{"as_of":"2026-08-19T00:43:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1d354dc5e7bbfbc327e17679b4c8daa73565cbc9fdf4c794edc77b0e4fefbab6","coverage":[{"denominator":44,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":44,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T20:45:30.252933Z","state":"measured"},{"denominator":44,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":44,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+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/2505.15840/citation-record","integrity":"/paper/2505.15840/integrity","json":"/paper/2505.15840/citation-record.json","paper":"/paper/2505.15840"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.10780","last_updated":"2023-03-21T16:48:53Z","snapshot_observed_at":"2026-08-16T15:47:02.716779Z","submitted_at":"2023-03-19T22:07:27Z","title":"A Comprehensive Review of Spiking Neural Networks: Interpretation, Optimization, Efficiency, and Best Practices","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.10780","snapshot_observed_at":"2026-08-15T20:45:30.081313Z","title":"A comprehensive review of spiking neural networks: Interpretation, optimization, efficiency, and best practices","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.081313Z"},"links":{"cited_paper":"/paper/2303.10780","citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:56d941e0953565421cae777c4eb56bc77a6a99fb5d0d6df699edf6722ea3abd5","observation_id":"c7e885f2-806d-4c90-a6b1-feb901420deb","resolution":{"observed_at":"2026-08-15T20:45:30.081313Z","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":"2026-08-15T20:45:30.086575Z","title":"Spikformer: When spiking neural network meets transformer","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.086575Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:bc23e2ed6959fe6dae3511f22c4c4c5ad6a68f3faa14030ce099dcc35cccedf7","observation_id":"8e617f3b-1482-4c33-8db9-53dd7f78fc8e","resolution":{"observed_at":"2026-08-15T20:45:30.086575Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.16552","last_updated":"2024-10-08T09:29:01Z","snapshot_observed_at":"2026-08-18T19:06:06.248179Z","submitted_at":"2024-03-25T08:57:27Z","title":"QKFormer: Hierarchical Spiking Transformer using Q-K Attention","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.16552","snapshot_observed_at":"2026-08-15T20:45:30.090539Z","title":"Qkformer: Hierarchical spiking transformer using qk attention","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.090539Z"},"links":{"cited_paper":"/paper/2403.16552","citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:472ae5a8a1594f19f7a82c5bbd196e8332424a84ac37e12b8894ab7605ced812","observation_id":"f9666aa4-9ee1-4f9c-b6c6-aaba5a1ad61d","resolution":{"observed_at":"2026-08-15T20:45:30.090539Z","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":"2026-08-15T20:45:30.095459Z","title":"Spikingformer: Spike-driven residual learning for transformer-based spiking neural network","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.095459Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:dd29acefdd28607253651de3cfdbe2fc9104d4eb9acdfed97e03bbac15315867","observation_id":"e1d64764-18c8-4e12-9b6b-4641a3cdd101","resolution":{"observed_at":"2026-08-15T20:45:30.095459Z","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":"2026-08-15T20:45:30.820936Z","title":"Spike- driven transformer","venue":null,"work_id":"3743a856-08a8-4f71-ab60-df9e09c50210","year":2023},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.099582Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:25a751430f3ea4406045be47e510c86a542086f6e7fa1190c362f9cf52f8b810","observation_id":"5f65838a-d101-4356-9edd-087596539155","resolution":{"observed_at":"2026-08-15T20:45:30.824586Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:45:30.808671Z","title":"Spike-driven transformer v2: Meta spiking neural network architecture inspiring the design of next-generation neuromorphic chips","venue":null,"work_id":"ebc21fc7-ff9b-40e0-9cab-451112bfa6b1","year":2024},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.103651Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:f6ef31a5f3ce135563532b3ab5e217484ad4450a54f38fcfa9d5dec6a9b14c58","observation_id":"5414045a-c154-4699-9383-204ff9c515f4","resolution":{"observed_at":"2026-08-15T20:45:30.812759Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:45:30.796500Z","title":"Direct