{"as_of":"2026-08-11T03:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:10394c67f7fde285af48e8423139fe107687bb544f13468d709e56c1472bea94","coverage":[{"denominator":59,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":59,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-09T22:22:15.878399Z","state":"measured"},{"denominator":59,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":59,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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/2607.06982/citation-record","integrity":"/paper/2607.06982/integrity","json":"/paper/2607.06982/citation-record.json","paper":"/paper/2607.06982"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T22:26:37.391089Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":"352cc249-6040-41d0-90fe-7fc5f7e3cdef","year":2009},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:ae57d1aee3ef0b29dee3bb205592c273ac95edc0e981a502b9be937a1e5db385","observation_id":"8a046f65-d4dd-4024-969b-49a521ba9cb2","resolution":{"observed_at":"2026-07-09T22:26:37.392357Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.344151Z","title":"Microsoft coco: Common objects in context,","venue":null,"work_id":"19f5b431-c35a-4d5a-bc2b-f252711bd1fa","year":2014},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:97c58f5e05e135d0c60f6a0fbc43dd4d7b85d2b24312fa9f0cf2cfdf6c916eac","observation_id":"29d2a971-e160-42b2-9759-dfb75adcdb14","resolution":{"observed_at":"2026-07-09T22:26:37.345212Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.406001Z","title":"Efficientnet: Rethinking model scaling for convo- lutional neural networks,","venue":null,"work_id":"dee5d4f4-287f-4ca3-a9a0-bff94c597603","year":2019},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:45f50735083e72a1b618447aa23ca7f1d8f1bf52152b59ebe104ed9bf2579e3b","observation_id":"1183d727-9043-4f55-a48a-5b04eac7d2bd","resolution":{"observed_at":"2026-07-09T22:26:37.407100Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.404455Z","title":"Designing network design spaces,","venue":null,"work_id":"71a700b6-4600-4e7b-9bfd-d28d0f8590c6","year":2020},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:2ba07175ff1521d33f83d0330833bc8d697afd88e6a0f5572e3c97c3f18533b8","observation_id":"692f006f-d91d-4516-8434-f74e4f53e86b","resolution":{"observed_at":"2026-07-09T22:26:37.405483Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.350904Z","title":"A convnet for the 2020s,","venue":null,"work_id":"194b81b9-9bee-45ee-9686-66277fd4fff9","year":2022},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:546e969f927f5a6dcf7792ef2759ed241e07e492a921145cdec30fac29f298ab","observation_id":"47ee679b-bc04-44c9-be48-04c3ee2c23e1","resolution":{"observed_at":"2026-07-09T22:26:37.351944Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.397757Z","title":"Edge computing: Vision and challenges,","venue":null,"work_id":"590563c6-2315-4668-98a6-8f03211e40cb","year":2016},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:f71c9265c593a1c7e32de82724d5ed6ca33b38a4963c18d75646fc48744aaba0","observation_id":"ce83e113-4041-42a9-b879-f512b0aa2770","resolution":{"observed_at":"2026-07-09T22:26:37.398841Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.401067Z","title":"Update compression for deep neural networks on the edge,","venue":null,"work_id":"41a7fe80-be7e-49ad-986b-0aa68858d8c6","year":2022},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:d14b49679d8b4ede640f2f4fb9199ccd64e0c269095fd6eb8c489775dafd0d68","observation_id":"f2173493-1a87-481b-bd67-35f320f411ce","resolution":{"observed_at":"2026-07-09T22:26:37.402221Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.376366Z","title":"Mobilenetv2: Inverted residuals and linear bottle- necks,","venue":null,"work_id":"4cb6aa86-e3ba-4a41-975a-6f86f37bb8b2","year":2018},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:8b3883688d1d2cfad489b05d42fcee47711fbff3d3e415578c93e7ad78d2b7f8","observation_id":"9abb729c-4370-4d5a-8432-2fd8af121b62","resolution":{"observed_at":"2026-07-09T22:26:37.377498Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.373095Z","title":"Mnasnet: