{"as_of":"2026-08-19T01:50:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:84af2ba3ae071dee9cb9aa3e048ea0d5d98959f11a403a24d88fb290f03e9fb2","coverage":[{"denominator":43,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":43,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T21:01:34.401475Z","state":"measured"},{"denominator":43,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":43,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+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/2505.11134/citation-record","integrity":"/paper/2505.11134/integrity","json":"/paper/2505.11134/citation-record.json","paper":"/paper/2505.11134"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:01:35.055979Z","title":"Obfu scated gradients give a false sense of security: Circumventing defenses to adversarial exampl es","venue":null,"work_id":"84b40752-7b27-4476-b8a9-61ddf52b33d5","year":2018},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.193580Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:a4fcc6e3a938c8354cb68c3c36f9c013516e6e73a580c8dc06bf6a82bd7c8ef3","observation_id":"822a7937-94c6-4d63-8a71-022541d8cffd","resolution":{"observed_at":"2026-08-15T21:01:35.060751Z","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":"2026-08-15T21:01:35.039267Z","title":"High-performance large-scale image recognition without normalization","venue":null,"work_id":"9b15208a-53c9-40e5-ba54-3fe9db4219fc","year":2021},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.199925Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:5ccef36a2bf10b811ce13dfa7367d95b63385bb1cecfc9eccdac45a1c666b5a5","observation_id":"0835e864-9d86-4516-a09c-a29a225f03fa","resolution":{"observed_at":"2026-08-15T21:01:35.045039Z","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":"2205.15130","last_updated":"2022-05-30T14:22:10Z","snapshot_observed_at":"2026-08-16T16:56:38.807104Z","submitted_at":"2022-05-30T14:22:10Z","title":"Why Adversarial Training of ReLU Networks Is Difficult?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.15130","snapshot_observed_at":"2026-08-15T21:01:34.205696Z","title":"Why adversarial training of relu networks is difficult? arXiv preprint arXiv:2205.15130 , 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.205696Z"},"links":{"cited_paper":"/paper/2205.15130","citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:4c7acb9808c68216c2c7d192ea031a81caa771610f509e790a32b1f8f3614a70","observation_id":"04dbb467-7554-4ff8-84d3-bcd2ad6210af","resolution":{"observed_at":"2026-08-15T21:01:34.205696Z","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":"2026-08-15T21:01:34.213898Z","title":"Imagenet: A large- scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.213898Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:d41c70d99672276b9a11918b153f6c96fe6b408c8fac741cb9341dbc59d1c49f","observation_id":"a5ee2603-6c76-44dd-ba75-e53d3ee25c40","resolution":{"observed_at":"2026-08-15T21:01:34.213898Z","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":"2026-08-15T21:01:34.219643Z","title":"Te mporal efficient training of spiking neural network via gradient re-weighting","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.219643Z"},"links":{"cited_paper":"/paper/2202.11946","citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:da98f5a427cc75a440fef712f861686f0356572082e88e633e13d8f8d0d7c5f9","observation_id":"e049f257-43ad-45e6-80e1-6d97a02897d3","resolution":{"observed_at":"2026-08-15T21:01:34.219643Z","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":"2026-08-15T21:01:35.017074Z","title":"Snn-rat: Robustness- enhanced spiking neural network through regularized adver sarial training","venue":null,"work_id":"347c9133-c726-4b2d-81cc-7ece2bcf919d","year":2022},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.224257Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:bb19b3fcd3d57f13b8c80d5928feb4e3153556f41e81e78c2c9bc677baa15993","observation_id":"7fbff9c5-1954-485f-8fa9-ab49e437500a","resolution":{"observed_at":"2026-08-15T21:01:35.021844Z","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":"2405.20694","last_updated":"2024-05-31T08:40:02Z","snapshot_observed_at":"2026-08-16T13:47:28.693015Z","submitted_at":"2024-05-31T08:40:02Z","title":"Robust Stable Spiking Neural Networks","version":1},"cited_work":{"arxiv_id":"2405.20694","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.20694","snapshot_observed_at":"2026-08-15T21:01:34.551219Z","title":"Robust