training for spiking neural networks: Faster, larger, better","venue":null,"work_id":"01db27e9-3181-4508-a159-7c38c4d3f193","year":2019},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.107672Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:05281d1cd85c45b99ff2cd7aece0ee658f26a67ecb6589c6e245db3c92cc2309","observation_id":"5e0ea681-b715-4984-8e75-f4c3843bcbca","resolution":{"observed_at":"2026-08-15T20:45:30.801084Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.14218","last_updated":"2025-02-20T03:15:52Z","snapshot_observed_at":"2026-08-18T14:23:11.037725Z","submitted_at":"2025-02-20T03:15:52Z","title":"Rethinking Spiking Neural Networks from an Ensemble Learning Perspective","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.14218","snapshot_observed_at":"2026-08-15T20:45:30.111541Z","title":"Rethinking spiking neural networks from an ensemble learning perspective","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.111541Z"},"links":{"cited_paper":"/paper/2502.14218","citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:d1687c2e6ccf815912fe69a8c078a487de1df49ba5cf6e895316300d6a05762f","observation_id":"d8e97ea2-ab9d-4776-9427-b1b84c19abaf","resolution":{"observed_at":"2026-08-15T20:45:30.111541Z","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":"2026-08-15T20:45:30.115717Z","title":"Towards memory-and time-efficient backpropagation for training spiking neural networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.115717Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:93c031f5ccc0a1dc4145306ee5386f061898e2afb2219ef7298eb13465ebf83e","observation_id":"95217f3e-527b-489f-b58f-8296dbfcdb7b","resolution":{"observed_at":"2026-08-15T20:45:30.115717Z","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":"2026-08-15T20:45:30.777309Z","title":"Rethinking the membrane dynamics and optimization objectives of spiking neural networks","venue":null,"work_id":"b3b73fa8-e263-43ec-8c45-2ae52787e635","year":2024},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.119534Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:13a83113ec465ee089d4b9ec1461d13a3f3f907d22a8ab8340c5e080d0211524","observation_id":"1d30ac0b-9acd-4811-b799-f1070820eef2","resolution":{"observed_at":"2026-08-15T20:45:30.781312Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:45:30.764973Z","title":"Deeptage: Deep temporal-aligned gradient enhancement for optimizing spiking neural networks","venue":null,"work_id":"42bfe249-8931-4ca6-9fda-d6211322cc8b","year":2025},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.123741Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:e6ee00eb9bc27a5aed9a38d6b93bdf4a2e986fde8b22a0922347cecbf1b8b32d","observation_id":"56392b6f-59b7-4504-95d9-b3de4e53c191","resolution":{"observed_at":"2026-08-15T20:45:30.768975Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04663","last_updated":"2025-02-19T15:11:51Z","snapshot_observed_at":"2026-08-16T14:20:42.438208Z","submitted_at":"2024-02-07T08:51:57Z","title":"CLIF: Complementary Leaky Integrate-and-Fire Neuron for Spiking Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.04663","snapshot_observed_at":"2026-08-15T20:45:30.127711Z","title":"Clif: Complementary leaky integrate-and-fire neuron for spiking neural networks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.127711Z"},"links":{"cited_paper":"/paper/2402.04663","citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:9925ef7161dbe45878b61f636c1cb3db794eec4d6a407dc756edcec478bda553","observation_id":"092a7009-801d-4152-bc23-43b8423ffcf9","resolution":{"observed_at":"2026-08-15T20:45:30.127711Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.19764","last_updated":"2025-03-03T18:51:11Z","snapshot_observed_at":"2026-08-18T16:52:19.346688Z","submitted_at":"2024-09-29T20:29:39Z","title":"Spiking Transformer with Spatial-Temporal Attention","version":3},"cited_work":{"arxiv_id":"2409.19764","doi":null,"metadata_source":"pith","pith_arxiv_id":"2409.19764","snapshot_observed_at":"2026-08-15T20:45:30.396598Z","title":"Spiking Transformer with Spatial-Temporal Attention","venue":"cs.NE","work_id":"66b504ed-c241-49f3-bf54-1934b7d60c38","year":2024},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.131763Z"},"links":{"cited_paper":"/paper/2409.19764","citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:b35d89757d2bd44b511edc21ec5e4c450e5d395065930f48cfee9a97d66d9b9c","observation_id":"db1bda9c-f75e-4769-ace0-699189ee3b90","resolution":{"observed_at":"2026-08-15T20:45:30.401567Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:45:30.752057Z","title":"Top-down