Platform-aware neural architecture search for mobile,","venue":null,"work_id":"57c1dadb-efcc-4925-bcdb-a0a298c5f45b","year":2019},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:7e4abc82218d29c325b5b8b2cddaba0b8c2c63f7e4c58f9bcf32c36a39431969","observation_id":"3b4243f8-4917-4d41-a0ea-fed1d1db4bb4","resolution":{"observed_at":"2026-07-09T22:26:37.374182Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.330044Z","title":"Dynamic resolution network,","venue":null,"work_id":"68388a7a-df0c-470a-9ed9-dc4cb55c64de","year":2021},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:699b9de998e889a7f519198452a0e2969009ef20237ff322c1dbc75a4ad01bc6","observation_id":"0d52e1bd-fea8-4cb8-ba5c-9ac11ebdeb1b","resolution":{"observed_at":"2026-07-09T22:26:37.331064Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.411078Z","title":"Hrank: Filter pruning using high-rank feature map,","venue":null,"work_id":"df1f3ea7-9664-4791-893d-3c6a1a360d6f","year":2020},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:57d4b18a97d411e07a51a62d9b86e1c2756a9ec019fbc9e465bf57cb91e4f8cd","observation_id":"1233fa3f-15e5-42c6-bfac-ff46311d15cb","resolution":{"observed_at":"2026-07-09T22:26:37.412228Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.368173Z","title":"Convolutional neural network pruning with structural redundancy reduction,","venue":null,"work_id":"35fa457b-694a-403e-8dbd-ec94e1b3da60","year":2021},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:ac2230166063039318b55bfd6521a9bf278d5586b188520d9756dfaad0d39b5e","observation_id":"4c5d7915-a8f8-47c7-ba39-c58137f14d16","resolution":{"observed_at":"2026-07-09T22:26:37.369289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.357492Z","title":"Slimmable neural networks,","venue":null,"work_id":"d6819fdf-6e2f-4a26-926a-d4cb8c9932c9","year":2019},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:be74acb68f9558ad6610f021bbbaed17609f33a60bb6014e10a3fec7402b5f37","observation_id":"56168db5-e2de-4f33-a435-9d7f128d77d5","resolution":{"observed_at":"2026-07-09T22:26:37.358515Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.371488Z","title":"Importance estimation for neural network pruning,","venue":null,"work_id":"de428cf5-baae-458e-b022-1ac1dad17f3b","year":2019},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:6750ac3372054310b8f3f07455b63ab6363e63ab2aba3c1cc3a9183887fc68e1","observation_id":"71abaab2-8159-427b-be1d-b45a5754ee4d","resolution":{"observed_at":"2026-07-09T22:26:37.372597Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1912.10178","last_updated":"2019-12-21T02:11:47Z","snapshot_observed_at":"2026-07-06T08:46:12.464068Z","submitted_at":"2019-12-21T02:11:47Z","title":"DBP: Discrimination Based Block-Level Pruning for Deep Model Acceleration","version":1},"cited_work":{"arxiv_id":"1912.10178","doi":null,"metadata_source":"pith","pith_arxiv_id":"1912.10178","snapshot_observed_at":"2026-07-09T22:26:36.953222Z","title":"DBP: Discrimination Based Block-Level Pruning for Deep Model Acceleration","venue":"cs.CV","work_id":"78adc891-d421-4c92-88ac-c97543185997","year":2019},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"cited_paper":"/paper/1912.10178","citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:ef776c0d85dc1d3f1b0736581b93a2dfbc8d8d2b60813f7d0db8badc71b39164","observation_id":"4b0b0839-d8e7-42bb-8d5c-62a62663ea65","resolution":{"observed_at":"2026-07-09T22:26:36.954380Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.381283Z","title":"Decore: Deep compression with reinforcement learning,","venue":null,"work_id":"4664b25c-8538-413b-96a7-8644966373ca","year":2022},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:ca48771a73f34caabbdbc018a09120b1522a1d9393ec760149963e109fe4e38a","observation_id":"798f0d20-511c-44ad-a914-d9a430f6b84c","resolution":{"observed_at":"2026-07-09T22:26:37.382361Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.384548Z","title":"Glance and focus: A dynamic approach to reducing spatial redundancy in image