{"as_of":"2026-08-12T05:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a6f498eaa613aca4406ba55b47535a7d1a3a2a405c323f8adaec10082a26ac7f","coverage":[{"denominator":56,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":56,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T13:04:27.843554Z","state":"measured"},{"denominator":56,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":56,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+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/2412.13553/citation-record","integrity":"/paper/2412.13553/integrity","json":"/paper/2412.13553/citation-record.json","paper":"/paper/2412.13553"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:04:28.924935Z","title":"Spike-train level backpropagation for training deep recurrent spiking neural networks","venue":null,"work_id":"abf8e83a-9086-463b-8f5b-44a7e4fd4ac6","year":2019},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.503709Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:31b15c5b15ea3d405d9ff4f121ab90e21103c196d3d99ed6885bd2bfb1623e71","observation_id":"469e7649-def1-431c-81f9-7d8b2f787388","resolution":{"observed_at":"2026-08-11T13:04:28.930743Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T13:04:28.907639Z","title":"Spiking deep residual networks","venue":null,"work_id":"7af14411-b2bf-4a3a-a0d8-d8df75713943","year":2021},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.510119Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:edd6fd1d1e56b34f2a639169625d0e283bb6ab95c22167f5063db6b8a37c2ace","observation_id":"76ac4945-8848-4f35-87d2-37e0415a1875","resolution":{"observed_at":"2026-08-11T13:04:28.913133Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T13:04:28.888325Z","title":"Dynamic spiking graph neural net- works","venue":null,"work_id":"c275f301-ef69-40f0-9954-02f05c34b209","year":2024},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.515619Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:d31b804884fc75f966f2c59645381e140232c3c73c3ad944c41d7fa89eec4913","observation_id":"98453628-fd8e-4177-90bf-4f7034f19562","resolution":{"observed_at":"2026-08-11T13:04:28.894190Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13939","last_updated":"2024-07-11T10:16:12Z","snapshot_observed_at":"2026-08-09T03:27:51.510607Z","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":"2026-08-11T13:04:27.521152Z","title":"Spikegpt: Generative pre-trained language model with spiking neural networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.521152Z"},"links":{"cited_paper":"/paper/2302.13939","citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:8a1aebba9265edda4be2bd5a6b91bb76aac04b9b12ce68d1231e16febd12b4ff","observation_id":"a6346d93-d81b-403b-a5cd-2e89f4f2fa82","resolution":{"observed_at":"2026-08-11T13:04:27.521152Z","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":"2026-08-11T13:04:28.869917Z","title":"Spikformer: When spiking neural network meets transformer","venue":null,"work_id":"bc2d6b54-6804-4477-996e-1d682da0ed9f","year":2023},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.527899Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:e7d6b82d1d1fbb655a999359926f9c7ef1dcb5ce9b8f169ac4909badfb2b661e","observation_id":"43dc4b53-c955-43b9-807b-eb22f86e3a86","resolution":{"observed_at":"2026-08-11T13:04:28.875212Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T13:04:28.851498Z","title":"Spike-driven transformer","venue":null,"work_id":"c4784e0f-2486-4821-ab79-eb139b5180ad","year":2024},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.533629Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:2ce9cba3ea6e2d6277175f7b02688dad705d02c3d3563bb3935582acb9ef3383","observation_id":"9092894d-7951-46a5-a9dc-65c1b6f3e80d","resolution":{"observed_at":"2026-08-11T13:04:28.857673Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T13:04:27.540991Z","title":"Spikingformer: Spike-driven residual learning for transformer-based spiking neural