Stable Spiking Neural Networks","venue":"cs.NE","work_id":"c9f0268f-f97c-4a4d-9ee8-f6056079e329","year":2024},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.228942Z"},"links":{"cited_paper":"/paper/2405.20694","citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:cfd3f0b0115f8cf2ce1b5fa5e0b9c7f9e4d5582dbbe2bd9429e03b4ac42a3e9a","observation_id":"00a9d9fe-ddb8-4aad-9aa9-5cbd30e6559c","resolution":{"observed_at":"2026-08-15T21:01:34.555697Z","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":"2026-08-15T21:01:35.002464Z","title":"En hancing the robustness of spiking neural networks with stochastic gating mechanisms","venue":null,"work_id":"18b9182c-94d9-4f0d-a88d-581f19a1d340","year":2024},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.233172Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:7250e8d2670798c19d12276bc10b00cd9b69744a56a811dae1284b1c23f8bafb","observation_id":"f96576ef-4df3-4369-916a-ce3c583e3fde","resolution":{"observed_at":"2026-08-15T21:01:35.007424Z","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":"2026-08-15T21:01:34.988864Z","title":"Spiking jelly: An open-source machine learning infrastructure platform for spike-based intelligence","venue":null,"work_id":"fa1d806e-ddfc-4ea5-a708-a45229de74c4","year":2023},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.236946Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:54e8e4f675bb98de84714e2fbf1add35fffb265ae0cb53b46813e386fec06bed","observation_id":"6b7a0507-7dc8-4750-8cd3-69d3d8aefd9a","resolution":{"observed_at":"2026-08-15T21:01:34.992751Z","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":"2026-08-15T21:01:34.977024Z","title":"Deep residual learning in spiking neural networks","venue":null,"work_id":"88f972a3-8a2d-4bbf-a1b1-ac7801bedd06","year":2021},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.240889Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:5881fc5e46f6ff8b1ea0c7faf07c51d76d68a68e18e8a0909b97b615ec47bece","observation_id":"62740e29-1eb0-4852-9c58-3ed016d95835","resolution":{"observed_at":"2026-08-15T21:01:34.980715Z","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":"2308.10373","last_updated":"2025-03-04T01:24:52Z","snapshot_observed_at":"2026-08-16T15:07:09.957917Z","submitted_at":"2023-08-20T21:47:54Z","title":"HoSNN: Adversarially-Robust Homeostatic Spiking Neural Networks with Adaptive Firing Thresholds","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.10373","snapshot_observed_at":"2026-08-15T21:01:34.244901Z","title":"Hosnn: Adversarially-robust ho meostatic spiking neural networks with adaptive firing thresholds","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.244901Z"},"links":{"cited_paper":"/paper/2308.10373","citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:9180dd412934f7ce33e85ee138e8930cb7f891b0f29379a046758ca9c496bd9b","observation_id":"3d95507d-b44f-4bd8-b7e1-c5d60cc7c366","resolution":{"observed_at":"2026-08-15T21:01:34.244901Z","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":"2026-08-15T21:01:34.962710Z","title":"An i nvestigation into neural net opti- mization via hessian eigenvalue density","venue":null,"work_id":"02991e06-bbe9-47b0-83d1-3a241dec3b6a","year":2019},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.249978Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:44a1c415841351ddde74dcfbfbe6cb411a599e2f9c1beecb21895e391b48bbea","observation_id":"fd36003f-8f7e-4c23-b51d-88a278253493","resolution":{"observed_at":"2026-08-15T21:01:34.967275Z","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":"1412.6572","last_updated":"2015-03-20T20:19:16Z","snapshot_observed_at":"2026-08-12T17:13:46.394331Z","submitted_at":"2014-12-20T01:17:12Z","title":"Explaining and Harnessing Adversarial Examples","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6572","snapshot_observed_at":"2026-08-15T21:01:34.254369Z","title":"Explaining and harnessing adver- sarial examples","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.254369Z"},"links":{"cited_paper":"/paper/1412.6572","citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:31c96d649d492d3d2a0809c31de9d9356afec905493ddaf3599b4e5df9e09abf","observation_id":"1db69901-1c27-451a-9453-59fa74982b33","resolution":{"observed_at":"2026-08-15T21:01:34.254369Z","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":"2026-08-15T21:01:34.949248Z","title":"Fully spiking neural network for legged