classification,","venue":null,"work_id":"e53ccd7e-efc5-4d6a-956d-9a07914773d1","year":2020},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:8157bef9fa8e6823c50708a343ed2f36cd516adf9644454337edb591dacee13a","observation_id":"318c22ea-5ba7-4c52-b463-04587e75b8e1","resolution":{"observed_at":"2026-07-09T22:26:37.385716Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2004.10934","last_updated":"2020-04-23T02:10:02Z","snapshot_observed_at":"2026-07-06T09:14:32.318388Z","submitted_at":"2020-04-23T02:10:02Z","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","version":1},"cited_work":{"arxiv_id":"2004.10934","doi":"10.3390/s22052341","metadata_source":"pith","pith_arxiv_id":"2004.10934","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","venue":"cs.CV","work_id":"7057aaee-27f6-4209-a83c-f59727f937a8","year":2020},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"cited_paper":"/paper/2004.10934","citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:f2b1f7cc602c89073e1d01b150494d9be9800716dcaa0fd606b0a4f64df8a828","observation_id":"ef71f83a-ab42-424a-ab76-592b81d53abe","resolution":{"observed_at":"2026-07-09T22:26:36.952108Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.387881Z","title":"Ssd: Single shot multibox detector,","venue":null,"work_id":"372b4583-29fe-4c02-8162-9d911e66f705","year":2016},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:7ce79685a39f1ffd06dbab2c7b574ef794a60f229069c91c76cd7beb31f5b716","observation_id":"35aa6036-07e6-47bd-96c0-81a3d7ddb9f4","resolution":{"observed_at":"2026-07-09T22:26:37.388923Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.331554Z","title":"Faster r-cnn: Towards real-time object detection with region proposal networks,","venue":null,"work_id":"41b90472-f727-4684-afc9-cd679eb5fd6e","year":2015},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:9c259a1c8ec7818630c7fcbef1deced3e3a4b3087a8a0d0d91e3e0b52d708d6f","observation_id":"dfe6d824-74c3-43d1-a966-8bde2cb3baa4","resolution":{"observed_at":"2026-07-09T22:26:37.332677Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.416253Z","title":"Mask r-cnn,","venue":null,"work_id":"a95c70e3-426a-4ff2-9cb5-e95f54865b33","year":2017},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:9d99bf3c4fdf78084ed76a3b553e0d97532aeb83cd29ab60f1de5a31b15e52e1","observation_id":"af843880-c3f7-418e-8d2d-e2bb21afbea5","resolution":{"observed_at":"2026-07-09T22:26:37.417303Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.386266Z","title":"The pascal visual object classes (voc) challenge,","venue":null,"work_id":"007b7b78-7df6-44f4-ac2e-bf91c43be5b7","year":2010},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:4e8e79eb6a35861ad518b211b9253cd5595ca4238bed279aaa932f20ada3edc4","observation_id":"f5d8b722-87fe-4bfb-98fe-ba238a437869","resolution":{"observed_at":"2026-07-09T22:26:37.387387Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.342536Z","title":"Unsupervised object discovery and co-localization by deep descriptor transformation,","venue":null,"work_id":"e59909b4-49a5-4787-8700-bb1690a27e9b","year":2019},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:6610556602822f460c4f94c2d7bfcb7915785941e338171514ff22ec90b163e5","observation_id":"0c04ca1b-fd2e-442b-b762-a71112ba65d7","resolution":{"observed_at":"2026-07-09T22:26:37.343624Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.374718Z","title":"Rethinking the route towards weakly supervised object localization,","venue":null,"work_id":"02fe72fa-27d7-4fc1-8efb-253a69dcf315","year":2020},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:df37f22c9c912f26a643f99ad53f6d9d6c1ee646f8df2a32165c9935c2a82127","observation_id":"e0455b16-4b54-4635-a04e-65342614b804","resolution":{"observed_at":"2026-07-09T22:26:37.375841Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.421180Z","title":"Learning deep features for discriminative localization,","venue":null,"work_id":"e8630527-00c0-46ef-915d-be4b19f28e23","year":2016},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:92e692c6b5b57656c2a5e2035a460c08c021779101dccf7fcd7d04e1016af1ee","observation_id":"19e691af-08cd-4975-b2ba-29b16935f9ed","resolution":{"observed_at":"2026-07-09T22:26:37.422277Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.394488Z","title":"Grad-cam: Visual explanations from deep networks via gradient-based localization,","venue":null,"work_id":"03ce73cb-8041-4f48-8295-229128493646","year":2017},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:eb56a67f833c780f2ff997d60d3a4bdd83168859adcc81d18dc7757a1615c60f","observation_id":"319f8e9b-6353-42af-81f6-726703fa64f8","resolution":{"observed_at":"2026-07-09T22:26:37.395619Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.366507Z","title":"Adversarial complementary learning for weakly supervised object localization,","venue":null,"work_id":"7c2f2903-53fd-4349-8839-7b8c432f6b40","year":2018},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:cc47c70823b23aaae0af07727ef20279bcff971c6089f150613efc331c740ee9","observation_id":"dae90626-c7b6-4e35-9f92-af58fe67c203","resolution":{"observed_at":"2026-07-09T22:26:37.367620Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.412765Z","title":"Bringing ai to edge: From deep learning’s perspective,","venue":null,"work_id":"913a6211-58a9-452d-8cc3-20703038039c","year":2022},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:6bb8421e53605fd1954d5a4ac5ec00ccdaba4b331441bef09313d8c11b0af343","observation_id":"310c3b26-f629-4d75-93d0-14838a02f07e","resolution":{"observed_at":"2026-07-09T22:26:37.413895Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.347556Z","title":"Layer pruning for obtaining shallower resnets,","venue":null,"work_id":"384b5c25-a9da-4c1d-9e48-771299ae58bf","year":2022},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:526c5c27d6d997f640ca0fe6ba0bb2eb0e20fb6bd660aee92a7c058b122887cb","observation_id":"a2c19f64-cb0d-4a60-857b-3cbbefda73d5","resolution":{"observed_at":"2026-07-09T22:26:37.348620Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.389422Z","title":"Branchynet: Fast inference via early exiting from deep neural networks,","venue":null,"work_id":"51c8145e-f6be-40c0-b0bd-b5c275475eda","year":2016},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:8b870dd6bca1c4aebfa236d69deb450583b2f785098d9fa129997f54ba960581","observation_id":"30b7b61f-3258-4632-97f8-311239f42ea6","resolution":{"observed_at":"2026-07-09T22:26:37.390566Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.345754Z","title":"Multi-scale dense networks for resource efficient image classification,","venue":null,"work_id":"24222053-39e8-4fb7-9ea6-5ddab963e9a7","year":2018},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:d95a65445b7a486ea67e77801e54f1ef59d3956cadcf074edf4592249248280b","observation_id":"1f0eb744-6d6d-46c0-ac7b-8a562f331be4","resolution":{"observed_at":"2026-07-09T22:26:37.347019Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.364731Z","title":"Adaptive neural networks for efficient inference,","venue":null,"work_id":"3efa0c22-977e-418a-aeee-0aaf2762f9a3","year":2017},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:9eeab91f123710fe963d015b45b1f536537e9fa04b99249b4751e43d13a396f2","observation_id":"1f2658c8-f774-4e34-8518-8b7ef896aaf6","resolution":{"observed_at":"2026-07-09T22:26:37.365987Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1603.08983","last_updated":"2017-02-21T16:21:21Z","snapshot_observed_at":"2026-08-04T14:24:45.814840Z","submitted_at":"2016-03-29T22:09:00Z","title":"Adaptive Computation Time for Recurrent Neural Networks","version":6},"cited_work":{"arxiv_id":"1603.08983","doi":"10.48550/arxiv.1603.08983","metadata_source":"pith","pith_arxiv_id":"1603.08983","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Adaptive Computation Time for Recurrent Neural Networks","venue":"cs.NE","work_id":"75565443-173e-479c-b0e7-d2464e7630be","year":2016},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"cited_paper":"/paper/1603.08983","citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:90941437e934a5a35b6a9f06c77bf97489318d6450cca7049966c568051e0e27","observation_id":"b9595270-271d-4af2-8430-c3ac92e44cca","resolution":{"observed_at":"2026-07-09T22:26:36.958778Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.340930Z","title":"Skipnet: Learning dynamic routing in convolutional networks,","venue":null,"work_id":"6008ffde-092c-4762-baba-239c48fed09e","year":2018},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:11dc6b6a04cfea835b6318951e8005bbdf135e198ad5b2836e4960ba7d4ae809","observation_id":"188c0187-e5b0-4a48-9a64-6415f9c4ff3b","resolution":{"observed_at":"2026-07-09T22:26:37.342040Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.399338Z","title":"Convolutional networks with adaptive infer- ence graphs,","venue":null,"work_id":"8e6feecb-502a-4877-be9b-eadba89ded7e","year":2018},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:37497bc25bd82f959e4f717192ac11bc2965402218958b97fefd1a9d5a707eb6","observation_id":"1247d3a0-6732-49fc-b36d-17a5d6795f7a","resolution":{"observed_at":"2026-07-09T22:26:37.400504Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.419598Z","title":"Channel gating neural networks,","venue":null,"work_id":"bf21eec5-ed9d-4371-a0d2-edc099044d93","year":2019},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:20b60d0340cc6fb115d5c5392c3e0e0ad2c547aa20f0a6962592b1ac85e6c7aa","observation_id":"7c717072-76eb-44f3-a6c0-2e8d869aee30","resolution":{"observed_at":"2026-07-09T22:26:37.420671Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.379782Z","title":"Runtime neural pruning,","venue":null,"work_id":"a9c5d84e-35c3-4478-b0f1-b5a9cbd229b6","year":2017},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:e60886366b852dbccf2de5ed31354090e7d4a9230ca64cea5f42b9dd5d00a372","observation_id":"8223500e-7c47-4112-b225-d5437640cee0","resolution":{"observed_at":"2026-07-09T22:26:37.380784Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.396142Z","title":"Dynamic channel pruning: Feature boosting and sup- pression,","venue":null,"work_id":"e0605a60-d447-4d24-8787-4e458367a3b7","year":2019},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:f585c90981db704a2dcb2bf98157afeb3d1650fac0456cad4f7d8e6ead96ae67","observation_id":"7502524c-33a3-4a91-b677-5c19e4416849","resolution":{"observed_at":"2026-07-09T22:26:37.397254Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.334884Z","title":"Channel selection using gumbel softmax,","venue":null,"work_id":"5caeeef5-9681-4066-8d65-7a388f2c7f24","year":2020},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:e5652368f39f114cae096a10646170fff4db2300e8d40369e036e4cbd2030e9b","observation_id":"c8c2439d-200e-4b02-a908-eb7648c19426","resolution":{"observed_at":"2026-07-09T22:26:37.336097Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.361380Z","title":"Resolution adaptive networks for efficient inference,","venue":null,"work_id":"ea19afa1-c43d-4939-a695-aa58302fb236","year":2020},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:7bb2bb8d3a7e72bb2b73b61310572a632f4997c9f6850905c8e8e9f98778ca6c","observation_id":"e51cf6ce-9a47-42b1-bbe2-4bb52d800751","resolution":{"observed_at":"2026-07-09T22:26:37.362602Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.352522Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":"65b7c9d9-c746-471b-86eb-a9c7ea7dac63","year":2016},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:a88dae74d0c6d25bb9fc948d5cba5dcaacb5ccb5ee08406e350ffd7ad270881d","observation_id":"4c079a55-1887-490d-b78c-9caf522cf651","resolution":{"observed_at":"2026-07-09T22:26:37.353675Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.354211Z","title":"Tiny-dsod: Lightweight object detection for resource- restricted usages,","venue":null,"work_id":"7779673b-de7e-4913-9074-fc32ef4aa162","year":2018},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:feab510d5668a16a1f514c44f8b341d2efc9a1d28928aefa3bcd1cd6dee860d5","observation_id":"78f813fd-aaa8-4bcb-a360-c8edf594e20f","resolution":{"observed_at":"2026-07-09T22:26:37.355378Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.349101Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":"1fee57fb-c4c6-403f-98d8-cf1ff5f1cbb6","year":2015},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:b1e7e0f7a550dae0068901ee3de77ab942c173601410f4a655413aac5caacdc6","observation_id":"0ba90781-a8de-43ec-ae18-e35477d3fe78","resolution":{"observed_at":"2026-07-09T22:26:37.350157Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.392878Z","title":"An