source":"pith","pith_arxiv_id":"2504.14762","snapshot_observed_at":"2026-08-15T16:37:56.828002Z","title":"A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization","venue":"cs.LG","work_id":"eb5ad633-77ad-4c8d-8ee7-7907995e9388","year":2025},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.587227Z"},"links":{"cited_paper":"/paper/2504.14762","citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:4a386ff3d5c31a86cdf28109d18d53b01fa5390d0a9f68ad27ead460a177f0e0","observation_id":"8110ae7b-4b0c-4b79-af1f-d0faf002571a","resolution":{"observed_at":"2026-08-15T16:37:56.831894Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:37:57.149561Z","title":"Flat minima,","venue":null,"work_id":"cd7e2362-944e-40c9-9771-063307eec7db","year":1997},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.590864Z"},"links":{"citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:6e435013f7baa67e84dca0f14bdd20576708924777065493f74b32017ffa061a","observation_id":"6951f56f-9266-4665-9ae5-056017967bb1","resolution":{"observed_at":"2026-08-15T16:37:57.153343Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1707.09564","last_updated":"2018-02-23T22:30:45Z","snapshot_observed_at":"2026-08-14T20:44:26.541416Z","submitted_at":"2017-07-29T22:36:35Z","title":"A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.09564","snapshot_observed_at":"2026-08-15T16:37:56.594408Z","title":"A PAC-Bayesian ap- proach to spectrally-normalized margin bounds for neural networks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.594408Z"},"links":{"cited_paper":"/paper/1707.09564","citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:7e08c772faa5cb66c74f36bef97b2121c32d48e23adaa1d16b8318ce7e2e5383","observation_id":"6d596a70-9d05-4337-8a57-e0e9209526be","resolution":{"observed_at":"2026-08-15T16:37:56.594408Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1706.08498","last_updated":"2017-12-05T06:08:38Z","snapshot_observed_at":"2026-08-17T13:35:48.482328Z","submitted_at":"2017-06-26T17:43:48Z","title":"Spectrally-normalized margin bounds for neural networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.08498","snapshot_observed_at":"2026-08-15T16:37:56.598002Z","title":"Spectrally-normalized margin bounds for neural networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.598002Z"},"links":{"cited_paper":"/paper/1706.08498","citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:b92310dbefc6154de7132d7d4383f1b57b70c9d98a5e70d1fe8fbbab5e35f4d5","observation_id":"7ee1c7dd-256c-4fce-9b16-0bef28769694","resolution":{"observed_at":"2026-08-15T16:37:56.598002Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.08253","last_updated":"2021-01-15T16:05:16Z","snapshot_observed_at":"2026-08-19T04:57:26.643015Z","submitted_at":"2020-02-19T16:00:47Z","title":"Distance-Based Regularisation of Deep Networks for Fine-Tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.08253","snapshot_observed_at":"2026-08-15T16:37:56.601584Z","title":"Distance-based regularisa- tion of deep networks for fine-tuning,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.601584Z"},"links":{"cited_paper":"/paper/2002.08253","citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:8d8d77002bc80373c1610249ebcc1bbcecf8dec61e1dc9cd0a061d4b3bd58564","observation_id":"96e287bf-6677-441b-92fe-6dff072ce526","resolution":{"observed_at":"2026-08-15T16:37:56.601584Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1712.09913","last_updated":"2018-11-07T06:25:20Z","snapshot_observed_at":"2026-08-16T02:13:45.865235Z","submitted_at":"2017-12-28T16:15:42Z","title":"Visualizing the Loss Landscape of Neural Nets","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1712.09913","snapshot_observed_at":"2026-08-15T16:37:56.605150Z","title":"Visualizing the loss landscape of neural nets,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.605150Z"},"links":{"cited_paper":"/paper/1712.09913","citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:0d89c50b08b215f5ad3f6d68aee930e00907dcc5f2463a84df30352c1b50bbeb","observation_id":"4e4cec81-7a65-4667-9cb8-a6d74f30ada2","resolution":{"observed_at":"2026-08-15T16:37:56.605150Z","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":"2026-08-15T16:37:57.136736Z","title":"Entropy-SGD: Biasing gradient descent into wide valleys,","venue":null,"work_id":"236c352c-50f7-4054-8791-f34088ef9ceb","year":2019},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.608709Z"},"links":{"citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:a39ed67b4b88c62e12a08253841b38362fac78e82b0d9281c7a76005b82dd137","observation_id":"ccd9a270-6ed1-49bb-b3c9-b3ba488874af","resolution":{"observed_at":"2026-08-15T16:37:57.140896Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:37:57.124376Z","title":"Information-theoretic analysis of gen- eralization capability of learning