network","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.540991Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:7f26b24bf27cd64ac2f65c317b781037965c398e8502ce1611ed5718c3112ea4","observation_id":"757c5cb4-000d-4bb5-b4d7-4b8bc25486b8","resolution":{"observed_at":"2026-08-11T13:04:27.540991Z","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":"2026-08-11T13:04:28.832388Z","title":"Attention is all you need","venue":null,"work_id":"8daf7e53-49df-4dca-8831-db49606ea3a5","year":2017},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.546550Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:b8575b2e3a051698a5985f6b9f6ee49527699b75165de4909fefd9fe8a6a4083","observation_id":"763a7d49-dc0b-4e6e-b892-ab67ff76ce94","resolution":{"observed_at":"2026-08-11T13:04:28.837697Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.16552","last_updated":"2024-10-08T09:29:01Z","snapshot_observed_at":"2026-07-06T17:50:01.477081Z","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":"2026-08-11T13:04:27.552083Z","title":"Qkformer: Hierarchical spiking transformer using qk attention","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.552083Z"},"links":{"cited_paper":"/paper/2403.16552","citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:e4d491a5a6b1172618e42a7e4f9124312911764ab8ccf93a1398663b3083c810","observation_id":"63af71b0-02a2-4dc0-97f2-223d06f4eb05","resolution":{"observed_at":"2026-08-11T13:04:27.552083Z","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":"2026-08-11T13:04:28.815927Z","title":"Masked spiking transformer","venue":null,"work_id":"0938471d-be4a-477b-9cb7-30af894421a7","year":2023},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.558161Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:30c1a43d9e5823e29aa81082ef59de60a37fc256c1fa150037e6ad9580549b60","observation_id":"e1cbba7c-87ad-4c58-9203-bc4d7bbea611","resolution":{"observed_at":"2026-08-11T13:04:28.821118Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.02557","last_updated":"2023-08-17T06:12:24Z","snapshot_observed_at":"2026-07-06T16:02:43.143897Z","submitted_at":"2023-08-02T11:41:54Z","title":"Attention-free Spikformer: Mixing Spike Sequences with Simple Linear Transforms","version":2},"cited_work":{"arxiv_id":"2308.02557","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.02557","snapshot_observed_at":"2026-08-11T13:04:28.078195Z","title":"Attention-free Spikformer: Mixing Spike Sequences with Simple Linear Transforms","venue":"cs.CV","work_id":"ca10bad1-b9ac-4731-b21e-803a2f011df0","year":2023},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.564394Z"},"links":{"cited_paper":"/paper/2308.02557","citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:b7ce1989cca52e1faaeffce809a6e031db774584b23a5671a52ffb70c88406ba","observation_id":"b04f0639-f027-421c-8ec0-37517cc2cfff","resolution":{"observed_at":"2026-08-11T13:04:28.084358Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-10T01:12:16.468283Z","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":"2026-08-11T13:04:27.571175Z","title":"An image is worth 16x16 words: Transformers for image recog- nition at scale","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.571175Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:5c00eb9f143257522ac3bd51d5f9970c2115a19302a1cfe4ce154af797036360","observation_id":"b1aad1f3-a0b2-4468-b2d2-68d39475378a","resolution":{"observed_at":"2026-08-11T13:04:27.571175Z","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":"2026-08-11T13:04:28.799638Z","title":"Cf-vit: A general coarse-to- fine method for vision transformer","venue":null,"work_id":"e7f2e896-1b45-453c-b474-0d0f7fe3daac","year":2023},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.577215Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:36d382838c6733fffb5017e12523f059015b539e0b1e647f0017e1dd5475179d","observation_id":"2db6aec4-bb1b-4da8-a1d0-88c76707f13a","resolution":{"observed_at":"2026-08-11T13:04:28.804936Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T13:04:28.785538Z","title":"Scaling vision transformers to 22 billion