{"as_of":"2026-08-09T21:38:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1098e039c5940ed2ff72d1a141beeba07c8158c119155141e0a115bc2e6bae9c","coverage":[{"denominator":62,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":62,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T21:11:58.856366Z","state":"measured"},{"denominator":62,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":62,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2507.00880/citation-record","integrity":"/paper/2507.00880/integrity","json":"/paper/2507.00880/citation-record.json","paper":"/paper/2507.00880"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2101.08134","last_updated":"2021-03-19T10:43:12Z","snapshot_observed_at":"2026-07-06T10:34:02.819928Z","submitted_at":"2021-01-20T13:59:52Z","title":"Zero-Cost Proxies for Lightweight NAS","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.08134","snapshot_observed_at":"2026-08-06T21:11:57.876246Z","title":"Zero-cost proxies for lightweight nas","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:57.876246Z"},"links":{"cited_paper":"/paper/2101.08134","citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:64e4d66a1cb061bf54b7c297743c417951088ef45719a1a973f0d73e0b32253f","observation_id":"2452f6f6-6785-455a-a796-8d4fb62a0868","resolution":{"observed_at":"2026-08-06T21:11:57.876246Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.09791","last_updated":"2020-04-29T20:49:05Z","snapshot_observed_at":"2026-07-06T08:16:55.767797Z","submitted_at":"2019-08-26T16:46:23Z","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.09791","snapshot_observed_at":"2026-08-06T21:11:58.008671Z","title":"Once-for-all: Train one network and specialize it for efficient deployment","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.008671Z"},"links":{"cited_paper":"/paper/1908.09791","citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:340d41f505cc98b26f8eb387fcef0c254173d099030b046c75a81469aa06aef4","observation_id":"986922d5-ecc3-4c4b-a2f4-77cf1fac760b","resolution":{"observed_at":"2026-08-06T21:11:58.008671Z","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":"2026-08-06T21:11:59.351417Z","title":"Contrastive neural archi- tecture search with neural architecture comparators","venue":null,"work_id":"39d578e8-5ca5-491d-bcc7-acf1d29d1731","year":2021},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.175163Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:b99c9408d3b19e2242d315d65856f8b663e93aecc8ed0153010c1b1175ba758d","observation_id":"ba253c5a-ef62-463d-aab0-b4beacce2984","resolution":{"observed_at":"2026-08-06T21:11:59.354086Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1712.03351","last_updated":"2017-12-09T07:50:27Z","snapshot_observed_at":"2026-08-06T18:44:17.571247Z","submitted_at":"2017-12-09T07:50:27Z","title":"Peephole: Predicting Network Performance Before Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1712.03351","snapshot_observed_at":"2026-08-06T21:11:58.341892Z","title":"Peephole: Pre- dicting network performance before training","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.341892Z"},"links":{"cited_paper":"/paper/1712.03351","citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:9d2e403582329313ac0d55c8fa595f30b0f3b196ab70e2f7614a002ec2c357bc","observation_id":"52855efe-3cd9-4942-a132-5ebebb51235a","resolution":{"observed_at":"2026-08-06T21:11:58.341892Z","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":"2026-08-06T21:11:58.406457Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.406457Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:1c940125a70f0bdb3dc91e57ed0689ef1aeb8c79b434bd81248c34a47370fa2b","observation_id":"4d4c528b-3448-4f4e-a6e4-10b725406e4e","resolution":{"observed_at":"2026-08-06T21:11:58.406457Z","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":"2026-08-06T21:11:59.338106Z","title":"Repvgg: Making vgg-style convnets great again","venue":null,"work_id":"f7c184ca-e507-4f53-aa7b-e2d6e14f807b","year":2021},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.456539Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:fdd0c3befcd741be5cc954c5a108fd01dde7e9362289bf3cf95c6baf1ee8d238","observation_id":"5a21a850-ee66-4250-a622-62f315ce35d5","resolution":{"observed_at":"2026-08-06T21:11:59.340751Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.02105","last_updated":"2024-02-03T10:00:11Z","snapshot_observed_at":"2026-07-06T17:24:49.522453Z","submitted_at":"2024-02-03T10:00:11Z","title":"ParZC: Parametric Zero-Cost Proxies for Efficient NAS","version":1},"cited_work":{"arxiv_id":"2402.02105","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.02105","snapshot_observed_at":"2026-08-06T21:11:58.957412Z","title":"ParZC: Parametric Zero-Cost Proxies for Efficient NAS","venue":"cs.CV","work_id":"ead330a1-1410-4509-8749-9579dd564809","year":2024},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.621110Z"},"links":{"cited_paper":"/paper/2402.02105","citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:1b4cb0f82867b99f2eca6660a791b01f953f4e964651261a092e1a69b894031e","observation_id":"5f832736-66e5-4f97-833d-660b533a5db2","resolution":{"observed_at":"2026-08-06T21:11:58.962414Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2001.00326","last_updated":"2020-01-15T12:38:55Z","snapshot_observed_at":"2026-08-08T12:15:50.581786Z","submitted_at":"2020-01-02T05:28:26Z","title":"NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.00326","snapshot_observed_at":"2026-08-06T21:11:58.717299Z","title":"Nas-bench-201: Extending the scope of reproducible neural architecture search","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.717299Z"},"links":{"cited_paper":"/paper/2001.00326","citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:f0c24a0dfaccb7789a32f9cf3fca9b93355881224c8c5bde0d969041f148fd48","observation_id":"b16e3f2c-cd57-42be-99de-981ccd765ed1","resolution":{"observed_at":"2026-08-06T21:11:58.717299Z","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":"2026-08-06T21:11:59.331057Z","title":"Pace: A parallelizable computation encoder for directed acyclic graphs","venue":null,"work_id":"5f4829bb-f62e-4561-8f84-c4366d102a32","year":2022},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.720478Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:a1a86b620b08b164091dd628b907c7f11a30a4fcd5217b92c1fd4b052204b94f","observation_id":"04a727eb-7e2e-4c28-91a6-ba388ead1689","resolution":{"observed_at":"2026-08-06T21:11:59.333462Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-06T21:11:58.723065Z","title":"An image is worth 16x16 words: Trans- formers for image recognition at scale","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.723065Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:a8924cb45861c082b52b7129071a680f32c6a0d1e9a96d7cfb62b98cf40d1171","observation_id":"9a8238b0-2f04-44c7-9368-2f46277e21c9","resolution":{"observed_at":"2026-08-06T21:11:58.723065Z","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":"2026-08-06T21:11:59.323615Z","title":"Brp-nas: Prediction-based nas using gcns","venue":null,"work_id":"572f2c7b-cd5d-4220-be19-af024ab01bbb","year":2020},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.725650Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:b65e02ed8ffc50904e512e29a1d55f19fc268bed997cb9bbe4202a2048f9e5c9","observation_id":"d031d8eb-16e1-4129-8853-691fa2e2ae6a","resolution":{"observed_at":"2026-08-06T21:11:59.325984Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2012.09699","last_updated":"2021-01-24T09:38:54Z","snapshot_observed_at":"2026-08-05T19:35:00.334774Z","submitted_at":"2020-12-17T16:11:47Z","title":"A Generalization of Transformer Networks to Graphs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.09699","snapshot_observed_at":"2026-08-06T21:11:58.728347Z","title":"A general- ization of transformer networks to graphs","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.728347Z"},"links":{"cited_paper":"/paper/2012.09699","citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:3cec9bb611efd4c9f012d7acac64f2a19ca9adcbe325b0df9df4cfade5367746","observation_id":"d8d25d2a-ac15-4ef8-8b6f-0bc9846faa7f","resolution":{"observed_at":"2026-08-06T21:11:58.728347Z","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":"2026-08-06T21:11:59.316076Z","title":"Neural topological ordering for computation graphs","venue":null,"work_id":"043b28a2-590f-42e1-bbd4-17fcc2809776","year":null},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.730859Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:f53770a2f853d8d57792c80537d7a74b93fe5ff49a99251d5a15b27c3a8868f9","observation_id":"734d2a02-6a7b-44a6-b9ea-8f01fd164fe9","resolution":{"observed_at":"2026-08-06T21:11:59.318835Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.308381Z","title":"Neural message passing for quantum