{"as_of":"2026-08-15T03:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a4ac2a23c3daae29e0137800b9b9af3fbcdb581929e575532750faf5b11322eb","coverage":[{"denominator":20,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":20,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T23:04:15.585923Z","state":"measured"},{"denominator":20,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":20,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+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/2508.06109/citation-record","integrity":"/paper/2508.06109/integrity","json":"/paper/2508.06109/citation-record.json","paper":"/paper/2508.06109"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T23:04:15.825727Z","title":"Uncertainty in machine learning: A safety perspective on autonomous driving,","venue":null,"work_id":"62ec397b-383b-40c7-8114-15ad711df5ca","year":2018},"citing_paper":{"arxiv_id":"2508.06109","last_updated":"2025-08-17T02:24:50Z","snapshot_observed_at":"2026-08-06T21:49:56.210675Z","submitted_at":"2025-08-08T08:15:26Z","title":"FMCE-Net++: Feature Map Convergence Evaluation and Training","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T23:04:15.526261Z"},"links":{"citing_paper":"/paper/2508.06109"},"observation_digest":"sha256:d69deb1f3e081de7af7385b86b90ded77b8faa338291d1486e7d14eb72944a22","observation_id":"038be50d-3efb-4efd-aae8-4d91b00168ad","resolution":{"observed_at":"2026-08-05T23:04:15.828788Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-05T23:04:15.815476Z","title":"Deep learning for safe autonomous driving: Current challenges and future directions,","venue":null,"work_id":"7bc4efe7-be2a-4ebf-985c-73180a67ef14","year":2020},"citing_paper":{"arxiv_id":"2508.06109","last_updated":"2025-08-17T02:24:50Z","snapshot_observed_at":"2026-08-06T21:49:56.210675Z","submitted_at":"2025-08-08T08:15:26Z","title":"FMCE-Net++: Feature Map Convergence Evaluation and Training","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T23:04:15.529880Z"},"links":{"citing_paper":"/paper/2508.06109"},"observation_digest":"sha256:bcb60c16b905d482181c70d72f26bd29ba32e52dd73fa326609da9dfbac3de9f","observation_id":"7eb27a60-2b3a-4b28-995a-5d2bb9fbaf0e","resolution":{"observed_at":"2026-08-05T23:04:15.818803Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-05T23:04:15.805329Z","title":"Explainability of deep vision-based autonomous driving systems: Review and chal- lenges,","venue":null,"work_id":"041abf94-b495-4d08-b5bd-984c928ab976","year":2022},"citing_paper":{"arxiv_id":"2508.06109","last_updated":"2025-08-17T02:24:50Z","snapshot_observed_at":"2026-08-06T21:49:56.210675Z","submitted_at":"2025-08-08T08:15:26Z","title":"FMCE-Net++: Feature Map Convergence Evaluation and Training","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T23:04:15.533000Z"},"links":{"citing_paper":"/paper/2508.06109"},"observation_digest":"sha256:2b70ebb29a66faa59f5a0ac36a5be57d840c6052aac7380e63e7c7009f0c6c4c","observation_id":"897bd65f-9064-44a4-84e6-89d91b8289c2","resolution":{"observed_at":"2026-08-05T23:04:15.808723Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-05T23:04:15.794736Z","title":"Explainable arti- ficial intelligence for autonomous driving: A comprehensive overview and field guide for future research directions,","venue":null,"work_id":"ae3f51b6-b66c-4402-a33a-b79c7ecd63f3","year":2024},"citing_paper":{"arxiv_id":"2508.06109","last_updated":"2025-08-17T02:24:50Z","snapshot_observed_at":"2026-08-06T21:49:56.210675Z","submitted_at":"2025-08-08T08:15:26Z","title":"FMCE-Net++: Feature Map Convergence Evaluation and