exponential learning rate schedule for deep learning,","venue":null,"work_id":"b57d430f-918c-4195-9573-c51891de3839","year":2020},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:8134561098a04d7475a7cb748a617de9361b65ebbb159e64165a20ea27c087d0","observation_id":"32f9b8e6-4a72-4914-9928-1b3b2b8ddc71","resolution":{"observed_at":"2026-07-09T22:26:37.393980Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.355910Z","title":"Hapi: Hardware-aware progressive inference,","venue":null,"work_id":"6bd4cc75-8100-4358-8c6c-a61eed5b4819","year":2020},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:6c4e58bacee3f5c40668bb68c1552de36b78b7632577ea00a6ef5e4568c28092","observation_id":"b76a3f3c-56d5-4544-a8e4-75ba963501c9","resolution":{"observed_at":"2026-07-09T22:26:37.356982Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.363103Z","title":"Shallow-deep networks: Understanding and mitigating network overthinking,","venue":null,"work_id":"9b98eedd-fb2d-4aac-bbc1-36cbc575a8ed","year":2019},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:3999285ec1a1f7e29abec5a280126998f1a62789e4fab43da1f78531ff897047","observation_id":"6f685cff-09e0-4739-9b04-fe14622ee67c","resolution":{"observed_at":"2026-07-09T22:26:37.364192Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-08-10T22:24:05.831832Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":"1409.1556","doi":"10.48550/arxiv.1409.1556","metadata_source":"pith","pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","venue":"cs.CV","work_id":"1c4b4409-c14b-488b-a086-c57a5aab8a29","year":2014},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:5b4401f37386d4e151ebbae771c038493cbe719b3af9a6885dfa1af7724f7be5","observation_id":"4db65c55-610a-4716-ad46-3e9ab0e6d179","resolution":{"observed_at":"2026-07-09T22:26:36.956582Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-07-12T23:51:07.915518+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-12T23:51:07.915518+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.382876Z","title":"Rethinking the inception architecture for computer vision,","venue":null,"work_id":"55102c05-8e36-4d66-82f0-cbf237f3ce0a","year":2016},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:620b203b985bd40d806dd8c0e5af9df8020bc8497c050224601628698410f173","observation_id":"325d1e26-664b-4eb9-a53c-53acc245c5ca","resolution":{"observed_at":"2026-07-09T22:26:37.384019Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.336672Z","title":"Wide residual networks,","venue":null,"work_id":"2f0811be-cb8f-4782-ad7d-ac2de3609879","year":2016},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:8c6cb02e4ba434c6a7fc77d8acabc48949f9fd84648ebafdaef4640e45a951d2","observation_id":"b2c225a4-6d46-477f-8111-c5bf6ca3fd35","resolution":{"observed_at":"2026-07-09T22:26:37.338715Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.409407Z","title":"Data-driven sparse structure selection for deep neural networks,","venue":null,"work_id":"f8506cf2-8f2a-404a-b39a-f05a623c1311","year":2018},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:9d0d5d7560ef676c8468a62dd4fb26bb2a956b9b9426d542f7ec560fab2b9443","observation_id":"1fb16f3a-3435-472b-bfc5-56c996fad770","resolution":{"observed_at":"2026-07-09T22:26:37.410563Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.402760Z","title":"Learning versatile filters for efficient convolutional neural networks,","venue":null,"work_id":"e5453be7-47a1-456e-a5fd-33d0bf0f9154","year":2018},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:1e345df808bc991d03e7c90b84bc6f3676f8f38b779e451c75f5ab626a0fd3bc","observation_id":"e5938fca-b86e-4f1a-9a1c-150671381171","resolution":{"observed_at":"2026-07-09T22:26:37.403937Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.414409Z","title":"Provable filter pruning for efficient neural