chemistry","venue":null,"work_id":"e7acbe2b-33a4-4c67-9f5d-df49a4547567","year":2017},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.733652Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:f995ebb478a38a9889e3202830ecd3672b5220aa7512699d2e5ddc72cdbe2c32","observation_id":"dadcc8f9-62ba-4d9e-b470-66a9c15e7623","resolution":{"observed_at":"2026-08-06T21:11:59.311088Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1706.02677","last_updated":"2018-04-30T21:53:41Z","snapshot_observed_at":"2026-08-09T05:23:26.365677Z","submitted_at":"2017-06-08T16:51:53Z","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.02677","snapshot_observed_at":"2026-08-06T21:11:58.736093Z","title":"Accurate, large mini- batch sgd: Training imagenet in 1 hour","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.736093Z"},"links":{"cited_paper":"/paper/1706.02677","citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:57ea4d5a83316c16e2bc7f0d9f25fea57109c197d7fe1659ea6bed3edac1deb3","observation_id":"514f6e6f-21f5-45ee-8d50-c788af746e95","resolution":{"observed_at":"2026-08-06T21:11:58.736093Z","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":"2026-08-06T21:11:59.301285Z","title":"Cmt: Convolutional neural networks meet vision transformers","venue":null,"work_id":"3c0cfc35-c10e-4925-8873-d106d987dc47","year":2022},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.739097Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:5d6efd4d130f520e274433f92e8033cfe06772010d1e3121c4389f96d5eab411","observation_id":"3e0b9753-082a-488c-94ef-2a7cf51e073d","resolution":{"observed_at":"2026-08-06T21:11:59.303796Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.294075Z","title":"Inductive representation learning on large graphs","venue":null,"work_id":"ca840278-ab7e-4c5a-b699-ffa001fc90ca","year":2017},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.742136Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:affef700fcd4ef3f9b966b356b0f4c878acbcef79d265230e926fa672c057cd0","observation_id":"7961f10f-17eb-49dd-a3c9-8285a7c7d672","resolution":{"observed_at":"2026-08-06T21:11:59.296536Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.286619Z","title":"Flowerformer: Empowering neural architecture encod- ing using a flow-aware graph transformer","venue":null,"work_id":"0746e61f-fc16-4647-be3d-5ac3bafa6951","year":2024},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.744448Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:c567fba744e32debca611ef166138740e9c597457741044011eda34f26c8cbe5","observation_id":"6705a868-e3e1-44a2-824b-61fa8dafe499","resolution":{"observed_at":"2026-08-06T21:11:59.289214Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.278257Z","title":"Cap: a context-aware neural predictor for nas","venue":null,"work_id":"cbe8a0de-95cd-428e-9cd8-7e3adb0acba3","year":2024},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.746766Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:344d399ef8208d231c51b24bfb7da22ef15e092b303e46ec69f49b622f3630ef","observation_id":"f79e7810-4465-41e4-888d-148cd613b564","resolution":{"observed_at":"2026-08-06T21:11:59.281372Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.271005Z","title":"Graph masked au- toencoder enhanced predictor for neural architecture search","venue":null,"work_id":"ef563347-1dcb-4824-88dc-3125db482877","year":2022},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.749826Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:95c6232a1fa28959e56d4acc736b05595f8cd5a595fe3fb2f7fb799e2f882273","observation_id":"96b08366-6b40-43c7-9f24-90800af498ac","resolution":{"observed_at":"2026-08-06T21:11:59.273472Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.263313Z","title":"A learned performance model for tensor processing units","venue":null,"work_id":"5c657ec1-d397-452d-b675-6dd3967a3bb5","year":null},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.752167Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:4c9b60bd12958ac9ecc4928e7b1c1ba396a8059ec5c39648d0d295a52540930e","observation_id":"495aedcc-e7e9-4ce9-a232-c6f6504279a5","resolution":{"observed_at":"2026-08-06T21:11:59.266278Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.255265Z","title":"Semi-supervised classi- fication with graph convolutional