robots","venue":null,"work_id":"b9e975b5-2ba9-48b2-8cc8-25a1d54b4ae1","year":2025},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.259977Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:a3a8aa962bc4a503294f67b45c37c9ca827f507c51945d39a0908aa5a1335b13","observation_id":"ff0aaf45-bd09-4a59-a301-a7b1a17134dc","resolution":{"observed_at":"2026-08-15T21:01:34.954146Z","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":"2026-08-15T21:01:34.935589Z","title":null,"venue":null,"work_id":"25d3db87-17b8-454d-96e0-921cf6e6e031","year":2022},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.264309Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:29991268e950f072081c008109121573d4452e74b018965495dfd8214432fefd","observation_id":"d3f7c3ed-853d-43d1-95d7-255d990f3d4d","resolution":{"observed_at":"2026-08-15T21:01:34.940011Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-15T21:01:34.268541Z","title":"Learning mult iple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.268541Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:528f4b8401c2e6308e44c63210ddb15b1d084fc6dfddf7e20f218fce5854aabe","observation_id":"8313df3b-bc58-4694-a62f-d17d20c84e42","resolution":{"observed_at":"2026-08-15T21:01:34.268541Z","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":"2026-08-15T21:01:34.913234Z","title":"Dsqn: Robust path plannin g of mobile robot based on deep spiking q-network","venue":null,"work_id":"8842b3e0-7988-42dd-86d1-be4d5060abf0","year":2025},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.272703Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:484062585989f9a4ae9a78313f24c1ca99869c61469aadd7f69e3667efff1fcf","observation_id":"f531cf6c-ab95-4f56-920c-a9f468ffc65f","resolution":{"observed_at":"2026-08-15T21:01:34.917584Z","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":"2026-08-15T21:01:34.897360Z","title":"Hire- snn: Harnessing the inherent robustness of energy-efficient deep spiking neural network s by training with crafted input noise","venue":null,"work_id":"9098f46b-c624-44aa-9655-c9c2364ad0f7","year":2021},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.276920Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:dd6864e043372b9a47f7eef5db03a303efcd924ca7c3c142999b25a38b71f447","observation_id":"fd4042e5-f983-4fd2-a912-b74900cdb6ca","resolution":{"observed_at":"2026-08-15T21:01:34.902526Z","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":"2026-08-15T21:01:34.884241Z","title":"Ssefusion: Salient semantic enhancement for multimodal medical image fusion with mamba and dynamic spiking neural networks","venue":null,"work_id":"0233f8a1-99af-40b3-ab45-798ed279f016","year":2025},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.283928Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:7fc71fe038be9a18ef9388af8482bb23571ebe3ff4aa0c13d87420bb26e08f9c","observation_id":"93af1deb-d5f2-4179-b50a-771848dac249","resolution":{"observed_at":"2026-08-15T21:01:34.888715Z","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":"2026-08-15T21:01:34.871308Z","title":"Energy-effi cient distributed spiking neural network for wireless edge intelligence","venue":null,"work_id":"3dd267c1-5d55-4af7-9175-3733ef3703dd","year":2024},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.288677Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:196b580a946e154abbbe41f50996b952a288e1abd27615fa6d23a5916709b9de","observation_id":"c2c81eba-c888-463e-8cad-bd259bb91683","resolution":{"observed_at":"2026-08-15T21:01:34.875742Z","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":"2405.20355","last_updated":"2024-05-30T05:39:27Z","snapshot_observed_at":"2026-08-16T13:47:55.190880Z","submitted_at":"2024-05-30T05:39:27Z","title":"Enhancing Adversarial Robustness in SNNs with Sparse Gradients","version":1},"cited_work":{"arxiv_id":"2405.20355","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.20355","snapshot_observed_at":"2026-08-15T21:01:34.493727Z","title":"Enhancing Adversarial Robustness in SNNs with Sparse Gradients","venue":"cs.NE","work_id":"680d61d3-3caa-4b7a-ae22-783194f671a4","year":2024},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.293007Z"},"links":{"cited_paper":"/paper/2405.20355","citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:f1c02e4f7a126c8ddead05af2fa7ca9e9872096e7a0da5eafdac53f203605461","observation_id":"1e1a6b56-2c99-4519-8b18-06930e6e6872","resolution":{"observed_at":"2026-08-15T21:01:34.502130Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:01:34.297624Z","title":"Networks