{"as_of":"2026-08-08T09:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f42400ff80c2116df059bc80c5fd29d324b16f1929f4528e0c55d5af5f37096a","coverage":[{"denominator":15,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":15,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T22:17:44.034506Z","state":"measured"},{"denominator":15,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":15,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2506.22015/citation-record","integrity":"/paper/2506.22015/integrity","json":"/paper/2506.22015/citation-record.json","paper":"/paper/2506.22015"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-07-06T04:11:24.157003Z","submitted_at":"2015-03-09T15:44:49Z","title":"Distilling the Knowledge in a Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.02531","snapshot_observed_at":"2026-08-06T22:17:43.137762Z","title":"Amc: Automl for model compression and acceleration on mobile devices","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.22015","last_updated":"2025-07-03T07:20:35Z","snapshot_observed_at":"2026-08-06T22:10:47.087808Z","submitted_at":"2025-06-27T08:28:21Z","title":"Towards Universal & Efficient Model Compression via Exponential Torque Pruning","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T22:17:43.137762Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2506.22015"},"observation_digest":"sha256:5699c3038eb64e60809bdfe6558f9daad800e7cd7110627350ff246cb24b9dde","observation_id":"36e2f12c-242c-4541-b801-1ff96174f6fb","resolution":{"observed_at":"2026-08-06T22:17:43.137762Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:17:44.647254Z","title":"Oscar: Object-semantics aligned pre-training for vision-language tasks","venue":null,"work_id":"7fa372c6-3723-4d54-9dd6-f90991b7993d","year":2020},"citing_paper":{"arxiv_id":"2506.22015","last_updated":"2025-07-03T07:20:35Z","snapshot_observed_at":"2026-08-06T22:10:47.087808Z","submitted_at":"2025-06-27T08:28:21Z","title":"Towards Universal & Efficient Model Compression via Exponential Torque Pruning","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T22:17:43.407388Z"},"links":{"citing_paper":"/paper/2506.22015"},"observation_digest":"sha256:101716addce2bdbafe2dce1a5288f6df54d25d194bfb857327fd0e4df8569e0f","observation_id":"f4826cb9-448e-47c4-afde-b52b91a1cdc2","resolution":{"observed_at":"2026-08-06T22:17:44.703237Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1907.11692","last_updated":"2019-07-26T17:48:29Z","snapshot_observed_at":"2026-07-31T22:31:37.910868Z","submitted_at":"2019-07-26T17:48:29Z","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.11692","snapshot_observed_at":"2026-08-06T22:17:43.478558Z","title":"Roberta: A robustly optimized bert pretraining approach","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2506.22015","last_updated":"2025-07-03T07:20:35Z","snapshot_observed_at":"2026-08-06T22:10:47.087808Z","submitted_at":"2025-06-27T08:28:21Z","title":"Towards Universal & Efficient Model Compression via Exponential Torque Pruning","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T22:17:43.478558Z"},"links":{"cited_paper":"/paper/1907.11692","citing_paper":"/paper/2506.22015"},"observation_digest":"sha256:499430a1ceadf4913fec27e5fba06f68a0a271a4d2d350bb49d33313e6a76402","observation_id":"b41e03eb-b961-4399-9ea8-aaf53bbbcf6f","resolution":{"observed_at":"2026-08-06T22:17:43.478558Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1906.06307","last_updated":"2020-02-16T18:23:41Z","snapshot_observed_at":"2026-07-06T08:00:25.359981Z","submitted_at":"2019-06-14T17:26:29Z","title":"A Signal Propagation Perspective for Pruning Neural Networks at Initialization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.06307","snapshot_observed_at":"2026-08-06T22:17:43.313565Z","title":"A signal propagation perspective for pruning neural networks at initialization","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2506.22015","last_updated":"2025-07-03T07:20:35Z","snapshot_observed_at":"2026-08-06T22:10:47.087808Z","submitted_at":"2025-06-27T08:28:21Z","title":"Towards Universal & Efficient Model Compression via Exponential Torque Pruning","version":3},"reference_index":1989,"source":"pdf_text","source_observed_at":"2026-08-06T22:17:43.313565Z"},"links":{"cited_paper":"/paper/1906.06307","citing_paper":"/paper/2506.22015"},"observation_digest":"sha256:bd127eabf23031f84366d3f3a63b4002553a4ca8c91c2e7a1ed143489fc0d292","observation_id":"59d43b14-6dba-4866-bc5a-48bc6318a5bb","resolution":{"observed_at":"2026-08-06T22:17:43.313565Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:17:44.318564Z","title":"Fine-tuning vision transformer using lora for image