parameters","venue":null,"work_id":"4bc940e6-4244-4fa7-8d45-7c9cd20d17c9","year":2023},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.582513Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:c6e08a4671c3b452bc640204841f92c88af9e36e7f4615eabe36c881e3ead7ce","observation_id":"dacb032b-a631-4a71-ae56-0dc2e62ef7eb","resolution":{"observed_at":"2026-08-11T13:04:28.789973Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.13824","last_updated":"2023-02-17T13:17:52Z","snapshot_observed_at":"2026-07-06T12:12:39.412868Z","submitted_at":"2021-11-27T06:20:53Z","title":"FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.13824","snapshot_observed_at":"2026-08-11T13:04:27.589120Z","title":"Fq-vit: Post-training quantization for fully quantized vi- sion transformer","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.589120Z"},"links":{"cited_paper":"/paper/2111.13824","citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:142bbd808165e034d2f475db65e0e0fc973e053082fdf4d00852f3b3fcbeb6fb","observation_id":"87709b98-df1d-47bd-af8c-e31829129ee5","resolution":{"observed_at":"2026-08-11T13:04:27.589120Z","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":"2026-08-11T13:04:28.769648Z","title":"Top-down visual attention from analysis by synthesis","venue":null,"work_id":"80416a37-3dd1-430e-915e-3764c66a6e42","year":2023},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.594737Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:6727ddffdc697ce2f4a4a107e72ac3c043466ccdb1994853b9ab465a9a378033","observation_id":"034478c9-f98d-4fca-9b53-a2962bdbcb2a","resolution":{"observed_at":"2026-08-11T13:04:28.774774Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T13:04:28.753127Z","title":"Riformer: Keep your vision backbone effective but removing token mixer","venue":null,"work_id":"0e65a0c4-1da4-4028-a270-2ed6d34a1e4f","year":2023},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.601657Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:8d1e5e63effe3d2b2b374e0cda6cbb093d0738c51998d9bd3236ae9190379d46","observation_id":"7020abd7-987a-486b-959e-a71b9c8534c2","resolution":{"observed_at":"2026-08-11T13:04:28.758309Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T13:04:28.737069Z","title":"A closer look at self-supervised lightweight vision transformers","venue":null,"work_id":"30dbb187-08f6-4fef-b27d-e28569bc60ba","year":2023},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.607455Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:9d257d8a21fdf181da8a709780a53a42d3deeded960f7b2ba5000f95420e88e9","observation_id":"b1ece7f6-a2d8-4e95-a63e-5d1068d13478","resolution":{"observed_at":"2026-08-11T13:04:28.742001Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T13:04:28.721206Z","title":"E fficientvit: Memory e fficient vision transformer with cascaded group attention","venue":null,"work_id":"ae10db87-0966-4e00-a4aa-ecf8a4a806c5","year":2023},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.613785Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:4ce5831c40569e0ca0ef8be838d5f5f762694bc9be582b66e6d9df6cba37a88c","observation_id":"999b83e3-0002-47e4-9b1e-ce170ff45acf","resolution":{"observed_at":"2026-08-11T13:04:28.726523Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2211.10686","last_updated":"2022-11-19T12:49:22Z","snapshot_observed_at":"2026-07-06T14:20:34.768988Z","submitted_at":"2022-11-19T12:49:22Z","title":"Spikeformer: A Novel Architecture for Training High-Performance Low-Latency Spiking Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.10686","snapshot_observed_at":"2026-08-11T13:04:27.619580Z","title":"Spikeformer: A novel architecture for training high-performance low-latency spiking neural network","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.619580Z"},"links":{"cited_paper":"/paper/2211.10686","citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:5ece8cf5b5912f510cfe3399b91c789a01b461dc5efaf96ed89f63b1f838122d","observation_id":"90e5a661-fc92-405b-a51d-30edfad688c0","resolution":{"observed_at":"2026-08-11T13:04:27.619580Z","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":"2026-08-11T13:04:28.704719Z","title":"Deep residual learning in spik- ing neural