influences on visual processing","venue":null,"work_id":"41ee92a3-a4d2-422c-8501-28b1df3f5fd2","year":2013},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.136200Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:9d5c1011653e5865224d6e994a32dc78b4413913c626a44228b74e49526a65f7","observation_id":"7c474253-f50f-4ca9-93e0-486a74e9105c","resolution":{"observed_at":"2026-08-15T20:45:30.756650Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:45:30.738860Z","title":"Top-down versus bottom-up control of attention in the prefrontal and posterior parietal cortices","venue":null,"work_id":"0b28300a-9625-4025-9705-22dedd30fe7d","year":2007},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.140105Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:e01791c58acb134b04a6c915dd9486b3e40ebc42ad9a3d513f2bcdfc54d6fc7b","observation_id":"401587f5-608a-4bc9-8bb5-d323da4c2729","resolution":{"observed_at":"2026-08-15T20:45:30.743635Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:45:30.727333Z","title":"The normalization model of attention.Neuron, 61(2):168– 185, 2009","venue":null,"work_id":"2e1b247a-7fcf-49cf-b53c-192d5d856f04","year":2009},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.143987Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:f72a8f168b8348bfc370877f5178d45096fe5cd725da5da4e55d9a63672766ce","observation_id":"d7547ba0-98bc-4cbf-8703-68d6f9a0d254","resolution":{"observed_at":"2026-08-15T20:45:30.731167Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:45:30.714976Z","title":"A common network of functional areas for attention and eye movements","venue":null,"work_id":"f4582093-1010-469a-bd76-b5236b1b5247","year":1998},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.148003Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:c6b7522c31b1d19632181fb78b6161894a2e5d6c16dea6b14fb8ed3515385652","observation_id":"d5a4a879-26ad-43eb-bcea-481857f3215f","resolution":{"observed_at":"2026-08-15T20:45:30.719182Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.02020","last_updated":"2024-01-04T01:33:33Z","snapshot_observed_at":"2026-08-17T21:01:42.349690Z","submitted_at":"2024-01-04T01:33:33Z","title":"Spikformer V2: Join the High Accuracy Club on ImageNet with an SNN Ticket","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.02020","snapshot_observed_at":"2026-08-15T20:45:30.152099Z","title":"Spikformer v2: Join the high accuracy club on imagenet with an snn ticket","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.152099Z"},"links":{"cited_paper":"/paper/2401.02020","citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:2b32158622d4a0c60e48c3a8122814403d06b97a7745c778ba106a2730caecc2","observation_id":"a48252be-a577-4575-8afb-b15514e93b16","resolution":{"observed_at":"2026-08-15T20:45:30.152099Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13939","last_updated":"2024-07-11T10:16:12Z","snapshot_observed_at":"2026-08-16T15:52:22.493008Z","submitted_at":"2023-02-27T16:43:04Z","title":"SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13939","snapshot_observed_at":"2026-08-15T20:45:30.156648Z","title":"Spikegpt: Generative pre-trained language model with spiking neural networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.156648Z"},"links":{"cited_paper":"/paper/2302.13939","citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:a127d7bca3f4ca2002874920d99426ee310b121d9bc875449cd92bb9580f3f37","observation_id":"4ce8f664-0bd8-4d86-a2ec-7615d474b651","resolution":{"observed_at":"2026-08-15T20:45:30.156648Z","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":"2026-08-15T20:45:30.702229Z","title":"Sglformer: Spiking global-local-fusion transformer with high performance","venue":null,"work_id":"0146a7a9-4fd0-4e61-b775-517515483193","year":2024},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.160695Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:72f4b24bf89076a1409fdb5c4bf703ce316e9fadc68de2f869a5c52bd1e64588","observation_id":"23db57b5-e5cd-46f7-8eac-e178ec35925f","resolution":{"observed_at":"2026-08-15T20:45:30.706268Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:45:30.689218Z","title":"Object recognition using a bio-inspired neuron model with bottom-up and top-down