networks","venue":null,"work_id":"5ac6cea5-925c-40b6-9367-aed83d3bf713","year":2016},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.754833Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:06addfc2730c1ff67c3370bc621917fece3690605e29bb222b45c25a2c8b80c0","observation_id":"23100c7c-3041-4609-9175-1a7a8838800e","resolution":{"observed_at":"2026-08-06T21:11:59.258273Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.247764Z","title":"Answering complex queries in knowledge graphs with bidi- rectional sequence encoders","venue":null,"work_id":"a52bc980-e0b2-4e00-afba-5ad5ddb8156c","year":null},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.757656Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:c021ca3daac5e2f7bcb4109e4547b4ea721748b0f64ad4e0b2e3be263779903c","observation_id":"c053f3df-f119-4a26-8d90-b9609cd23e28","resolution":{"observed_at":"2026-08-06T21:11:59.250399Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.240306Z","title":"Learning multiple layers of features from tiny images, 2009","venue":null,"work_id":"f39bf6a8-a8f2-4c05-8410-7d9f37a056f6","year":2009},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.760323Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:b0e9017416077149202c7bdd78dfd9d57147c34bbc41f957350c340a90e73c1f","observation_id":"44d80921-4cfc-426c-b986-d86717f7beb5","resolution":{"observed_at":"2026-08-06T21:11:59.242783Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.232842Z","title":"Neural graph em- bedding for neural architecture search","venue":null,"work_id":"be740964-6f1a-4c72-947b-93b9aecb77d4","year":2020},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.762637Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:e01362f9f267bafa78103a237fa4db6dc980b7ae0f31150d941172448436e7d1","observation_id":"0d0ac11f-b65c-45b0-a780-98575865b737","resolution":{"observed_at":"2026-08-06T21:11:59.235504Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.225770Z","title":"Progressive neural architecture search","venue":null,"work_id":"da560404-48aa-4eed-893a-7a0c77249deb","year":2018},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.765304Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:a7b6e1ca041e4a381ef0f7870ca36d34244bfd2af5a360186f526102de8b4563","observation_id":"5bdfde9c-105d-4b68-a91d-a8cbdac5ceea","resolution":{"observed_at":"2026-08-06T21:11:59.228241Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.217841Z","title":"Nnlqp: A multi-platform neural network la- tency query and prediction system with an evolving database","venue":null,"work_id":"068441cf-b483-4cbe-98d6-a3f473c0a3ee","year":2022},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.767522Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:041ddedd23e6af2303df78b2c29d9cc46835a139d37d97ccf74683cb76d3523c","observation_id":"84cba2a2-65a4-49c4-9028-31394ef5fc36","resolution":{"observed_at":"2026-08-06T21:11:59.220612Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1608.03983","last_updated":"2017-05-03T16:28:09Z","snapshot_observed_at":"2026-07-06T05:06:55.589962Z","submitted_at":"2016-08-13T13:46:05Z","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1608.03983","snapshot_observed_at":"2026-08-06T21:11:58.770088Z","title":"Sgdr: Stochas- tic gradient descent with warm restarts","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.770088Z"},"links":{"cited_paper":"/paper/1608.03983","citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:cd09655d194560f694322fb5a6b312fb21e1f87765ba27169415f1c25627a342","observation_id":"cda97b8f-95bd-4785-8819-cd0664cb6da4","resolution":{"observed_at":"2026-08-06T21:11:58.770088Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-09T20:34:52.923500Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-06T21:11:58.773130Z","title":"Decoupled weight decay regularization","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.773130Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:60dc83f36cb339030dfae7d9f3485ab01d48689030f30e33e3708535e3b367a3","observation_id":"91b84355-d2ca-48ef-905c-23293a2a7e05","resolution":{"observed_at":"2026-08-06T21:11:58.773130Z","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":"2026-08-06T21:11:59.210773Z","title":"Tnasp: A transformer-based nas predictor with a self- evolution framework","venue":null,"work_id":"1f827a14-cb6f-4936-977f-67edf168a67b","year":2021},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.775632Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:7f53a234e2b21f8f89478b3351bc0c63330ed2d1abd32473820ab4e11da89dc4","observation_id":"02e4abb2-4ce6-4e40-b9be-7c28305d83f6","resolution":{"observed_at":"2026-08-06T21:11:59.213189Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.203006Z","title":"Pinat: A permutation invari- ance augmented transformer for nas predictor","venue":null,"work_id":"39fde591-7260-4475-99d7-a8a48f2c98bf","year":2023},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.778358Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:0fac998173fdaefa17f6519657bf3ad64805110db0e52ed20f321149a44c45b1","observation_id":"ceeadd6b-7360-4606-b18e-fb3b33281ba8","resolution":{"observed_at":"2026-08-06T21:11:59.205869Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.195241Z","title":"Neural architecture optimization","venue":null,"work_id":"a374ce02-2ac1-4c71-a61b-dfd73d663061","year":2018},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.780761Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:d68885e1e8b96a9ab1f3360b82c03d4aff76f234c74bee8a5013992da113207f","observation_id":"f20e144b-6fba-454a-a260-d2e29ff80823","resolution":{"observed_at":"2026-08-06T21:11:59.197925Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.187871Z","title":"Semi-supervised neural architecture search","venue":null,"work_id":"f823b775-89cc-4eaf-b6c8-6c8870fca413","year":2020},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.783056Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:c897a8b0f5580438daf81ffa5b9e754ec673f158316422dadd1e8a16c0a24aab","observation_id":"7536d73c-31b9-4ad1-9f5f-ce258b40fe2d","resolution":{"observed_at":"2026-08-06T21:11:59.190555Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.180215Z","title":"Transformers over directed acyclic graphs","venue":null,"work_id":"2d05af89-a684-45de-ab4b-50cf4f9a2266","year":2023},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.785485Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:26d212790ee9ac09148fcc1c691175e8b167b40cf8a9e9f9925de5d424dcac2a","observation_id":"b0e62bcb-e025-4bcd-bca8-0dabdaa51469","resolution":{"observed_at":"2026-08-06T21:11:59.183124Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.172525Z","title":"A generic graph-based neural architecture encoding scheme for predictor-based nas","venue":null,"work_id":"58180d0a-5716-4b6c-8060-4a7bfa77fe11","year":2020},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.787585Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:53968a67cb67f55bf22f62778e758686f28bfadf2490d7c9a40da44641dd6e44","observation_id":"3f35c706-76da-4b56-ba61-ca364c7e6cc1","resolution":{"observed_at":"2026-08-06T21:11:59.175301Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.165282Z","title":"Ta-gates: An encoding scheme for neu- ral network architectures","venue":null,"work_id":"93d7de41-a49e-4c90-bd1e-07278049e352","year":2022},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.790458Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:80fdb2bd353cceb93465f7e53836d06489297e2105427a4334e099407c7486fa","observation_id":"85c4b94c-954f-483a-ad16-22c8f18d70c5","resolution":{"observed_at":"2026-08-06T21:11:59.167641Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.158113Z","title":"Acceleration of stochastic approximation by averaging","venue":null,"work_id":"69dac066-e2b9-4eeb-981a-f7d4719675d0","year":1992},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.792765Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:570a2dc1e78c72009cbafe3ab787d58125f21309f39025e593efc791f3c91ff8","observation_id":"d94be2d4-628f-481f-9795-a12f9229d7fe","resolution":{"observed_at":"2026-08-06T21:11:59.160660Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.150620Z","title":"Estimates of the regression coefficient based on kendall’s tau","venue":null,"work_id":"9ee04404-c847-4cc2-8573-21682b9a2b71","year":1968},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.795126Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:f300ff374c78c2add4580f00707f008b716368cc93b75f166c9fc92622fd6fb6","observation_id":"cc5d4f63-c1bf-4756-8e26-0f517a931f31","resolution":{"observed_at":"2026-08-06T21:11:59.153325Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.143278Z","title":"Bridging the gap between sample-based and one-shot neural architecture search with bonas","venue":null,"work_id":"5a37c00c-0706-4b9e-bfde-38e5a004c370","year":null},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.797503Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:ac710d9a57363500d4e2c6ffef27fc617482c8e492413e5a72ea66928f8f65c5","observation_id":"176111b2-b9a2-42f6-bcce-02df02b4cb85","resolution":{"observed_at":"2026-08-06T21:11:59.146093Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.136104Z","title":"Going