{"as_of":"2026-08-07T07:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:246bd33482095456625bf6f3e4f3b291ba9407b8712a093dfee8c3e6a4390304","coverage":[{"denominator":40,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":40,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T18:23:12.890108Z","state":"measured"},{"denominator":40,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":40,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+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/2512.05906/citation-record","integrity":"/paper/2512.05906/integrity","json":"/paper/2512.05906/citation-record.json","paper":"/paper/2512.05906"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T18:23:09.233569Z","title":"Cambridge University Press, 2006","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:09.233569Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:c880657c9b1a49f18ccba7e1d9cda419d73f0adcf3408c521f89555aaf6442fd","observation_id":"683da58c-e37a-4079-a408-a95b2c1acd32","resolution":{"observed_at":"2026-08-03T18:23:09.233569Z","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":"2026-08-03T18:23:09.277773Z","title":"Supervised learning in spiking neural networks with synaptic delay-weight plasticity.Neurocomputing, 409:103–118, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:09.277773Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:668dfc09bcc2f205fb581289d4b4f1e5e04fab1e670774303d88fe54b17f2825","observation_id":"6577c55b-f6c9-4918-986f-0475593fcb14","resolution":{"observed_at":"2026-08-03T18:23:09.277773Z","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":"2026-08-03T18:23:09.380758Z","title":"Homeostatic bidirec- tional plasticity in upbound and downbound micromodules of the olivocerebellar system","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:09.380758Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:0f6cc2441131e9f60bf5c3b8f0d98c1dc850fa261fdda7cb4b32e39be6d902b9","observation_id":"b776fa08-3a05-443a-81ee-4b3f02ad8898","resolution":{"observed_at":"2026-08-03T18:23:09.380758Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.14606","last_updated":"2026-08-03T02:53:27Z","snapshot_observed_at":"2026-08-06T23:27:26.110991Z","submitted_at":"2024-03-21T17:55:16Z","title":"The Elements of Differentiable Programming","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.14606","snapshot_observed_at":"2026-08-03T18:23:09.461381Z","title":"The elements of differentiable programming","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:09.461381Z"},"links":{"cited_paper":"/paper/2403.14606","citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:c711e7a5e14b5e09a4e248e1b71a76a0ae82ec1a1dc1f84655349e4e2340236f","observation_id":"68cdb978-8fbb-4761-bce2-418ccbb01a03","resolution":{"observed_at":"2026-08-03T18:23:09.461381Z","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":"2026-08-03T18:23:09.513551Z","title":"Trick- ing ai chips into simulating the human brain: A detailed performance analysis.Neuro- computing, 598:127953, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:09.513551Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:35d98dddd908b0a9651b538c7abef85a09370d68f503790022c4c3ba4d6b5886","observation_id":"625483ed-776c-4c0c-a0d5-a33cf0a75372","resolution":{"observed_at":"2026-08-03T18:23:09.513551Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.05106","last_updated":"2024-02-22T09:13:35Z","snapshot_observed_at":"2026-07-06T16:44:59.350633Z","submitted_at":"2023-11-09T02:47:38Z","title":"A differentiable brain simulator bridging brain simulation and brain-inspired computing","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.05106","snapshot_observed_at":"2026-08-03T18:23:09.581857Z","title":"A differentiable brain simulator bridging brain simulation and brain- inspired computing.arXiv preprint arXiv:2311.05106, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:09.581857Z"},"links":{"cited_paper":"/paper/2311.05106","citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:69cffbdad8701c9a73cd282442a9449bdaba9a70eeffb31ade0ec03c3b8886a1","observation_id":"5d3fd0ca-b7de-4e63-8076-541c3f1709b6","resolution":{"observed_at":"2026-08-03T18:23:09.581857Z","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":"10.1101/2024.08.21.608979","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Kadhim, Matthijs Pals, Jonas Beck, Ziwei Huang, Manuel Gloeckler, Janne K","venue":"bioRxiv (Cold Spring Harbor