Training","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T23:04:15.536074Z"},"links":{"citing_paper":"/paper/2508.06109"},"observation_digest":"sha256:e2e3d4cce101a0151b865606f4473682888911e9cc68aba404e05a74b9f16a88","observation_id":"9677aa3e-643a-497b-bd8e-feea81774f4e","resolution":{"observed_at":"2026-08-05T23:04:15.798219Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.04041","last_updated":"2024-05-07T06:25:49Z","snapshot_observed_at":"2026-08-13T00:13:24.944118Z","submitted_at":"2024-05-07T06:25:49Z","title":"Feature Map Convergence Evaluation for Functional Module","version":1},"cited_work":{"arxiv_id":"2405.04041","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.04041","snapshot_observed_at":"2026-08-05T23:04:15.648279Z","title":"Feature Map Convergence Evaluation for Functional Module","venue":"cs.AI","work_id":"68abde24-66a8-4002-959f-7b04c15488d9","year":2024},"citing_paper":{"arxiv_id":"2508.06109","last_updated":"2025-08-17T02:24:50Z","snapshot_observed_at":"2026-08-06T21:49:56.210675Z","submitted_at":"2025-08-08T08:15:26Z","title":"FMCE-Net++: Feature Map Convergence Evaluation and Training","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T23:04:15.539409Z"},"links":{"cited_paper":"/paper/2405.04041","citing_paper":"/paper/2508.06109"},"observation_digest":"sha256:f5956e3786b7fd99e5898f6b6253d2bdce48ec53e310c8ff8af0efd718383280","observation_id":"35c07198-3490-4b25-8c61-2ddbee2b60a0","resolution":{"observed_at":"2026-08-05T23:04:15.651856Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-05T23:04:15.783618Z","title":"To what extent do dnn-based image classification models make unreliable inferences?","venue":null,"work_id":"5d8ce1bd-545a-48fe-a071-68d849cb7e29","year":2021},"citing_paper":{"arxiv_id":"2508.06109","last_updated":"2025-08-17T02:24:50Z","snapshot_observed_at":"2026-08-06T21:49:56.210675Z","submitted_at":"2025-08-08T08:15:26Z","title":"FMCE-Net++: Feature Map Convergence Evaluation and Training","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T23:04:15.542827Z"},"links":{"citing_paper":"/paper/2508.06109"},"observation_digest":"sha256:926ade31ea27a0823896752ef111cee718b2670278ac4994cc80b6583855ff73","observation_id":"d8e16d9b-2bd9-44c8-9cee-9dc6a214bb0a","resolution":{"observed_at":"2026-08-05T23:04:15.786836Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-05T23:04:15.773404Z","title":"Image classification using dnn with an improved optimizer,","venue":null,"work_id":"f606ac76-12fe-44a2-8d83-b8cab8029895","year":2020},"citing_paper":{"arxiv_id":"2508.06109","last_updated":"2025-08-17T02:24:50Z","snapshot_observed_at":"2026-08-06T21:49:56.210675Z","submitted_at":"2025-08-08T08:15:26Z","title":"FMCE-Net++: Feature Map Convergence Evaluation and Training","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T23:04:15.546275Z"},"links":{"citing_paper":"/paper/2508.06109"},"observation_digest":"sha256:72658a0e659e9274cb914c03ae002cbb2cb13559b64a5d5c67a205fc292054d2","observation_id":"12ed1ccb-b12d-4461-bb3d-640cd1029c74","resolution":{"observed_at":"2026-08-05T23:04:15.776497Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-05T23:04:15.763540Z","title":"isec: An optimized deep learning model for image classification on edge computing,","venue":null,"work_id":"6c73a68b-cffd-405d-bc23-bb54ac3bbb58","year":2020},"citing_paper":{"arxiv_id":"2508.06109","last_updated":"2025-08-17T02:24:50Z","snapshot_observed_at":"2026-08-06T21:49:56.210675Z","submitted_at":"2025-08-08T08:15:26Z","title":"FMCE-Net++: Feature Map Convergence Evaluation and Training","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T23:04:15.548987Z"},"links":{"citing_paper":"/paper/2508.06109"},"observation_digest":"sha256:288a7ad3f47f76c1a9f1090594c64d0e5088adc22d020cfdf75f2ef6b4c7ff16","observation_id":"55e9a9c2-8d9e-4ee3-908c-607ce6144d56","resolution":{"observed_at":"2026-08-05T23:04:15.766778Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-05T23:04:15.753544Z","title":"Optimizing