networks","venue":null,"work_id":"2f1e965b-d529-4523-b009-f62b9cabb541","year":2021},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.626499Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:f8c1478c08d5086d13ad2400ffd65ac29d07344c77dc3bde258feaafcf0d017e","observation_id":"bc1709d2-8219-42f3-914d-0b99fd442b80","resolution":{"observed_at":"2026-08-11T13:04:28.710246Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.05954","last_updated":"2023-05-19T07:50:16Z","snapshot_observed_at":"2026-08-04T06:43:28.735044Z","submitted_at":"2023-05-10T07:48:08Z","title":"Enhancing the Performance of Transformer-based Spiking Neural Networks by SNN-optimized Downsampling with Precise Gradient Backpropagation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.05954","snapshot_observed_at":"2026-08-11T13:04:27.633501Z","title":"Enhanc- ing the performance of transformer-based spiking neural net- works by improved downsampling with precise gradient back- propagation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.633501Z"},"links":{"cited_paper":"/paper/2305.05954","citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:2ded1a2c11f8b6f10b4aeaa6fcd345ed87573f182660fc2b655a5d494b68aa76","observation_id":"1125d456-94c6-4790-8e18-fe77ea784087","resolution":{"observed_at":"2026-08-11T13:04:27.633501Z","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":"2026-08-11T13:04:28.687243Z","title":"Temporal-wise attention spiking neural networks for event streams classification","venue":null,"work_id":"acb158dc-6c90-4bed-a2a8-a40a32f29f13","year":2021},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.642256Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:a2624357f23622ec409b613332abc1bb6870e08b84996025d6b6019fde3e0562","observation_id":"36dd4ebc-22bf-40cf-a122-960eb9db0df0","resolution":{"observed_at":"2026-08-11T13:04:28.692788Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T13:04:28.669209Z","title":"Tcja-snn: Temporal-channel joint attention for spiking neural networks","venue":null,"work_id":"cd859f9a-8bac-4439-bbb9-b9bac0e5ad4c","year":2024},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.649302Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:20377e19bb5a20ed4dfe63cf88e573d95ebb794ce5f3ba887a274655eaa02c50","observation_id":"e3c6d10d-8f21-4de1-a315-df4e8264d917","resolution":{"observed_at":"2026-08-11T13:04:28.674756Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T13:04:28.653572Z","title":"Spatial-temporal self-attention for asyn- chronous spiking neural networks","venue":null,"work_id":"0fb7cf0e-8de8-4316-abbb-96d6a73e9b75","year":2023},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.655385Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:4e3ab63fe58e7aa2b90173c5b9ae4a7eb6e53b735241db98128e43054ed0b49b","observation_id":"f7c36e0b-9aa4-4f6e-b7d2-9860f501693c","resolution":{"observed_at":"2026-08-11T13:04:28.658842Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T13:04:28.635712Z","title":"Attention spiking neural networks","venue":null,"work_id":"3716fc8b-af36-4214-8efe-5be83ff28c51","year":2023},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.661153Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:c1e59cdca667d08a711c668eec40ed4839ae5ba646ffbc9084ae7b2ec3c895ff","observation_id":"8cd46d6b-d892-494f-bc04-27980221a062","resolution":{"observed_at":"2026-08-11T13:04:28.641694Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T13:04:28.617995Z","title":"Stsc-snn: Spatio-temporal synaptic connection with temporal convolution and attention for spiking neural net- works","venue":null,"work_id":"78d2dc6d-7958-4dda-9741-ed1b5a200de1","year":2022},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.667673Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:cf1cf5bda9ac52de63ecd5ee5a9c3a13ccd158d70aa8841b8c4380e28809c068","observation_id":"4f2e99cb-3f7e-41ea-82b5-0755cb06e74c","resolution":{"observed_at":"2026-08-11T13:04:28.623937Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.09376","last_updated":"2023-11-15T21:09:08Z","snapshot_observed_at":"2026-08-11T17:13:47.984084Z","submitted_at":"2023-11-15T21:09:08Z","title":"DISTA: Denoising Spiking Transformer with intrinsic plasticity and spatiotemporal