Laboratory)","work_id":"c6a24e42-e7c4-4021-8d49-7aa1e39a3d15","year":2024},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:09.657071Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:5e3e188d5367ccf79c343a2aa5871c541c5e0de88a253557c5382c02511ac7a4","observation_id":"fe387d95-eec8-4532-895e-75f8a3f4cb64","resolution":{"observed_at":"2026-08-03T18:23:23.531368Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-03T18:23:09.718771Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:09.718771Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:12cd81b67c771dc53f8d135046192e8cf6e92a8b14de7f9a5b7c7425c8bf20e5","observation_id":"81d6f7d7-6a67-4bf3-99f9-d65821d4c7fc","resolution":{"observed_at":"2026-08-03T18:23:09.718771Z","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":"2026-08-03T18:23:09.796699Z","title":"Saunders, Hassaan Khan, Devdhar Patel, Darpan T","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:09.796699Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:4fb38474eabfde4edc6a0ee5790304e5655fffcc0de70626d94396adb4a03d32","observation_id":"08612788-e4b7-4410-ab2d-af731447008e","resolution":{"observed_at":"2026-08-03T18:23:09.796699Z","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":"2026-08-03T18:23:09.856584Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:09.856584Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:dc2a0f6c7c30984df2745b6a533a745a53e93c250f011294b311b1b1eacfe66e","observation_id":"3bfd1ae4-1b9e-41db-b119-b28c63d3e727","resolution":{"observed_at":"2026-08-03T18:23:09.856584Z","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":"2026-08-03T18:23:09.919750Z","title":"Nengodl: Combining deep learning and neuromorphic modelling methods.Neuroinformatics, 17(4):611–628, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:09.919750Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:e557ed94d98f79730bf4a069c41d3ad979a1e2d58bbdcbaf1bf8a2e9c292ba17","observation_id":"573175fa-a3ad-42cf-990d-a27d0acaabe8","resolution":{"observed_at":"2026-08-03T18:23:09.919750Z","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":"2026-08-03T18:23:10.019506Z","title":"Muir, Felix Bauer, and Philipp Weidel","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:10.019506Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:39b43dee791d7ad3cfd95ba4808a5a37f6c64d55305181757c61989c04452d06","observation_id":"f455f23f-1b8d-49d6-8db8-65b50ebdc44f","resolution":{"observed_at":"2026-08-03T18:23:10.019506Z","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":"2026-08-03T18:23:10.243183Z","title":"Spikingjelly","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:10.243183Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:27560310366e484d7cdbdcc959a6d719678b2710ec5905967ec8150de330d2eb","observation_id":"502a367c-76b2-4b19-a0b6-7d9a372c10b3","resolution":{"observed_at":"2026-08-03T18:23:10.243183Z","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":"2026-08-03T18:23:10.313945Z","title":"Norse - A deep learning library for spiking neural networks, January 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:10.313945Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:7d6a4d09a1c4f1be8d08d3c530d023f0ac732e2d25ccd7beb126cd848dbf647b","observation_id":"31f3f63a-2a72-48c5-bcd0-b59132b9b509","resolution":{"observed_at":"2026-08-03T18:23:10.313945Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12894","last_updated":"2023-08-13T04:51:16Z","snapshot_observed_at":"2026-08-01T22:24:18.683633Z","submitted_at":"2021-09-27T09:28:04Z","title":"Training Spiking Neural Networks Using Lessons From Deep Learning","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12894","snapshot_observed_at":"2026-08-03T18:23:10.388178Z","title":"Training spik- ing neural networks using lessons from deep learning.arXiv preprint arXiv:2109.12894, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:10.388178Z"},"links":{"cited_paper":"/paper/2109.12894","citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:7a153b224cac454716dd70694cc8f4135a511877697e62054993ddaa65e944ba","observation_id":"06b53d6e-4435-4ac2-89a2-3ba8b9fbf124","resolution":{"observed_at":"2026-08-03T18:23:10.388178Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.18994","last_updated":"2024-02-29T09:46:44Z","snapshot_observed_at":"2026-07-06T17:37:17.675101Z","submitted_at":"2024-02-29T09:46:44Z","title":"Spyx: A Library for Just-In-Time Compiled Optimization of Spiking Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.18994","snapshot_observed_at":"2026-08-03T18:23:10.458532Z","title":"Spyx: A library for just-in-time compiled opti- mization of spiking neural networks.arXiv preprint