deeper with convolutions","venue":null,"work_id":"4397d449-9bbd-4c51-a303-3359daf1b854","year":2015},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.800067Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:1b2f077aaaf5b182679ae1590f2072ff953f7496d37806b7c5beb7dc726cbc61","observation_id":"0e24ed5c-ed43-445c-b1db-f82085584182","resolution":{"observed_at":"2026-08-06T21:11:59.138538Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.07965","snapshot_observed_at":"2026-08-06T21:11:58.802805Z","title":"Directed acyclic graph neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.802805Z"},"links":{"cited_paper":"/paper/2101.07965","citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:11aab49d13e62e41109101e7a47e58bb15b8616b86b0448163effdd4751cd1db","observation_id":"6ba1561c-64e4-443e-aa7f-af0b9db91c99","resolution":{"observed_at":"2026-08-06T21:11:58.802805Z","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":"2026-08-06T21:11:59.129129Z","title":"Attention is all you need","venue":null,"work_id":"abdedb2d-c619-482c-9ed9-275c5eec363c","year":2017},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.805180Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:6deef8d0763b623773bfd67e6cd325188ee53bac8ac7152708c1990ef05b5c9e","observation_id":"c6f1c11c-1360-4ac1-bc7e-7d02c9c66e78","resolution":{"observed_at":"2026-08-06T21:11:59.131483Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.122140Z","title":"Graph at- tention networks","venue":null,"work_id":"2e68560c-b865-46a1-aacd-128b862764dc","year":2018},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.807659Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:e72225067bdb825a089541eba09d60aabc1abfcc5f8dfc21a0cf6441ed81102b","observation_id":"6d745bc4-eb5b-4457-8fbc-d8b543daae98","resolution":{"observed_at":"2026-08-06T21:11:59.124464Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.114439Z","title":"Neural predictor for neural architecture search","venue":null,"work_id":"506995a2-404f-41dc-8796-ec256da0e6c0","year":2020},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.810329Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:48e7d965466102434dca01e7717477ec1b226cab557f96bf0c24ce3f2956e270","observation_id":"b586f910-b09e-4820-a2f0-41123dff6d4a","resolution":{"observed_at":"2026-08-06T21:11:59.117417Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.107383Z","title":"Bananas: Bayesian optimization with neural architectures for neural architecture search","venue":null,"work_id":"a91c4a89-a38f-43b9-8b28-d2b8da5ba945","year":2021},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.812723Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:c938f9d441800a032ed9b412172257ac6c1793522dc51ebb10643689ab9dd34c","observation_id":"7151e4bf-c734-47e3-9c93-fe63d7dce1d0","resolution":{"observed_at":"2026-08-06T21:11:59.109906Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1901.10430","last_updated":"2019-02-22T23:46:38Z","snapshot_observed_at":"2026-07-06T07:29:49.559045Z","submitted_at":"2019-01-29T18:01:35Z","title":"Pay Less Attention with Lightweight and Dynamic Convolutions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1901.10430","snapshot_observed_at":"2026-08-06T21:11:58.814873Z","title":"Pay less attention with lightweight and dy- namic convolutions","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.814873Z"},"links":{"cited_paper":"/paper/1901.10430","citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:32c4eeb42315cbbe5359260eeeaea1a20714c64157cc52462feac749511397ff","observation_id":"2096e4f0-14bf-49c3-88a5-262bd07951ee","resolution":{"observed_at":"2026-08-06T21:11:58.814873Z","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":"2026-08-06T21:11:59.100335Z","title":"Representing long- range context for graph neural networks with global atten- tion","venue":null,"work_id":"b11be403-966c-41ac-8c08-060103ed51c2","year":2021},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.817332Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:6b7a7eb2d4b1f440cfebbebc4279981d3f3d0d1a5c1a0f201845980ee3ee931b","observation_id":"f47681c2-b79b-4824-9c8c-cf85f9ff1bad","resolution":{"observed_at":"2026-08-06T21:11:59.102897Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.093230Z","title":"How