convolutional neural networks archi- tecture using a modified particle swarm optimization for image classi- fication,","venue":null,"work_id":"5aeb47b7-ea15-45c9-ad54-06d8aa12ab50","year":2023},"citing_paper":{"arxiv_id":"2508.06109","last_updated":"2025-08-17T02:24:50Z","snapshot_observed_at":"2026-08-06T21:49:56.210675Z","submitted_at":"2025-08-08T08:15:26Z","title":"FMCE-Net++: Feature Map Convergence Evaluation and Training","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T23:04:15.552022Z"},"links":{"citing_paper":"/paper/2508.06109"},"observation_digest":"sha256:e8bcfa0b04f9b616f291413beda4c5900caed4c7f019f59b142a855655990184","observation_id":"8fda686a-919a-484a-b776-319899e0d36d","resolution":{"observed_at":"2026-08-05T23:04:15.756717Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2007.13005","last_updated":"2020-07-25T20:26:05Z","snapshot_observed_at":"2026-08-12T02:56:20.062398Z","submitted_at":"2020-07-25T20:26:05Z","title":"Jointly Optimizing Preprocessing and Inference for DNN-based Visual Analytics","version":1},"cited_work":{"arxiv_id":"2007.13005","doi":null,"metadata_source":"pith","pith_arxiv_id":"2007.13005","snapshot_observed_at":"2026-08-05T23:04:15.632758Z","title":"Jointly Optimizing Preprocessing and Inference for DNN-based Visual Analytics","venue":"cs.DB","work_id":"b6ec3067-61ee-4c56-9b7a-bff1de3537e1","year":2020},"citing_paper":{"arxiv_id":"2508.06109","last_updated":"2025-08-17T02:24:50Z","snapshot_observed_at":"2026-08-06T21:49:56.210675Z","submitted_at":"2025-08-08T08:15:26Z","title":"FMCE-Net++: Feature Map Convergence Evaluation and Training","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T23:04:15.554961Z"},"links":{"cited_paper":"/paper/2007.13005","citing_paper":"/paper/2508.06109"},"observation_digest":"sha256:bc843ce50b3071642bc558c4629125fc61134f391525dbd2f1f8116a13a662d9","observation_id":"360cbb24-3b83-497c-b36a-82c28ac9c79d","resolution":{"observed_at":"2026-08-05T23:04:15.636300Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-05T23:04:15.743500Z","title":"A testing and evaluation framework for the quality of dnn models,","venue":null,"work_id":"2703a906-40f4-4990-8cba-c468f2559447","year":2024},"citing_paper":{"arxiv_id":"2508.06109","last_updated":"2025-08-17T02:24:50Z","snapshot_observed_at":"2026-08-06T21:49:56.210675Z","submitted_at":"2025-08-08T08:15:26Z","title":"FMCE-Net++: Feature Map Convergence Evaluation and Training","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T23:04:15.558166Z"},"links":{"citing_paper":"/paper/2508.06109"},"observation_digest":"sha256:13e18379ccf5f867a624ba07e3dd0be2f577db8181e31f9f3d62978d8763577e","observation_id":"bc33a50a-d461-4b88-b1d1-86dad22ea42f","resolution":{"observed_at":"2026-08-05T23:04:15.746722Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-05T23:04:15.733594Z","title":"Deepxplore: Automated whitebox testing of deep learning systems,","venue":null,"work_id":"b80ce29f-52c3-47f5-86c7-d1f33e5f6534","year":2017},"citing_paper":{"arxiv_id":"2508.06109","last_updated":"2025-08-17T02:24:50Z","snapshot_observed_at":"2026-08-06T21:49:56.210675Z","submitted_at":"2025-08-08T08:15:26Z","title":"FMCE-Net++: Feature Map Convergence Evaluation and Training","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T23:04:15.561141Z"},"links":{"citing_paper":"/paper/2508.06109"},"observation_digest":"sha256:85aa8c5fabf4dad5780d152f570b5c3aedbee56666cccddf6025c93e880e1f2f","observation_id":"b781d346-8f85-4d0c-9b3d-8dbeaf5e585c","resolution":{"observed_at":"2026-08-05T23:04:15.736700Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-05T23:04:15.723602Z","title":"Efficient