arXiv:2402.18994, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:10.458532Z"},"links":{"cited_paper":"/paper/2402.18994","citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:0d089cb11091262ee938017b21b3a0855a39a60052f2853761cad26dbbca9c30","observation_id":"3fe79449-27b4-40f5-b4f0-a1e8091db009","resolution":{"observed_at":"2026-08-03T18:23:10.458532Z","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":"2026-08-03T18:23:10.606150Z","title":"Event-based backpropagation can compute exact gradients for spiking neural networks.Scientific Reports, 11(1):12829, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:10.606150Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:849bc81065af6a542feaf7a3ba348521913d70d17b953c0758a3d80ed7e10034","observation_id":"e1574b4d-dc84-493c-8004-81f05eb653c0","resolution":{"observed_at":"2026-08-03T18:23:10.606150Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.19165","last_updated":"2025-04-16T15:42:10Z","snapshot_observed_at":"2026-07-06T18:07:23.217029Z","submitted_at":"2024-04-30T00:02:34Z","title":"DelGrad: Exact event-based gradients for training delays and weights on spiking neuromorphic hardware","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.19165","snapshot_observed_at":"2026-08-03T18:23:10.745377Z","title":"Delgrad: Exact gradients in spiking networks for learning transmission delays and weights.arXiv preprint arXiv:2404.19165, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:10.745377Z"},"links":{"cited_paper":"/paper/2404.19165","citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:16b1d7bf87d8826b66632f6ce04aa9735152177cef0ad6e5522357d765560bd3","observation_id":"a630b0b3-8740-4255-9994-b6f16e61ae27","resolution":{"observed_at":"2026-08-03T18:23:10.745377Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.16841","last_updated":"2024-01-30T09:27:13Z","snapshot_observed_at":"2026-07-06T17:22:19.869691Z","submitted_at":"2024-01-30T09:27:13Z","title":"jaxsnn: Event-driven Gradient Estimation for Analog Neuromorphic Hardware","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.16841","snapshot_observed_at":"2026-08-03T18:23:10.881585Z","title":"jaxsnn: Event-driven gradient estimation for analog neuromorphic hardware.arXiv preprint arXiv:2401.16841, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:10.881585Z"},"links":{"cited_paper":"/paper/2401.16841","citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:925735396f508549dc9f35d8f2fe66a966f6b0cacc7a088753345ce19191d20f","observation_id":"3c3e2332-fb88-4538-bdce-e1c8693d111f","resolution":{"observed_at":"2026-08-03T18:23:10.881585Z","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":"2026-08-03T18:23:11.044895Z","title":"mlgenn: accelerating snn inference using gpu-enabled neural networks.Neuromorphic Computing and Engineering, 2(2):024002, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:11.044895Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:8348064976f23fd48de814b9c00d1d04e6e1ff2eb95212e5a018db51a6a0bea5","observation_id":"8bdb876f-c01f-4831-bd42-6b2cd989a5a9","resolution":{"observed_at":"2026-08-03T18:23:11.044895Z","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":"2026-08-03T18:23:11.121051Z","title":"Cam- bridge University Press, 2009","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:11.121051Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:4b27225f72b435ecb75c39e5922430b0e3b3cbcdfce6c2fb9e199e4100e02365","observation_id":"ffe67d7c-b4ff-4538-bd2e-fc5a7c15f17b","resolution":{"observed_at":"2026-08-03T18:23:11.121051Z","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":"2026-08-03T18:23:11.235416Z","title":"Arbor—a morphologically-detailed neural net- work simulation library for contemporary high-performance computing architectures","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:11.235416Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:695b3353229d686b7c1cbbd6558abaeb87e5840ceb678ebc3667cfc90ec8c224","observation_id":"a5929ef1-f69f-4f52-9abb-5744e5ce2335","resolution":{"observed_at":"2026-08-03T18:23:11.235416Z","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":"2026-08-03T18:23:11.343524Z","title":"The groq software- defined scale-out tensor streaming multiprocessor: From chips-to-systems architectural overview","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:11.343524Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:0d0b19070dc1b741155cf050ec07943d2a3b5612bcfa92b47c2b4d7dfe7fe2c9","observation_id":"d1c6ab24-0fff-44fe-91b9-223a3e33b104","resolution":{"observed_at":"2026-08-03T18:23:11.343524Z","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":"2026-08-03T18:23:11.466011Z","title":"Eden: a high-performance, general-purpose, neuroml-based neural simula- tor.Frontiers in neuroinformatics, 16:724336, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:11.466011Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:1cab144b81539e3ac995287191f74adfbe6e79a289ec3c385cc9021178ca0bb0","observation_id":"748d0aed-771e-405b-8ad4-119da320080c","resolution":{"observed_at":"2026-08-03T18:23:11.466011Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.07331","last_updated":"2025-06-26T16:08:40Z","snapshot_observed_at":"2026-07-06T20:20:19.257784Z","submitted_at":"2025-01-13T13:44:34Z","title":"Efficient Event-based Delay Learning in Spiking Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.07331","snapshot_observed_at":"2026-08-03T18:23:11.543153Z","title":"Efficient event-based delay learning in spiking neural networks.arXiv preprint arXiv:2501.07331, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:11.543153Z"},"links":{"cited_paper":"/paper/2501.07331","citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:d81d57772c1a205f6f978735430f3a2cfec886b8ff42f48ec23c01109850c622","observation_id":"9fb7736f-fbad-4e26-9de1-82017a34520e","resolution":{"observed_at":"2026-08-03T18:23:11.543153Z","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":"2026-08-03T18:23:11.606929Z","title":"MIT press, 2007","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:11.606929Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:1c890a24b75aefdbb185e65be43b49e97368ef62ff0013e3358ca753f54a8253","observation_id":"10c050c4-05fc-40f9-bd5e-2e52c7eb7f55","resolution":{"observed_at":"2026-08-03T18:23:11.606929Z","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":"2026-08-03T18:23:11.712632Z","title":"Gradient diffusion: Enhancing multicompartmental neuron models for gradient-based self-tuning and homeostatic control.arXiv preprint arXiv:2412.07327, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:11.712632Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:c73c6156b0a01f4499426ec127c5e4abfdfeb68d3469f96f94d3553b6b9ab042","observation_id":"a50840dd-93d9-4fe4-8fa4-77009d858311","resolution":{"observed_at":"2026-08-03T18:23:11.712632Z","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":"2026-08-03T18:23:11.787008Z","title":"Fast and energy-efficient neuromorphic deep learning with first-spike times.Nature machine intelligence, 3(9):823–835, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:11.787008Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:4d3d037278f72e12bcb74c950c5ed8394d6e585a4f94e6aeaba1450d97b40026","observation_id":"451673fb-f362-44b7-a392-8269f1b6abb2","resolution":{"observed_at":"2026-08-03T18:23:11.787008Z","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":"2026-08-03T18:23:11.893770Z","title":"Nest: An environment for neural systems simulations.Forschung und wisschenschaftliches Rechnen, Beitr¨ age zum Heinz-Billing- Preis, 58:43–70, 2001","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:11.893770Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:6452aa2800d78bc529be4e8f6b892bd9625b40ca95d1a73b37fb5604e87c180a","observation_id":"3ba8215d-7ef0-484c-b71e-2daea50f3158","resolution":{"observed_at":"2026-08-03T18:23:11.893770Z","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":"2026-08-03T18:23:12.002357Z","title":"Brian 2- the second coming: spiking neural network simulation in python with code generation","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:12.002357Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:07e498b617bbb814f3f4828a5dbe5988b73d4ad2b816d1e71545125770378a13","observation_id":"59a4e369-e57e-474a-b909-0f69759cc96e","resolution":{"observed_at":"2026-08-03T18:23:12.002357Z","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":"2026-08-03T18:23:12.074736Z","title":"Genn: a code generation framework for accelerated brain simulations.Scientific reports, 6(1):18854, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:12.074736Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:b22c30200a9c3b278b078d4d2712bdc3b63bd55ff119958b49f3d769257fd9a7","observation_id":"2c0e1c9f-9bca-42fc-851c-9833bcfad795","resolution":{"observed_at":"2026-08-03T18:23:12.074736Z","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":"2026-08-03T18:23:12.209023Z","title":"Loss shaping enhances exact gradient learning with eventprop in spiking neural networks.Neuromorphic Computing and Engineering, 