powerful are graph neural networks? In International Conference on Learning Representations, 2018","venue":null,"work_id":"ac60a737-112a-4433-a3a4-6738a4aea863","year":2018},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.819585Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:5be7f4a221b6bc6b58f1dd056787441a97a30bb228c98b16e63b0c6de5f2bd4a","observation_id":"9a8c1917-68a9-4ac9-b2a8-0945d6dcb56a","resolution":{"observed_at":"2026-08-06T21:11:59.095875Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.086263Z","title":"Parcnetv2: Oversized kernel with enhanced attention","venue":null,"work_id":"2cb4346c-f8c5-4c7c-8295-9301722f0b22","year":2023},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.821820Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:7decafe05704914dd17c18c85d600fded128f17e05fce4a82149ccfaa37907ee","observation_id":"a358c9d9-a32a-4a57-8ca2-b3fcbc169bbf","resolution":{"observed_at":"2026-08-06T21:11:59.088718Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.078744Z","title":"Renas: Relativistic eval- uation of neural architecture search","venue":null,"work_id":"b5e42d92-102a-4aae-a293-231d972315c6","year":2021},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.824102Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:f02dbe222b6dcca4cc8432892f119699e96257b2afbf8f0c6170bb77e1e8c7e9","observation_id":"7d76eeca-af22-4e09-96cb-d60675d4ff12","resolution":{"observed_at":"2026-08-06T21:11:59.081331Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.071104Z","title":"Does unsupervised architecture representation learning help neural architecture search? Advances in Neural Information Processing Systems, 33:12486–12498, 2020","venue":null,"work_id":"5dd5ab24-9b24-4f7d-a5d1-181095934d93","year":2020},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.826432Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:84742b14e1b819031a366cacbe871a080cd80b55bf4bff9436693bc84c792b44","observation_id":"148e74f5-445f-43e6-92be-6fa0e1218b35","resolution":{"observed_at":"2026-08-06T21:11:59.074180Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.063721Z","title":"Nar-former: Neural architecture representation learning towards holistic attributes prediction","venue":null,"work_id":"8cb28baf-3c1d-4e92-8fb3-6ccdadfcf674","year":2023},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.828987Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:3b4d1aaebd191bb560ef58fc91066fb8f0c661301e1e8d6f446eccc545b63dd5","observation_id":"d0e03a8e-c05d-4ee2-81b6-ba435c161fc9","resolution":{"observed_at":"2026-08-06T21:11:59.066301Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.056186Z","title":"Nar-former v2: Rethinking transformer for uni- versal neural network representation learning","venue":null,"work_id":"ff91bd70-5a53-4f1a-b22d-f92dcd055c35","year":2024},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.831679Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:da6d920a14f55dbcfbc85ed72adb98ba0bb594c4a8a4ecff8003a76c1b86a716","observation_id":"c5008702-7ff3-401f-9325-a125db08cc7a","resolution":{"observed_at":"2026-08-06T21:11:59.058746Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.048858Z","title":"Nas-bench-101: Towards reproducible neural architecture search","venue":null,"work_id":"8a5faad7-3c43-41a6-b214-ef57187747e8","year":null},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.834093Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:89f1b739dab02b52d146c7fe2ebbafa1813f83e44afa9b6136bc7f3fd5665f0e","observation_id":"7843c696-39ba-452a-87c4-c8ca67aea055","resolution":{"observed_at":"2026-08-06T21:11:59.051455Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.040984Z","title":"Do transformers really perform badly for graph representation? In Thirty-Fifth Conference on Neural Information Process- ing Systems, 2021","venue":null,"work_id":"a8668d8e-b5d7-4a1f-a082-cf761c4d1d95","year":2021},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.836930Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:b5000d9388429fd649c9343ec8fbcc9cee980dce5df880217f33bc60b5bda131","observation_id":"4169bfa9-461e-494e-872f-cae618adeecd","resolution":{"observed_at":"2026-08-06T21:11:59.044128Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.033191Z","title":"Graph structure of neural