online testing for dnn- enabled systems using surrogate-assisted and many-objective opti- mization,","venue":null,"work_id":"38a22772-9804-4cea-a545-69eb0b42c50b","year":2022},"citing_paper":{"arxiv_id":"2508.06109","last_updated":"2025-08-17T02:24:50Z","snapshot_observed_at":"2026-08-06T21:49:56.210675Z","submitted_at":"2025-08-08T08:15:26Z","title":"FMCE-Net++: Feature Map Convergence Evaluation and Training","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T23:04:15.564755Z"},"links":{"citing_paper":"/paper/2508.06109"},"observation_digest":"sha256:a8a73a1c8d2cff3d1f430fef113c5eba64139734a474aab373cd00efc33ad2e2","observation_id":"ac1b6c1e-7e26-4517-b9de-ba57fb9c4256","resolution":{"observed_at":"2026-08-05T23:04:15.726870Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-05T23:04:15.713448Z","title":"A scenario- based functional testing approach to improving dnn performance,","venue":null,"work_id":"507d7365-7cfa-44eb-b08e-efc390d1abba","year":2023},"citing_paper":{"arxiv_id":"2508.06109","last_updated":"2025-08-17T02:24:50Z","snapshot_observed_at":"2026-08-06T21:49:56.210675Z","submitted_at":"2025-08-08T08:15:26Z","title":"FMCE-Net++: Feature Map Convergence Evaluation and Training","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T23:04:15.567690Z"},"links":{"citing_paper":"/paper/2508.06109"},"observation_digest":"sha256:2106898b79fd7ebb56b142131faafad579822b88b61a07857cfc039b276f52ba","observation_id":"e5e1eb25-efd2-49c5-a6f4-3fb5e9f4c544","resolution":{"observed_at":"2026-08-05T23:04:15.716690Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-05T23:04:15.703202Z","title":"Selection of test samples to improve dnn test efficiency based on neuron clusters,","venue":null,"work_id":"3c22d463-c99e-4c95-a6f4-b1e08d93b77b","year":2024},"citing_paper":{"arxiv_id":"2508.06109","last_updated":"2025-08-17T02:24:50Z","snapshot_observed_at":"2026-08-06T21:49:56.210675Z","submitted_at":"2025-08-08T08:15:26Z","title":"FMCE-Net++: Feature Map Convergence Evaluation and Training","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T23:04:15.570528Z"},"links":{"citing_paper":"/paper/2508.06109"},"observation_digest":"sha256:df4162699b31851a90a6a96871b4104c13bdb280d3e344efbd2d7ed8bcc897db","observation_id":"c37cd7a9-9088-4a99-a95c-4ead8803edea","resolution":{"observed_at":"2026-08-05T23:04:15.706232Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.09716","last_updated":"2022-03-17T08:58:51Z","snapshot_observed_at":"2026-08-08T09:51:17.979311Z","submitted_at":"2021-03-17T15:18:18Z","title":"Quantitative Performance Assessment of CNN Units via Topological Entropy Calculation","version":5},"cited_work":{"arxiv_id":"2103.09716","doi":null,"metadata_source":"pith","pith_arxiv_id":"2103.09716","snapshot_observed_at":"2026-08-05T23:04:15.614813Z","title":"Quantitative Performance Assessment of CNN Units via Topological Entropy Calculation","venue":"cs.CV","work_id":"61cfba8c-eb94-4c40-ad0e-978d90a13cf6","year":2021},"citing_paper":{"arxiv_id":"2508.06109","last_updated":"2025-08-17T02:24:50Z","snapshot_observed_at":"2026-08-06T21:49:56.210675Z","submitted_at":"2025-08-08T08:15:26Z","title":"FMCE-Net++: Feature Map Convergence Evaluation and Training","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T23:04:15.573581Z"},"links":{"cited_paper":"/paper/2103.09716","citing_paper":"/paper/2508.06109"},"observation_digest":"sha256:0f408b23c195256644b8e8419001ca1f85c3f5c35a83a0c006f85ae429ff41d0","observation_id":"541abb9c-f028-4866-887d-eb377c80eaeb","resolution":{"observed_at":"2026-08-05T23:04:15.620588Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-05T23:04:15.693048Z","title":"Explaining