attention","version":1},"cited_work":{"arxiv_id":"2311.09376","doi":null,"metadata_source":"pith","pith_arxiv_id":"2311.09376","snapshot_observed_at":"2026-08-11T13:04:27.965606Z","title":"DISTA: Denoising Spiking Transformer with intrinsic plasticity and spatiotemporal attention","venue":"cs.NE","work_id":"7d687d1d-8675-4303-a626-6638941fd864","year":2023},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.675570Z"},"links":{"cited_paper":"/paper/2311.09376","citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:6bab7c079dc251800cada55551522bc6193f7e2d569be071744d7ff2cd1cfed8","observation_id":"fbf228bb-3dc3-4367-9143-a0989cdb8bf4","resolution":{"observed_at":"2026-08-11T13:04:27.972900Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T13:04:28.600294Z","title":"A spatial–channel– temporal-fused attention for spiking neural networks","venue":null,"work_id":"0cf4ac64-c86d-4605-8b11-a92ce8ae5da0","year":2023},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.683419Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:6cfd7cd7fd2247769c98c2938b4dc24edd94dea7ebb888ac862d23db58b6ef3d","observation_id":"52d2ea8b-5519-4d9b-854a-4e049819dbf6","resolution":{"observed_at":"2026-08-11T13:04:28.605555Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T13:04:27.689422Z","title":"Simple model of spiking neurons","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.689422Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:4f223fa0c142b38ebe10094d18ef516544ac08a6f0548f8ca3e4cd7a6b6c8d2e","observation_id":"5ac30d88-48af-49bc-b6c9-3f78a5cc799b","resolution":{"observed_at":"2026-08-11T13:04:27.689422Z","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":"2026-08-11T13:04:28.571206Z","title":"A quantitative de- scription of membrane current and its application to conduction and excitation in nerve","venue":null,"work_id":"b01c29aa-e4d0-43d5-bcd4-20e30976dfa4","year":1952},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.694601Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:ffe69e8d35a79557bb53788e54354209b3f9d90b46ae27549911dcbb672c4a24","observation_id":"f9f40413-063c-4efb-9279-cd43faae546a","resolution":{"observed_at":"2026-08-11T13:04:28.576178Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T13:04:28.553327Z","title":"A novel image denoising algorithm combining attention mechanism and residual unet network","venue":null,"work_id":"80fae181-046f-4d8c-abe3-057d2c8f0ff0","year":2024},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.701162Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:e219ce57c7aa54cf1c7aa57038e9d4cf443366e81e13e8e8efeb8bce666c476e","observation_id":"2320bef2-441d-4c83-aeb7-b8262d352384","resolution":{"observed_at":"2026-08-11T13:04:28.559118Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.08874","last_updated":"2024-07-15T09:42:48Z","snapshot_observed_at":"2026-07-06T17:01:40.744034Z","submitted_at":"2023-12-14T16:26:29Z","title":"Agent Attention: On the Integration of Softmax and Linear Attention","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.08874","snapshot_observed_at":"2026-08-11T13:04:27.708808Z","title":"Agent attention: On the integration of softmax and linear attention","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.708808Z"},"links":{"cited_paper":"/paper/2312.08874","citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:9bee47a291d494b1b041275aae70ee3de465f479a0e6f6eb8ddda5d6ea526f7d","observation_id":"629cfab8-7aea-46eb-82f2-cdd46231e392","resolution":{"observed_at":"2026-08-11T13:04:27.708808Z","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":"2026-08-11T13:04:27.715685Z","title":"Flatten transformer: Vision transformer using focused linear attention","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.715685Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:58d947b60c2493669590d33ac5ed7d7318ceb28b1ed1c9666fae493a88d47db9","observation_id":"8244b163-3110-4e4e-b303-b79e907bf0ba","resolution":{"observed_at":"2026-08-11T13:04:27.715685Z","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":"2026-08-11T13:04:28.524587Z","title":"Learning multiple lay- ers of features from tiny