algorithms","venue":null,"work_id":"84b22bb2-82cc-407c-a340-4c4aa2831d30","year":2017},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.612498Z"},"links":{"citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:7987a39c0fcf475ba9650bf269a457f51a96c544ea0ca69855e30f8f7a45ee09","observation_id":"e42d9679-c352-4358-a1e7-beb8f6a17097","resolution":{"observed_at":"2026-08-15T16:37:57.128336Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02406","last_updated":"2015-03-09T09:39:41Z","snapshot_observed_at":"2026-08-19T16:30:07.889432Z","submitted_at":"2015-03-09T09:39:41Z","title":"Deep Learning and the Information Bottleneck Principle","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.02406","snapshot_observed_at":"2026-08-15T16:37:56.616010Z","title":"Deep learning and the information bottleneck principle,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.616010Z"},"links":{"cited_paper":"/paper/1503.02406","citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:95dc1334d13e839874f7fc8f16d8e6ea7cd5db6ff70a361901c32b21e68991a5","observation_id":"55b4d7e1-566d-4aa9-a35d-b2be4fc95f14","resolution":{"observed_at":"2026-08-15T16:37:56.616010Z","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":"2026-08-15T16:37:57.111744Z","title":null,"venue":null,"work_id":"06008006-6228-4068-928a-e40d577eba73","year":2018},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.619709Z"},"links":{"citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:114cffdb3e0bc025d3680c3a53a4df503a179c1afe0af0d3a456cfe8fcf671bd","observation_id":"287684cc-4d7a-49a5-81ef-3648365a903b","resolution":{"observed_at":"2026-08-15T16:37:57.116255Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:37:57.099332Z","title":"Neural networks and principal component analysis: Learning from examples without local minima,","venue":null,"work_id":"1fc841e6-2b27-4c8c-8b17-4add797c135a","year":1989},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.623213Z"},"links":{"citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:8e32e976c78ef2ece242e49ecb060e2b814423b0ce9f1f2b88dacacd8cd6e668","observation_id":"0ca72d69-34ca-4fea-a91d-1e75da8b2b11","resolution":{"observed_at":"2026-08-15T16:37:57.103164Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1606.05340","last_updated":"2016-06-17T18:13:20Z","snapshot_observed_at":"2026-08-14T21:52:22.870994Z","submitted_at":"2016-06-16T19:59:57Z","title":"Exponential expressivity in deep neural networks through transient chaos","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.05340","snapshot_observed_at":"2026-08-15T16:37:56.626530Z","title":"Exponential expressivity in deep neural networks through transient chaos,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.626530Z"},"links":{"cited_paper":"/paper/1606.05340","citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:86531d91b19890f0db4ba49a7450f7fed97c6723a7eba91dd698faf65aac983b","observation_id":"56d1f92e-bd4d-4ee2-abc2-00931cc9fcfb","resolution":{"observed_at":"2026-08-15T16:37:56.626530Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1805.12076","last_updated":"2018-05-30T16:50:28Z","snapshot_observed_at":"2026-08-18T17:29:13.286913Z","submitted_at":"2018-05-30T16:50:28Z","title":"Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.12076","snapshot_observed_at":"2026-08-15T16:37:56.630340Z","title":"Towards understanding the role of over-parametrization in generalization of neural networks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.630340Z"},"links":{"cited_paper":"/paper/1805.12076","citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:aff9c4c59c86209b9de025207bc04711a92508138eea28eb4a0e48e3828ac971","observation_id":"86f91329-3b8e-4467-974b-1ce53ae825ea","resolution":{"observed_at":"2026-08-15T16:37:56.630340Z","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":"2026-08-15T16:37:57.088692Z","title":"On the number of variables to use in principal component regression,","venue":null,"work_id":"167c7307-f9c8-4fd9-8a67-649e51a8c417","year":2019},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.634009Z"},"links":{"citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:b9df571aa5f86b452a54398a9b74e410fe991460d32187d55eaaff3466f00330","observation_id":"44a03e2b-c39e-415d-8708-f372841e5ce5","resolution":{"observed_at":"2026-08-15T16:37:57.092355Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1912.02803","last_updated":"2019-12-05T18:51:57Z","snapshot_observed_at":"2026-08-08T12:08:12.089821Z","submitted_at":"2019-12-05T18:51:57Z","title":"Neural Tangents: Fast and Easy Infinite Neural Networks in Python","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.02803","snapshot_observed_at":"2026-08-15T16:37:56.637651Z","title":"Neural tangents: Fast and easy infinite neural networks in