the black- box model: A survey of local interpretation methods for deep neural networks,","venue":null,"work_id":"f3da3ef3-a031-4252-a79b-02eedd3f0db3","year":2021},"citing_paper":{"arxiv_id":"2508.06109","last_updated":"2025-08-17T02:24:50Z","snapshot_observed_at":"2026-08-06T21:49:56.210675Z","submitted_at":"2025-08-08T08:15:26Z","title":"FMCE-Net++: Feature Map Convergence Evaluation and Training","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T23:04:15.576797Z"},"links":{"citing_paper":"/paper/2508.06109"},"observation_digest":"sha256:03db0232dfed528e48f96d07e071916491c2da7b72ea9564993930caafea2fd2","observation_id":"936b6c0b-1235-4776-8779-8c0d16b973f6","resolution":{"observed_at":"2026-08-05T23:04:15.696479Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-05T23:04:15.681479Z","title":"Accelerating image classification using feature map similarity in convolutional neural networks,","venue":null,"work_id":"b6f3479e-1c76-4312-b832-a0cc3ca7304d","year":2018},"citing_paper":{"arxiv_id":"2508.06109","last_updated":"2025-08-17T02:24:50Z","snapshot_observed_at":"2026-08-06T21:49:56.210675Z","submitted_at":"2025-08-08T08:15:26Z","title":"FMCE-Net++: Feature Map Convergence Evaluation and Training","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T23:04:15.579670Z"},"links":{"citing_paper":"/paper/2508.06109"},"observation_digest":"sha256:43a37d7f6289c758fe008d36b7b371b3c19b6ee2ba22b6020e7380aaffe36fca","observation_id":"2a7f9583-db4e-4547-98af-f437d4254361","resolution":{"observed_at":"2026-08-05T23:04:15.685377Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-05T23:04:15.670641Z","title":"End-to-end self-driving using deep neural networks with multi-auxiliary tasks,","venue":null,"work_id":"634422b4-1512-4535-868a-a1126aede7b1","year":2019},"citing_paper":{"arxiv_id":"2508.06109","last_updated":"2025-08-17T02:24:50Z","snapshot_observed_at":"2026-08-06T21:49:56.210675Z","submitted_at":"2025-08-08T08:15:26Z","title":"FMCE-Net++: Feature Map Convergence Evaluation and Training","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T23:04:15.582730Z"},"links":{"citing_paper":"/paper/2508.06109"},"observation_digest":"sha256:6b87caedafaa806706b4036d286e0c29fc51c0ee671b2ac74098ec165197aca3","observation_id":"b0c8bac9-428d-4c11-898f-43994a631046","resolution":{"observed_at":"2026-08-05T23:04:15.674177Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-05T23:04:15.659326Z","title":"Bevformer v2: Adapting modern image backbones to bird’s-eye-view recognition via perspective supervision,","venue":null,"work_id":"d31d1529-872b-4640-bf80-d16a7757d88b","year":2023},"citing_paper":{"arxiv_id":"2508.06109","last_updated":"2025-08-17T02:24:50Z","snapshot_observed_at":"2026-08-06T21:49:56.210675Z","submitted_at":"2025-08-08T08:15:26Z","title":"FMCE-Net++: Feature Map Convergence Evaluation and Training","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T23:04:15.585923Z"},"links":{"citing_paper":"/paper/2508.06109"},"observation_digest":"sha256:64cff98486b7403bf476df4ac18d6ca921a84423b8c8fefaddacc265dde159d6","observation_id":"bf9fdf26-b276-4ef9-b121-d79d30b8e1d8","resolution":{"observed_at":"2026-08-05T23:04:15.663191Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2508.06109","last_updated":"2025-08-17T02:24:50Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T21:49:56.210675Z","submitted_at":"2025-08-08T08:15:26Z","title":"FMCE-Net++: Feature Map Convergence Evaluation and Training"},"reference_resolution":{"displayed":20,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":3,"verified_fuzzy":17},"total_outbound_references":20},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 0 inbound Pith citation observations for arXiv:2508.06109."}