images","venue":null,"work_id":"d0a7eb2d-63b1-4e5c-8069-be84a6cd7af5","year":2009},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.720899Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:a76a5ed04b17a6646ebd6226b373f2693b2435dd1ce343c7d574fc9fa66cd017","observation_id":"2c7374eb-888d-43be-a4ed-a3afe906498b","resolution":{"observed_at":"2026-08-11T13:04:28.529872Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T13:04:28.507249Z","title":"Cifar10-dvs: an event-stream dataset for object classifica- tion","venue":null,"work_id":"dff386d4-7725-4475-97a4-44f3fc699bff","year":2017},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.726316Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:020b790400e2435ab69d91ce55c381051eb9ae43491900bfd67d58c3513d395a","observation_id":"ff6f34f5-7633-40ce-95ba-016f3bd35aad","resolution":{"observed_at":"2026-08-11T13:04:28.512334Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T13:04:28.488861Z","title":"A low power, fully event-based gesture recognition system","venue":null,"work_id":"2d4e71fa-a21e-431f-955d-abc87af00184","year":2017},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.731593Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:d0532c4ab556ea1c9542a58a89be73c12914959b2d2db2efa0f5e08882f623f7","observation_id":"064b132c-5625-46cf-9b61-62bdc70ef8cf","resolution":{"observed_at":"2026-08-11T13:04:28.494906Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2005.01807","last_updated":"2020-05-04T19:30:43Z","snapshot_observed_at":"2026-08-10T09:06:07.761032Z","submitted_at":"2020-05-04T19:30:43Z","title":"Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.01807","snapshot_observed_at":"2026-08-11T13:04:27.739763Z","title":"Enabling deep spiking neural networks with hybrid conversion and spike timing dependent backpropagation","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.739763Z"},"links":{"cited_paper":"/paper/2005.01807","citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:0632094b4817aa0bac93808eecdfee38d629ee6a9fb52d450f0443d193ff577a","observation_id":"8cdf1251-3d79-4d0c-af10-1ad07dbfa2c5","resolution":{"observed_at":"2026-08-11T13:04:27.739763Z","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":"2026-08-11T13:04:28.471949Z","title":"Optimizing deeper spiking neural networks for dynamic vision sensing","venue":null,"work_id":"93bb9414-9374-458e-addf-692478fdaa53","year":2021},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.745247Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:000d770ec2100321680618bf22f00d0caab1bd474604e391df5b3f9aa3619c86","observation_id":"7f1a4302-e218-4dc7-a5d4-3501b447f839","resolution":{"observed_at":"2026-08-11T13:04:28.477004Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T13:04:28.453646Z","title":"Incorporating learnable membrane time constant to enhance learning of spiking neural networks","venue":null,"work_id":"0c79f3ee-fcaa-488d-ac10-43dfffe14f9d","year":2021},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.750602Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:51fa63cf91829c809bd5247f32b93800dee3139990076822aab71567353222e4","observation_id":"9736b678-ba04-4c46-9575-b63bc3d0257a","resolution":{"observed_at":"2026-08-11T13:04:28.459100Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T13:04:28.436468Z","title":"Spatio- temporal backpropagation for training high-performance spik- ing neural networks","venue":null,"work_id":"bb639bbb-8a23-47b2-b9c3-dd3e28b50e3d","year":2018},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.757032Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:540f163c08a99bc3b672c60dfa8fa32dff521b1d0b7959508335b31073bedb64","observation_id":"af87e84d-b2bc-4fd0-8b82-d7b2ba707073","resolution":{"observed_at":"2026-08-11T13:04:28.442043Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T13:04:28.421147Z","title":"Direct training for spiking neural networks: Faster, larger, better","venue":null,"work_id":"e3cec153-affc-4e2f-adea-7b6560dbe59a","year":2019},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.763321Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:ee0a7ecd21efa61acaa52b9d799d45e37c8991222b0a4f5258c9bdcd88d3f878","observation_id":"39455273-3a4d-4b0c-83ac-ad2c5b86680e","resolution":{"observed_at":"2026-08-11T13:04:28.425979Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T13:04:28.405749Z","title":"Temporal