of spiking neurons: the third generation of neural network models","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.297624Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:3fad30d93d45be6540f36b4e4989e2af8f7e0d683adb8f1b469ccea46ad30d2c","observation_id":"7cec095a-78ee-48ef-928e-97f223861cae","resolution":{"observed_at":"2026-08-15T21:01:34.297624Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1706.06083","last_updated":"2019-09-04T18:53:10Z","snapshot_observed_at":"2026-08-07T14:27:46.872660Z","submitted_at":"2017-06-19T17:53:11Z","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.06083","snapshot_observed_at":"2026-08-15T21:01:34.302139Z","title":"Towards deep learning models resistant to adversari al attacks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.302139Z"},"links":{"cited_paper":"/paper/1706.06083","citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:c0f903c53c5df4201283dbce6755055edefa9f11ec8edb4f56bd9c39eb431762","observation_id":"6e8a0efb-96c3-4a9a-80f0-112de100ea1b","resolution":{"observed_at":"2026-08-15T21:01:34.302139Z","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":"2026-08-15T21:01:34.848255Z","title":"To- wards memory-and time-efficient backpropagation for train ing spiking neural networks","venue":null,"work_id":"f2c50279-5973-4f60-ab82-b8cc70e28775","year":2023},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.306611Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:ebde1be7c5987bda6b2424e875a0cc2cdc8f7a6d99613e49fc9b0c5df6d59111","observation_id":"92875b48-f3c3-470b-8e60-46a87f266071","resolution":{"observed_at":"2026-08-15T21:01:34.853618Z","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":"2026-08-15T21:01:34.834766Z","title":"Introductory lectures on convex optimization: A basic cour se, volume 87","venue":null,"work_id":"a3e202b0-300f-45c0-9876-130a7d5ddb5d","year":2013},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.311523Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:96d4b84794fa1c23917c96bd9cf2c241b4cfbb0f67388138407e3c4763de42d7","observation_id":"d553e86e-91f8-48f2-9d37-b1bbcafdbd52","resolution":{"observed_at":"2026-08-15T21:01:34.839229Z","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":"2410.09674","last_updated":"2024-10-29T18:17:48Z","snapshot_observed_at":"2026-08-16T13:09:59.137306Z","submitted_at":"2024-10-12T23:54:44Z","title":"EG-SpikeFormer: Eye-Gaze Guided Transformer on Spiking Neural Networks for Medical Image Analysis","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.09674","snapshot_observed_at":"2026-08-15T21:01:34.316354Z","title":"Eg-spikeformer: Eye-ga ze guided transformer on spiking neural networks for medical image analysis","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.316354Z"},"links":{"cited_paper":"/paper/2410.09674","citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:a3a629bbad86d154b8083c67c69f2f71683854821da4b1f6898483573c4ed7d9","observation_id":"54717595-2c0f-4851-ae99-afe46e1e1d0c","resolution":{"observed_at":"2026-08-15T21:01:34.316354Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.01703","last_updated":"2019-12-03T22:06:05Z","snapshot_observed_at":"2026-07-06T08:41:49.632205Z","submitted_at":"2019-12-03T22:06:05Z","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.01703","snapshot_observed_at":"2026-08-15T21:01:34.320951Z","title":"Pytorch: An imperative style, high-performa nce deep learning library","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.320951Z"},"links":{"cited_paper":"/paper/1912.01703","citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:4500eb354eafcfbfb6e1e8ca0a992f05a130da0bae938f84b6cf0c93e0599208","observation_id":"eeed24d6-2433-4ad2-b4ae-3b7d3076a9f1","resolution":{"observed_at":"2026-08-15T21:01:34.320951Z","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":"2026-08-15T21:01:34.820496Z","title":"Towards artificial general int elligence with hybrid tianjic chip architecture","venue":null,"work_id":"1d5ac610-fa9e-4af6-a404-b4a03a1d07ce","year":2019},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.325654Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:daf1c2e95fbebdb477ccf9af169220e9ecd1668d4f2bf0cf28dc048fe556ab6e","observation_id":"ead6ff5a-2c1f-48e9-8b7e-4461329d7587","resolution":{"observed_at":"2026-08-15T21:01:34.824554Z","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":"2026-08-15T21:01:34.806782Z","title":"Conversion of