pathways","venue":null,"work_id":"c2adf07f-6f86-4dab-b7ab-8254b5f2bf04","year":2011},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.164608Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:84d681808e808480cd48c8b9dca24604d1781ed8c76144936f8e7d95e6978ece","observation_id":"027161f8-1136-4fbf-9709-be5015dcf319","resolution":{"observed_at":"2026-08-15T20:45:30.693781Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:45:30.168266Z","title":"Bottom-up and top-down attention for image captioning and visual question answering","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.168266Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:5c09207f0e96d2ac7c6443d435860e5f0be2b0213402871b5861405ab9b16076","observation_id":"28c6e6cb-8033-442f-bd7b-b77723a1657c","resolution":{"observed_at":"2026-08-15T20:45:30.168266Z","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":"2026-08-15T20:45:30.668447Z","title":"Top-down visual attention from analysis by synthesis","venue":null,"work_id":"bb436cff-e85c-4bec-97fb-efd45f3adff2","year":2023},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.171816Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:7813235393ff9c5e6e579e281b4bd490b046e521ac1fb5ee8e5eddad00d81660","observation_id":"555e2c10-844e-43cd-a541-26105dca3051","resolution":{"observed_at":"2026-08-15T20:45:30.672765Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02415","last_updated":"2024-06-16T15:24:53Z","snapshot_observed_at":"2026-08-16T15:26:45.574723Z","submitted_at":"2023-06-04T17:38:06Z","title":"Biologically-Motivated Learning Model for Instructed Visual Processing","version":3},"cited_work":{"arxiv_id":"2306.02415","doi":null,"metadata_source":"pith","pith_arxiv_id":"2306.02415","snapshot_observed_at":"2026-08-15T20:45:30.355595Z","title":"Biologically-Motivated Learning Model for Instructed Visual Processing","venue":"cs.AI","work_id":"bcf8c7c2-5456-4d95-a337-4f7f91799059","year":2023},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.175153Z"},"links":{"cited_paper":"/paper/2306.02415","citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:00c95aa58681334ad0eb5e3eba8d8e456c766f534a4996c98c9e51cd18f06aef","observation_id":"398c116f-cecd-4100-90b1-198da29d36af","resolution":{"observed_at":"2026-08-15T20:45:30.360222Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:45:30.178915Z","title":"Cambridge University Press, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.178915Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:78229c14bfa290c08ed7e700aee14313f68ee349295df354ef8042e34126a880","observation_id":"fc218b1b-624e-48ca-9216-141dc0a34f8d","resolution":{"observed_at":"2026-08-15T20:45:30.178915Z","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":"2026-08-15T20:45:30.182205Z","title":"Attention is all you need","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.182205Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:d1678b468672aed12f427a192217a1d1790835cbeb4fb4aed4f78c1f432a6527","observation_id":"dbd900ba-ae48-4b0a-9d26-7df38052ba88","resolution":{"observed_at":"2026-08-15T20:45:30.182205Z","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":"2026-08-15T20:45:30.185844Z","title":"Metaformer is actually what you need for vision","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.185844Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:94de3b2bf5c29270e15f5f952b892482cb1542f29c72c6f7b028ddee2f175d0b","observation_id":"3b0ee828-07aa-4de8-bfd2-e4c57065a2a6","resolution":{"observed_at":"2026-08-15T20:45:30.185844Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-16T09:25:53.087782Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-15T20:45:30.189500Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.189500Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:463cbe09bed66d220127327fb21e224a4e8cde9a6754b5475752123ce8573991","observation_id":"55394f8c-c8fb-455e-9d24-ff68f341b28a","resolution":{"observed_at":"2026-08-15T20:45:30.189500Z","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":"2026-08-15T20:45:30.193784Z","title":"Training data-efficient image transformers & distillation through attention","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.193784Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:60e229ace64ff68879a035ead8f3f72815fe3160b3177769591e67d4911f1b7c","observation_id":"01cd6553-9316-4c83-824e-b5437ad4994f","resolution":{"observed_at":"2026-08-15T20:45:30.193784Z","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":"2026-08-15T20:45:30.197847Z","title":"Swin