spike sequence learn- ing via backpropagation for deep spiking neural networks","venue":null,"work_id":"b4c0d072-acba-4fec-b955-cc9006bdcc2e","year":2020},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.769291Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:e406110d8bdfb7610215fab011719f43bc75e2f9a0c4af59abc9c44605d81ae0","observation_id":"c7927bd0-29b6-403b-aa05-c5f7a577c982","resolution":{"observed_at":"2026-08-11T13:04:28.410907Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T13:04:28.388789Z","title":"Di fferentiable spike: Rethinking gradient-descent for training spiking neural networks","venue":null,"work_id":"7438bb85-3e77-4998-9abf-7d56578c6251","year":2021},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.775195Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:9c86813a699eafe454f382e2176f3c00b051b9eb080d60352aaf2c2dd6685f8d","observation_id":"83ca00aa-fa95-40b3-a58f-8a88a5d97907","resolution":{"observed_at":"2026-08-11T13:04:28.394367Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T13:04:28.371665Z","title":"Go- ing deeper with directly-trained larger spiking neural networks","venue":null,"work_id":"27f5e516-3515-40a1-aea1-1977255413aa","year":2021},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.781659Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:571c763798850a710c28d811762003309fbff40b623e50b779539985d9539282","observation_id":"7050ff9e-1b66-4094-bcb4-7bba2ed7549c","resolution":{"observed_at":"2026-08-11T13:04:28.376657Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.11946","last_updated":"2022-05-15T11:17:43Z","snapshot_observed_at":"2026-08-10T10:53:47.581058Z","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":"2026-08-11T13:04:27.787518Z","title":"Temporal efficient training of spiking neural network via gra- dient re-weighting","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.787518Z"},"links":{"cited_paper":"/paper/2202.11946","citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:663a396da8b87b04e5728314d85af4bad233d35a2bf15350de9edaef433f0c0d","observation_id":"49dde595-c022-4ee5-8c48-8e54ec359d34","resolution":{"observed_at":"2026-08-11T13:04:27.787518Z","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":"2026-08-11T13:04:28.355111Z","title":"Diet-snn: A low-latency spik- ing neural network with direct input encoding and leakage and threshold optimization","venue":null,"work_id":"f6a1cb8e-43e8-4b1d-a02c-37a19a23e6e8","year":2021},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.793285Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:f8126c232736eb9324487ba6713f218874758122d1492958c7ab5cc28ac6108f","observation_id":"eadf0a58-af3f-4c9b-88ff-454b79c44461","resolution":{"observed_at":"2026-08-11T13:04:28.360452Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T13:04:28.337952Z","title":"Ad- vancing spiking neural networks toward deep residual learning","venue":null,"work_id":"9d39265c-8048-42e0-b214-6356b8c8835f","year":2024},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.798943Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:5f1004502f76b2ecb83cd1cc21776417f961ce47bf0e84d9eee568c44c258e56","observation_id":"9a1885e6-7c1c-4984-a044-cdb47a4d4c12","resolution":{"observed_at":"2026-08-11T13:04:28.343289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T13:04:28.321939Z","title":"Training high-performance low-latency spiking neural networks by differentiation on spike representation","venue":null,"work_id":"b9f5061d-c47d-42a2-b1da-25fa07db2f15","year":2022},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.803671Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:183cb7f2ac2e78bbfcd9f908cdad69318f4c74a577242d44d55727cf1f24ff40","observation_id":"39b78356-2876-4697-9d21-e6cc6ce20c74","resolution":{"observed_at":"2026-08-11T13:04:28.327057Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-09T20:34:52.923500Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-11T13:04:27.809754Z","title":"Fixing