continuous-valued deep networks to efficient event-driven networks for image classification","venue":null,"work_id":"7ed5d47c-70d6-4be2-aa51-5332d3cf206a","year":2017},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.330034Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:24e172cc3fcb07318e06f772ce15e3512ba36ecb4b50e70478f6d58a7d9bb8df","observation_id":"216b02cf-fe89-4495-a124-6b41f44b5969","resolution":{"observed_at":"2026-08-15T21:01:34.812087Z","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":"2026-08-15T21:01:34.795492Z","title":"Lid ar-driven spiking neural network for collision avoidance in autonomous driving","venue":null,"work_id":"74ac69b1-9626-4fc3-b9cd-c57998f99cd1","year":2021},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.333676Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:b3ec7fe7e5de48d00fcc7395fbe3788874931510f84889c0a061c9bae70e223c","observation_id":"24b269d3-aa16-4f1d-9b00-05c270e3402b","resolution":{"observed_at":"2026-08-15T21:01:34.799355Z","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":"2026-08-15T21:01:34.781444Z","title":"A comprehensive analysis on adversari al robustness of spiking neural networks","venue":null,"work_id":"beda8ae9-9ee3-414b-b15a-1b2ee3b87d88","year":2019},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.337701Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:e12b5a2bdff433d6cabb4cc820ba38a343c132168cd17359ff774087a15a8d43","observation_id":"d3d28983-f9d4-49f2-88c8-a50fd010433a","resolution":{"observed_at":"2026-08-15T21:01:34.786302Z","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":"2026-08-15T21:01:34.768442Z","title":"Inherent adversarial ro- bustness of deep spiking neural networks: Effects of discre te input encoding and non-linear activations","venue":null,"work_id":"8a73d0dd-573b-4880-9792-f7e51d30ba95","year":2020},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.341516Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:150cab83100153aa1642798832eee1d912f02e3e2903bda1c9666cb95e0e3714","observation_id":"720a2adb-97ec-4ca3-ba42-c4731244786b","resolution":{"observed_at":"2026-08-15T21:01:34.773227Z","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":"2026-08-15T21:01:34.754992Z","title":"Carsnn: An efficient spiking neural network for event-based autonomous cars on the loihi neuromorphic research processor","venue":null,"work_id":"d05f65c0-90ec-4d94-835f-04cb35bea248","year":2021},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.348621Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:cf19fc8b5f578ee32560037e98c89a1c57340b434adb1febe58a4a70eecac389","observation_id":"40ad367d-d521-49ea-a21c-789d486975fe","resolution":{"observed_at":"2026-08-15T21:01:34.759459Z","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":"2026-08-15T21:01:34.738289Z","title":"Ssf: Accelerating training of spiking neural networ ks with stabilized spiking flow","venue":null,"work_id":"22a1f478-22ea-42e9-885d-a369c02e9921","year":2023},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.352752Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:272a3f7ff945dd2c1443666ad1077d87f1ae1b20fcf4d558152ccbe1cff6d5ff","observation_id":"df936788-bf14-4238-9b1a-d2c3b066cc19","resolution":{"observed_at":"2026-08-15T21:01:34.742577Z","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":"2026-08-15T21:01:34.723647Z","title":"Spa tio-temporal backpropagation for training high-performance spiking neural networks","venue":null,"work_id":"89cbf3ec-a8a6-4e67-8122-f189cc2d760f","year":2018},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.357265Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:912027a25080588c57beac63c9861174b43e0e669fdc1de77361d9ce2b2cb7ba","observation_id":"f502ec03-d67e-4a17-b049-d5ae18165959","resolution":{"observed_at":"2026-08-15T21:01:34.729255Z","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":"2026-08-15T21:01:34.708286Z","title":"Online training through time for spiking neural networks","venue":null,"work_id":"0c34f312-f24d-4153-acef-48537783d117","year":2022},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.362855Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:d52512b4a77f7d1773a03b812d0cf7075673c8ccbe433dde578fab028a6a3133","observation_id":"cea73d1e-a21c-4c98-80d9-68cce9396551","resolution":{"observed_at":"2026-08-15T21:01:34.713336Z","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":"2026-08-15T21:01:34.693306Z","title":"Feel-snn: Robust