5(1):014001, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:12.209023Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:b9f5b7b31707db6032f9174a8f556ad9533d4a942bf4c09a23d7b4b81fd32071","observation_id":"202dd50f-b885-4c3e-82e1-fec7caa29e1a","resolution":{"observed_at":"2026-08-03T18:23:12.209023Z","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":"2026-08-03T18:23:12.305280Z","title":"Fast simulations of highly-connected spiking cortical models using gpus.Frontiers in Computational Neuroscience, 15:627620, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:12.305280Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:0cd88f22d697bdcf0856f7da13eaac011c18835b466430495291db3df0783b8c","observation_id":"d286dcbf-1012-4008-95a0-6ee01d4ec7f3","resolution":{"observed_at":"2026-08-03T18:23:12.305280Z","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":"2026-08-03T18:23:12.450200Z","title":"A proof of a key formula in the error- backpropagation learning algorithm for multiple spiking neural networks","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:12.450200Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:f22982e86c3a23c13c249d55b36b91506f6a188f615ac5724cbb6e136f2ea983","observation_id":"c34d8a88-b991-48b1-b7da-20e944a87c3a","resolution":{"observed_at":"2026-08-03T18:23:12.450200Z","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":"2026-08-03T18:23:12.581246Z","title":"Bgpq: A heap-based priority queue design for gpus","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:12.581246Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:3164b82295a95814cec91be10ad78cc797121e482a8df04da560a22867ab41d9","observation_id":"8b02ff34-8d0b-474a-aa49-0ed4f6832cb3","resolution":{"observed_at":"2026-08-03T18:23:12.581246Z","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":"2026-08-03T18:23:12.651237Z","title":"Tpu v4: An optically reconfigurable supercomputer for machine learning with hardware support for embeddings","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:12.651237Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:777b223033683fc86a5daab4401c2d7640394b56ab3f77c54e6585fea636e6cb","observation_id":"08dcadbb-352c-4826-94c6-742a810838ba","resolution":{"observed_at":"2026-08-03T18:23:12.651237Z","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":"2026-08-03T18:23:12.748232Z","title":"Think fast: A tensor streaming processor (tsp) for accelerating deep learning workloads","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:12.748232Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:890aea97c8e9d5b68875967977a8553ed64d7f3aebdb448a919648b63d0847e8","observation_id":"770c3cb1-ba04-42fb-8722-443ec861b408","resolution":{"observed_at":"2026-08-03T18:23:12.748232Z","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":"2026-08-03T18:23:12.830641Z","title":"Huma: Hetero- geneous, ultra low-latency model accelerator for the virtual brain on a versal adaptive soc","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:12.830641Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:3327af30e8ee4037d08d4748a2cc21930d0d1683f32ec0a9be4010dad5e825b2","observation_id":"3a164481-6655-43df-96b4-8a8c91c90141","resolution":{"observed_at":"2026-08-03T18:23:12.830641Z","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":"2026-08-03T18:23:12.890108Z","title":"Efficient and realistic brain simulation: A review and design guide for memristor-based approaches.Advanced Materials Tech- nologies, page e01587, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:12.890108Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:9cf63e8fac4a13dfba6fd925038081ee36334a820e28df448334f1f8aad1613a","observation_id":"35dfc3a7-f3ba-4f18-a32b-d6e9d8beb485","resolution":{"observed_at":"2026-08-03T18:23:12.890108Z","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":"2026-08-03T18:23:10.125855Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-03T18:23:10.125855Z"},"links":{"citing_paper":"/paper/2512.05906"},"observation_digest":"sha256:ec949a416936808f9213215f41dfec65550b329ea4078e498977b1c82dd0b21f","observation_id":"c0362f53-16dd-4abd-b9ea-34d9aaf024f8","resolution":{"observed_at":"2026-08-03T18:23:10.125855Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2512.05906","last_updated":"2026-07-07T12:56:19Z","latest_version":2,"primary_category":"cs.NE","snapshot_observed_at":"2026-08-06T00:22:38.419572Z","submitted_at":"2025-12-05T17:39:59Z","title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs"},"reference_resolution":{"displayed":40,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":39,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":40},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 0 inbound Pith citation observations for arXiv:2512.05906."}