networks","venue":null,"work_id":"d1e7b43c-9273-4ef9-bc32-9faaae1535f0","year":null},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.839751Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:3fad9d798c9ddebc9ad3cbe5ab23614169ac08910acf008d03eea353dc9e5fcd","observation_id":"aeff0ea2-7b1d-4f47-996c-efdd427cb369","resolution":{"observed_at":"2026-08-06T21:11:59.035958Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.05749","last_updated":"2020-12-18T18:01:04Z","snapshot_observed_at":"2026-07-06T07:07:47.487337Z","submitted_at":"2018-10-12T22:21:05Z","title":"Graph HyperNetworks for Neural Architecture Search","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.05749","snapshot_observed_at":"2026-08-06T21:11:58.842536Z","title":"Graph hy- pernetworks for neural architecture search","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.842536Z"},"links":{"cited_paper":"/paper/1810.05749","citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:ad8ca62d292d51ac6832553f0417252737e1ee6619b472ace81ee04201c389f0","observation_id":"776ad859-bfca-4294-b2e9-b9d09daf7081","resolution":{"observed_at":"2026-08-06T21:11:58.842536Z","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":"2026-08-06T21:11:59.024517Z","title":"Nn-meter: Towards accurate latency prediction of deep-learning model inference on diverse edge devices","venue":null,"work_id":"eee59d06-9b54-4deb-89cc-2dc1c7e637a8","year":2021},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.845145Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:3efe6bcbc6626334cf621b5c771227b794af25ea553d70a466b26378eabd82cd","observation_id":"2a11d187-babb-4e4b-a6b7-41b8b5e9a05e","resolution":{"observed_at":"2026-08-06T21:11:59.027576Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.016519Z","title":"directed WL test","venue":null,"work_id":"b0ba6f28-3625-44bc-97be-62a5e92ef38b","year":null},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.847470Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:d593765629fa6c1924b939e3f11685078266fc733697466fdd8115f8ea41325c","observation_id":"ef5c0b52-85cb-4674-b597-47b8c2a618cb","resolution":{"observed_at":"2026-08-06T21:11:59.019251Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.008643Z","title":"For accuracy prediction, we show the experiment settings on NAS-Bench-101 in Section 2.1.1 and NAS- Bench-201 in Section 4.1","venue":null,"work_id":"9a415ab5-b4e8-41ca-818f-3c39daa4b8b0","year":2023},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.850571Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:ec683ecd670ef4806be8f8824dbbf732cf1c7ad007a0c6180e8034013b540167","observation_id":"5e86d9fa-5379-4158-87c6-4d87a7dc51d8","resolution":{"observed_at":"2026-08-06T21:11:59.011252Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:59.000495Z","title":"Ablation on hyperparameters This work adopts a Transformer as the backbone, and the hyperparameters of Transformers have been well-settled in previous research","venue":null,"work_id":"8eb5d476-16f2-4f14-8160-cf1d486d777c","year":null},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.853654Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:e26b20b88055d03dbdfd5dad1a381d726727b5aca7df0badaaaddfd8f64ffe3b","observation_id":"4a1cef73-ac1d-4d04-b516-e4dcf65d4ec0","resolution":{"observed_at":"2026-08-06T21:11:59.003323Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:11:58.992798Z","title":"Theoretical Analysis Our ASMA method has less or equal computational com- plexity than the vanilla attention","venue":null,"work_id":"cd658258-f125-4f7c-8bff-8a75920fe990","year":null},"citing_paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:58.856366Z"},"links":{"citing_paper":"/paper/2507.00880"},"observation_digest":"sha256:dbf858fd1536ccaf49a3ce6a8622d23b53a356fe9d68f412747d5524e1238cae","observation_id":"c701c7c7-dec7-4e04-9f94-4b46890f031d","resolution":{"observed_at":"2026-08-06T21:11:58.995423Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.00880","last_updated":"2025-07-01T15:46:18Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T00:16:49.464630Z","submitted_at":"2025-07-01T15:46:18Z","title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation"},"reference_resolution":{"displayed":62,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":13,"verified_exact":1,"verified_fuzzy":48},"total_outbound_references":62},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 62 of 62 outbound references and 0 inbound Pith citation observations for arXiv:2507.00880."}