transformer: Hierarchical vision transformer using shifted windows","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.197847Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:743a399d2f9f52d7f5f1d1f3a75db831aec12815164e6386a176f71a4cef82b4","observation_id":"e2167563-40d4-4476-b734-91909e1f7501","resolution":{"observed_at":"2026-08-15T20:45:30.197847Z","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":"2026-08-15T20:45:30.201645Z","title":"Scaling spike-driven transformer with efficient spike firing approximation training","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.201645Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:472688c94211db60adf419e9cf26b9eeb239a82382d7904661e2d83bdbb23222","observation_id":"711772f5-775e-4440-993d-de622876b541","resolution":{"observed_at":"2026-08-15T20:45:30.201645Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.11946","last_updated":"2022-05-15T11:17:43Z","snapshot_observed_at":"2026-08-16T17:19:00.751333Z","submitted_at":"2022-02-24T08:02:37Z","title":"Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.11946","snapshot_observed_at":"2026-08-15T20:45:30.205573Z","title":"Temporal efficient training of spiking neural network via gradient re-weighting","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.205573Z"},"links":{"cited_paper":"/paper/2202.11946","citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:0a3e5d0484f646de3ca975c0f0649213e9a51b537bfee7522247fb59bb4382c5","observation_id":"13630d10-1f7e-4efa-adb1-46b0d1eca5f4","resolution":{"observed_at":"2026-08-15T20:45:30.205573Z","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":"2026-08-15T20:45:30.210023Z","title":"Going deeper with directly-trained larger spiking neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.210023Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:999fb5720401bc7abea171445dcea16d344935a24bdf8a204c5c98e591a0c6a3","observation_id":"fedb822e-d328-4e83-88d4-6e3952d2f894","resolution":{"observed_at":"2026-08-15T20:45:30.210023Z","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":"2026-08-15T20:45:30.604141Z","title":"Recdis-snn: Rectifying membrane potential distribution for directly training spiking neural net- works","venue":null,"work_id":"bc572714-b13b-4cca-93fc-59b0e9246e6a","year":2022},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.214189Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:679ec79499f5261ea36918bc7d0dbceef25e339fc3e0aa4f3414223349a9d2a7","observation_id":"d52a4a7d-3344-476e-a48f-6cae80124a08","resolution":{"observed_at":"2026-08-15T20:45:30.608487Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:45:30.218178Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.218178Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:bcbc5c5b304f58ddddf6dcd852269eeeb6ed6d8c537823305735b86ece77cae6","observation_id":"54c9bdc3-696b-45ff-9521-245d3b9aa6c7","resolution":{"observed_at":"2026-08-15T20:45:30.218178Z","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":"2026-08-15T20:45:30.221882Z","title":"Cifar10-dvs: an event- stream dataset for object classification","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.221882Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:a23ddae0e543ae1d02557bfb7dc67418adc8a2f7859a9ef86bba876742b48f4f","observation_id":"589a1346-4364-4449-b5a6-312c12758b81","resolution":{"observed_at":"2026-08-15T20:45:30.221882Z","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":"2026-08-15T20:45:30.225494Z","title":"A low power, fully event-based gesture recognition system","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.225494Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:b98df77954f36180902e019a3fe4146a7e2bf60376305474d845e5cb078957de","observation_id":"e68d807e-7208-423f-949e-f276acfd0334","resolution":{"observed_at":"2026-08-15T20:45:30.225494Z","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":"2026-08-15T20:45:30.229910Z","title":"Imagenet: A large- scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.229910Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:e903960ef64c1cd0d6fbd8edb038fd38b98efeac9f411733bafeb39cfa5d3cd1","observation_id":"2a659521-fb70-4703-93ff-7f82ae5a5e22","resolution":{"observed_at":"2026-08-15T20:45:30.229910Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.12261","last_updated":"2019-03-28T20:56:37Z","snapshot_observed_at":"2026-08-15T10:34:34.836991Z","submitted_at":"2019-03-28T20:56:37Z","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.12261","snapshot_observed_at":"2026-08-15T20:45:30.233591Z","title":"Benchmarking