networks,","venue":null,"work_id":"12126248-61a3-43e6-b2f2-57dc0a940169","year":2019},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:5d65f85b1e58f0194c1424247da4c4a611ed679f8ecaf0c605c818adf017f2cb","observation_id":"f319b51e-bdff-4081-9907-c11a41baeff7","resolution":{"observed_at":"2026-07-09T22:26:37.415720Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.339250Z","title":"Centripetal sgd for pruning very deep convolutional networks with complicated structure,","venue":null,"work_id":"0f4d816f-d920-4b9a-9504-1d8afcf51272","year":2019},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:aa72e45bc82a5556fe7fe633dbd972396a8dadcaaea89eea6dd458557b6e7e79","observation_id":"a6e6bdb7-f4dd-4f07-a819-d5d36223bddf","resolution":{"observed_at":"2026-07-09T22:26:37.340406Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.407703Z","title":"Towards optimal structured cnn pruning via generative adversarial learning,","venue":null,"work_id":"2c25c985-9ad9-4ef8-95de-b9c1eb5b0e8f","year":2019},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:81a93a7d7e06088f7ad80d785e949e5e71e37c9a8c72154d6fb8625a87f9e65d","observation_id":"a0ae7f46-2b48-4a42-a994-9bce28e9aaa9","resolution":{"observed_at":"2026-07-09T22:26:37.408883Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.333178Z","title":"Autopruner: An end-to-end trainable filter pruning method for efficient deep model inference,","venue":null,"work_id":"7263b803-20a2-4759-b997-42185a7255ba","year":2020},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:eef009263af2ff306adb5bd30fbb9e235b30b27c5e6b54e1ddf45bbc82ab1a38","observation_id":"f48327a2-9f46-4b07-badf-43983714f94c","resolution":{"observed_at":"2026-07-09T22:26:37.334362Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.359052Z","title":"Densely connected convolutional networks,","venue":null,"work_id":"7e05c3fa-3715-46b1-bb7d-ab1bf9009745","year":2017},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:ecc0267198bc3e674bdcef27410a7201751f7c58712240ae6aacff2ea2cceeaa","observation_id":"0ec14429-5fef-4c89-ac3e-5e75e5f5c3a7","resolution":{"observed_at":"2026-07-09T22:26:37.360855Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.369805Z","title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift,","venue":null,"work_id":"b88d1196-5c79-4b0b-9012-07f74a9fafc1","year":2015},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:6dc609ec3ffa0c1dabafc6d0684ebb26b4b49008763fe55ad79fd081e35dd840","observation_id":"bece9939-3897-4794-9b62-0ae34bfac5b7","resolution":{"observed_at":"2026-07-09T22:26:37.370960Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.417840Z","title":"Variational convolutional neural network pruning,","venue":null,"work_id":"797636e3-9164-40bb-8800-3a9b97703313","year":2019},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:2666a1bdaa254dde974be4deab267cfa8cffa9e2ace72ab17c7568485821206d","observation_id":"bae9f694-88d1-4512-861e-010fa9b61297","resolution":{"observed_at":"2026-07-09T22:26:37.419074Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T22:26:37.378031Z","title":"His current research interests include edge intelli- gence, hardware-aware neural architecture search, and model compression","venue":null,"work_id":"6afe74d5-5364-498a-97a8-854fe304e232","year":2007},"citing_paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-07-09T22:22:15.878399Z"},"links":{"citing_paper":"/paper/2607.06982"},"observation_digest":"sha256:7455213054c70e2c7902caeb8c444eef54d203ba6605fa2bc4912834596bd879","observation_id":"46bfbdbd-ba8c-400e-a76b-e884ea79264d","resolution":{"observed_at":"2026-07-09T22:26:37.379251Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2607.06982","last_updated":"2026-07-08T04:03:32Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T09:29:17.284522Z","submitted_at":"2026-07-08T04:03:32Z","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI"},"reference_resolution":{"displayed":59,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":4,"verified_fuzzy":55},"total_outbound_references":59},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 59 of 59 outbound references and 0 inbound Pith citation observations for arXiv:2607.06982."}