python,","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.637651Z"},"links":{"cited_paper":"/paper/1912.02803","citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:76f167f9c60ce5b0550b686552c383e1d645ebf201751db43e5dd64438f31022","observation_id":"40c362ec-2fc0-4f45-a6d7-3a6072e42164","resolution":{"observed_at":"2026-08-15T16:37:56.637651Z","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":"2026-08-15T16:37:57.077783Z","title":"Geometric deep learning: Going beyond Euclidean data,","venue":null,"work_id":"707f79ec-93ea-4794-88b9-d4bf75f72bd9","year":2017},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.641315Z"},"links":{"citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:bfcb31d482ab9e32b74d9aef7e8f48c9bc8131760656a35df7125228454c1574","observation_id":"cda8406e-ac65-4b4d-97e2-70945b3a20f2","resolution":{"observed_at":"2026-08-15T16:37:57.081350Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.02907","last_updated":"2017-02-22T09:55:36Z","snapshot_observed_at":"2026-08-17T10:49:36.026134Z","submitted_at":"2016-09-09T19:48:41Z","title":"Semi-Supervised Classification with Graph Convolutional Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.02907","snapshot_observed_at":"2026-08-15T16:37:56.644761Z","title":"Semi-supervised classification with graph convolutional networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.644761Z"},"links":{"cited_paper":"/paper/1609.02907","citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:cba990398fe916291cb67ecefb6b1814253d469be838ef26f00da9c508c9c5cf","observation_id":"067941cb-f048-4f73-a8f0-1381f00a4464","resolution":{"observed_at":"2026-08-15T16:37:56.644761Z","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":"2026-08-15T16:37:57.067389Z","title":null,"venue":null,"work_id":"1d9e73a5-05ae-4c00-988e-a8910050faae","year":2020},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.649384Z"},"links":{"citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:1f9683a5820dd8fc542886f677922155d9d76ee4c58bfdfe9838da7e296f67ad","observation_id":"4ed75622-7bac-4a2c-a7dd-89e64ad51d61","resolution":{"observed_at":"2026-08-15T16:37:57.071004Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1705.08504","last_updated":"2019-01-24T19:01:56Z","snapshot_observed_at":"2026-08-15T04:41:52.358740Z","submitted_at":"2017-05-23T19:47:52Z","title":"Interpreting Blackbox Models via Model Extraction","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1705.08504","snapshot_observed_at":"2026-08-15T16:37:56.652609Z","title":"Interpreting blackbox models via model extraction,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.652609Z"},"links":{"cited_paper":"/paper/1705.08504","citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:9b5d0bd239378414611b5644deb2bbe6134abbf4264e84ff460319ecdcf027ed","observation_id":"381143b3-23ba-4ec4-84a2-30ce03b066fa","resolution":{"observed_at":"2026-08-15T16:37:56.652609Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.00891","last_updated":"2019-09-18T01:54:10Z","snapshot_observed_at":"2026-08-14T17:49:24.448493Z","submitted_at":"2018-12-03T16:45:28Z","title":"Interpretable Deep Learning under Fire","version":3},"cited_work":{"arxiv_id":"1812.00891","doi":null,"metadata_source":"pith","pith_arxiv_id":"1812.00891","snapshot_observed_at":"2026-08-15T16:37:56.716109Z","title":"Interpretable Deep Learning under Fire","venue":"cs.CR","work_id":"6f50260f-dacd-4d1e-a3b7-5e00f57d3247","year":2018},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.656329Z"},"links":{"cited_paper":"/paper/1812.00891","citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:c910895c3b23b59730c02d463ca803f2f5b8575cbdb5a4b99da25f34a0bb39eb","observation_id":"2aa6db75-fd6c-4372-a10f-b8f69b2f8b9a","resolution":{"observed_at":"2026-08-15T16:37:56.720539Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:37:57.056542Z","title":"PyTorch: An imperative style, high- performance deep learning library,","venue":null,"work_id":"d0f214ca-ad43-4c0c-b04c-51f1d08849eb","year":2019},"citing_paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T16:37:56.659938Z"},"links":{"citing_paper":"/paper/2509.03056"},"observation_digest":"sha256:f92ab7b5055f3381043ab951a0fbcd01969e4719c3ef882d8a83beb0606b5e3a","observation_id":"affae9a0-1b1e-4523-b8cc-09e1f004412a","resolution":{"observed_at":"2026-08-15T16:37:57.060623Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2509.03056","last_updated":"2025-09-04T01:30:08Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-18T05:13:18.409981Z","submitted_at":"2025-09-03T06:38:22Z","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs"},"reference_resolution":{"displayed":43,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":22,"verified_exact":3,"verified_fuzzy":18},"total_outbound_references":43},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2509.03056."}