neural network robustness to common corruptions and perturbations","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.233591Z"},"links":{"cited_paper":"/paper/1903.12261","citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:d5648c912fd42bbc82b555e038431b9c3a1d5124e82263aadd3ff58b0c5faa40","observation_id":"695346ef-6ba3-42d6-9b30-71530851caf1","resolution":{"observed_at":"2026-08-15T20:45:30.233591Z","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":"2026-08-15T20:45:30.551425Z","title":"Training high-performance low-latency spiking neural networks by differentiation on spike representation","venue":null,"work_id":"3e417fbd-d97a-4869-9bb1-1044dcdc67a3","year":2022},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.237721Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:273b2e6d5f3405252a2146bf14c8ea81bfd1afbc9c966ea962716a1a0bd4a99b","observation_id":"05313118-33bc-419b-bc5a-aa2d2172dda9","resolution":{"observed_at":"2026-08-15T20:45:30.555640Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-14T20:13:52.872565Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-15T20:45:30.241419Z","title":"Decoupled weight decay regularization","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.241419Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:df8934f56bf7413bb9bdb59210c5a016dd1d338a4c163c76122c9b226df170bb","observation_id":"339650e8-df46-42ec-9908-422a1d86ff3e","resolution":{"observed_at":"2026-08-15T20:45:30.241419Z","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":"2026-08-15T20:45:30.538285Z","title":"Integer-valued training and spike-driven inference spiking neural network for high-performance and energy-efficient object detection","venue":null,"work_id":"d59b7ad0-a4c6-42e7-83f5-1fd970f5132b","year":2024},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.245059Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:da8c96c4edf10e7358c65e8d54c0368058088d8277990d1cdaf6b3d07d4d4827","observation_id":"ad65b8fc-7e11-468a-9dcd-4d5ac9a2a391","resolution":{"observed_at":"2026-08-15T20:45:30.542952Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:45:30.524927Z","title":"Beyond classification: Directly training spiking neural networks for semantic segmentation","venue":null,"work_id":"2771d1af-48f9-4162-bf0a-c17affca4e89","year":2022},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.249337Z"},"links":{"citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:52dbc62efe9715111f102d3726c8dde6d397c36de7c37df9bb8d19d80a3fcb40","observation_id":"8dcc51c6-dc02-412c-9137-f1b2ff3110e5","resolution":{"observed_at":"2026-08-15T20:45:30.529237Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.19230","last_updated":"2024-06-27T14:54:27Z","snapshot_observed_at":"2026-08-16T13:39:02.940475Z","submitted_at":"2024-06-27T14:54:27Z","title":"Spiking Convolutional Neural Networks for Text Classification","version":1},"cited_work":{"arxiv_id":"2406.19230","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.19230","snapshot_observed_at":"2026-08-15T20:45:30.286437Z","title":"Spiking Convolutional Neural Networks for Text Classification","venue":"cs.NE","work_id":"2b639140-abcf-4496-8af7-7f7dd380478c","year":2024},"citing_paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:30.252933Z"},"links":{"cited_paper":"/paper/2406.19230","citing_paper":"/paper/2505.15840"},"observation_digest":"sha256:f08d85b4e05f100a765ffbbea4ce645aebc9d709830bc7111756e9d3b71a5fff","observation_id":"b8c5dc6c-4ad6-451d-8a70-9094a1d477ff","resolution":{"observed_at":"2026-08-15T20:45:30.292774Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.15840","last_updated":"2025-05-23T03:45:06Z","latest_version":2,"primary_category":"cs.NE","snapshot_observed_at":"2026-08-18T08:19:16.972018Z","submitted_at":"2025-05-17T15:55:32Z","title":"TDFormer: A Top-Down Attention-Controlled Spiking Transformer"},"reference_resolution":{"displayed":44,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":25,"verified_exact":2,"verified_fuzzy":16},"total_outbound_references":44},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 0 inbound Pith citation observations for arXiv:2505.15840."}