weight decay regu- larization in adam","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.809754Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:7cbb1abf69072bba82b83593b972858114337ce78d8f3a81db5d570941c6ac38","observation_id":"c565dd9d-de63-4ad1-bae5-c043a6673376","resolution":{"observed_at":"2026-08-11T13:04:27.809754Z","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":"2026-08-11T13:04:28.306256Z","title":"Swin transformer: Hier- archical vision transformer using shifted windows","venue":null,"work_id":"8df67062-b367-4767-941d-902efaf3d5be","year":2021},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.815783Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:aab969b12bc390e82376c781c75bc7e51318133b18e411662f56388ef25c4d2e","observation_id":"26f1d287-75b0-473f-96d7-db2e4042fa4a","resolution":{"observed_at":"2026-08-11T13:04:28.311112Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T13:04:27.822051Z","title":"Neuronal dynamics: From single neurons to networks and models of cognition","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.822051Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:b236c47b89cb0a50f39f5cbbd51579c234e3f06dbc49452513f4c4de66f9833d","observation_id":"d260fecd-c5e4-4965-b868-924a5e8751f8","resolution":{"observed_at":"2026-08-11T13:04:27.822051Z","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":"2026-08-11T13:04:28.276572Z","title":"1.1 computing’s energy problem (and what we can do about it)","venue":null,"work_id":"e37086eb-2a2a-48a6-8bba-af262f521284","year":2014},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.827771Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:71639b66c48cb2192a896ea62c2f6c621ccc2f5926fb6da7126be64784bb3752","observation_id":"07233d81-283f-4756-ba3f-414120e3df65","resolution":{"observed_at":"2026-08-11T13:04:28.282069Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T13:04:28.257544Z","title":"Liaf-net: Leaky integrate and analog fire net- work for lightweight and e fficient spatiotemporal information processing","venue":null,"work_id":"e7cb13e6-c6c7-4ac3-a24d-f412ff81a644","year":2021},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.832712Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:1d21154e62401c61597252c81d4657e03c113181638aedb0980161334bd14ff5","observation_id":"0b1dbc93-5ae1-4b36-aaa0-4bd848aa32cb","resolution":{"observed_at":"2026-08-11T13:04:28.264538Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T13:04:28.240155Z","title":"E fficient processing of spatio-temporal data streams with spiking neural networks","venue":null,"work_id":"537af190-1254-44b2-8147-b74456ef06af","year":2020},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.838489Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:1ddee10bbc7525cb406b2c71b7ecc289307cfdee6631e292a1571bf373944d9c","observation_id":"554ff5bf-299e-4c56-b1bf-1a22c0e6002a","resolution":{"observed_at":"2026-08-11T13:04:28.245552Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T13:04:28.223456Z","title":"Synaptic plasticity dynamics for deep continuous local learning (decolle)","venue":null,"work_id":"54f3696e-e841-4915-bbbf-6bfa7cfd12eb","year":2020},"citing_paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-11T13:04:27.843554Z"},"links":{"citing_paper":"/paper/2412.13553"},"observation_digest":"sha256:a674154896ab6a28b34cbe03fc8cb3e0164d3b6951590853107f1613529f23a3","observation_id":"7ea51e29-e8e9-4465-bb2b-f4b1cd6d77ab","resolution":{"observed_at":"2026-08-11T13:04:28.228767Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.13553","last_updated":"2024-12-18T07:07:38Z","latest_version":1,"primary_category":"cs.NE","snapshot_observed_at":"2026-08-11T17:13:49.227129Z","submitted_at":"2024-12-18T07:07:38Z","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks"},"reference_resolution":{"displayed":56,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":14,"verified_exact":2,"verified_fuzzy":40},"total_outbound_references":56},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 56 of 56 outbound references and 0 inbound Pith citation observations for arXiv:2412.13553."}