spiking neural networks with frequency encoding and evolutionary l eak factor","venue":null,"work_id":"cfc8038f-4bbf-4ede-a2f8-6dfe9aabd8db","year":2024},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.368631Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:2466123cc41da12e7004c14d85413b2ade6888d6ce5bee1ed8f144b4eb40e3f3","observation_id":"5ded862d-bf54-4f26-8697-09ab278b1aaf","resolution":{"observed_at":"2026-08-15T21:01:34.698593Z","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":"2026-08-15T21:01:34.677365Z","title":"Hierarchical spiking-based model for efficient image class ification with enhanced feature ex- traction and encoding","venue":null,"work_id":"d46b973f-5321-4d68-be8e-4907eadbcd7d","year":2022},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.373255Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:54f8c742b520dfe34888fd6b6725b3c4b5e08ab526f8d870ad6470ee7feaffb1","observation_id":"f8d34ae4-0310-4aff-ad8d-ef05ae7280ab","resolution":{"observed_at":"2026-08-15T21:01:34.682058Z","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":"2026-08-15T21:01:34.663509Z","title":"Pyhessian: Neural networks through the lens of the hessian","venue":null,"work_id":"c181c26f-d4fe-43d1-bd0d-645f614d8fe8","year":2020},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.377848Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:7c5acb83186dcb41b8afd0ae5a22bc19892cd6500880b13b30b923cdf5df8e74","observation_id":"0d2a83b6-5c7f-4361-8851-35c4fb736a37","resolution":{"observed_at":"2026-08-15T21:01:34.668268Z","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":"2026-08-15T21:01:34.650638Z","title":"Spiking neu ral networks in intelligent edge computing","venue":null,"work_id":"a9e45ce1-eb26-45a5-8b60-2932b58feb3f","year":2024},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.383600Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:7ee1bf7ca542aface94804b336605335c9473eb6d887c28fbc268ef9aab672dd","observation_id":"c33da9fa-a343-49a2-9612-ef9d8f952932","resolution":{"observed_at":"2026-08-15T21:01:34.654814Z","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":"2026-08-15T21:01:34.636154Z","title":"Autonomous driving with spiking neural networks","venue":null,"work_id":"0084810d-9a07-47d1-ae58-73af75936825","year":2024},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.389411Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:0e401d6c4f90f8dc6b092e4fc2a70b8670a3566ef463c3d07dcfd97cf5a872bf","observation_id":"51a59173-4d33-495c-b5e6-ea9a703df4dc","resolution":{"observed_at":"2026-08-15T21:01:34.640581Z","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":"2026-08-15T21:01:34.619446Z","title":"Defending batch-level label inference and repla cement attacks in vertical federated learning","venue":null,"work_id":"6cb7399b-6e30-46e4-805c-0390aa72b34a","year":2022},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.395471Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:2837e7d0d59f6b605f380eb7b9aa71477bf0c65f67903f3d2a6b6d2b33655285","observation_id":"c025bac3-6ecc-4836-841b-da057d4d76df","resolution":{"observed_at":"2026-08-15T21:01:34.623861Z","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":"2026-08-15T21:01:34.603787Z","title":"Table 5: Hyperparameter settings for experiments","venue":null,"work_id":"e1af084b-9432-4357-900d-bbf14c3a29b3","year":null},"citing_paper":{"arxiv_id":"2505.11134","last_updated":"2025-05-16T11:29:49Z","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:34.401475Z"},"links":{"citing_paper":"/paper/2505.11134"},"observation_digest":"sha256:bd3ce1bf92ebe2d4de3194708f7055243dc644e36656ba838ac91c639d90742a","observation_id":"fe58af80-4d7c-4e01-b409-72f10382f525","resolution":{"observed_at":"2026-08-15T21:01:34.609895Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"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":"2505.11134","last_updated":"2025-05-16T11:29:49Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T20:54:52.465357Z","submitted_at":"2025-05-16T11:29:49Z","title":"Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection"},"reference_resolution":{"displayed":43,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":11,"verified_exact":2,"verified_fuzzy":29},"total_outbound_references":43},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-18T06:34:40.430872+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 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2505.11134."}