classification","venue":null,"work_id":"8ae81cf9-eae5-4367-8d8a-22ee7bd46788","year":2025},"citing_paper":{"arxiv_id":"2506.22015","last_updated":"2025-07-03T07:20:35Z","snapshot_observed_at":"2026-08-06T22:10:47.087808Z","submitted_at":"2025-06-27T08:28:21Z","title":"Towards Universal & Efficient Model Compression via Exponential Torque Pruning","version":3},"reference_index":1996,"source":"pdf_text","source_observed_at":"2026-08-06T22:17:43.771825Z"},"links":{"citing_paper":"/paper/2506.22015"},"observation_digest":"sha256:544118fd83f580099f44eaec99476535d25a7fab4ade88768f4898fbf5ef909e","observation_id":"18b1d31d-34f3-4d6a-95d7-64a362a98f2f","resolution":{"observed_at":"2026-08-06T22:17:44.388563Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T22:17:44.496896Z","title":"To compress, or not to compress: Characterizing deep learning model compression for embedded inference","venue":null,"work_id":"277c1918-4869-400e-9adf-12430ceef513","year":2018},"citing_paper":{"arxiv_id":"2506.22015","last_updated":"2025-07-03T07:20:35Z","snapshot_observed_at":"2026-08-06T22:10:47.087808Z","submitted_at":"2025-06-27T08:28:21Z","title":"Towards Universal & Efficient Model Compression via Exponential Torque Pruning","version":3},"reference_index":2002,"source":"pdf_text","source_observed_at":"2026-08-06T22:17:43.567822Z"},"links":{"citing_paper":"/paper/2506.22015"},"observation_digest":"sha256:bbeccc0d39ffeccfbc2154f27c566db866816eb1ad4c24fc4849181a35a4790a","observation_id":"695b8328-70d5-4e3d-b8a8-da09a4f98ac9","resolution":{"observed_at":"2026-08-06T22:17:44.573245Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:17:42.841733Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.22015","last_updated":"2025-07-03T07:20:35Z","snapshot_observed_at":"2026-08-06T22:10:47.087808Z","submitted_at":"2025-06-27T08:28:21Z","title":"Towards Universal & Efficient Model Compression via Exponential Torque Pruning","version":3},"reference_index":2009,"source":"pdf_text","source_observed_at":"2026-08-06T22:17:42.841733Z"},"links":{"citing_paper":"/paper/2506.22015"},"observation_digest":"sha256:15bd792cf0e67a61d0a88277488ee2a54e7bc8c43f928c81812cb2eb90823259","observation_id":"039d89c2-fbc9-4190-a271-90e129738e76","resolution":{"observed_at":"2026-08-06T22:17:42.841733Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1804.07461","last_updated":"2019-02-22T23:53:34Z","snapshot_observed_at":"2026-07-06T06:34:26.609892Z","submitted_at":"2018-04-20T06:35:04Z","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.07461","snapshot_observed_at":"2026-08-06T22:17:43.942787Z","title":"Glue: A multi-task benchmark and analysis platform for natural language understanding","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.22015","last_updated":"2025-07-03T07:20:35Z","snapshot_observed_at":"2026-08-06T22:10:47.087808Z","submitted_at":"2025-06-27T08:28:21Z","title":"Towards Universal & Efficient Model Compression via Exponential Torque Pruning","version":3},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-06T22:17:43.942787Z"},"links":{"cited_paper":"/paper/1804.07461","citing_paper":"/paper/2506.22015"},"observation_digest":"sha256:eb3d3b7df52e75a52f3e319607bf5ca9d7a3ff733ef9177155aca120519f9111","observation_id":"437dd516-34e5-40d3-bcbf-1ae41f47fd27","resolution":{"observed_at":"2026-08-06T22:17:43.942787Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1808.06866","last_updated":"2018-08-21T12:22:38Z","snapshot_observed_at":"2026-07-06T06:56:39.566826Z","submitted_at":"2018-08-21T12:22:38Z","title":"Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1808.06866","snapshot_observed_at":"2026-08-06T22:17:43.047924Z","title":"Structured pruning for deep convolutional neural networks: A survey","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.22015","last_updated":"2025-07-03T07:20:35Z","snapshot_observed_at":"2026-08-06T22:10:47.087808Z","submitted_at":"2025-06-27T08:28:21Z","title":"Towards Universal & Efficient Model Compression via Exponential Torque Pruning","version":3},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-06T22:17:43.047924Z"},"links":{"cited_paper":"/paper/1808.06866","citing_paper":"/paper/2506.22015"},"observation_digest":"sha256:111c90769e82c6fadb8af7fd04885299bc8900865cf90cb6f7e2a84dd8f56fc4","observation_id":"a66c0dd6-5109-40c1-aabc-e80d3bdc2481","resolution":{"observed_at":"2026-08-06T22:17:43.047924Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1510.00149","last_updated":"2016-02-15T06:25:40Z","snapshot_observed_at":"2026-08-04T16:59:47.843960Z","submitted_at":"2015-10-01T09:03:44Z","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1510.00149","snapshot_observed_at":"2026-08-06T22:17:42.965857Z","title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.22015","last_updated":"2025-07-03T07:20:35Z","snapshot_observed_at":"2026-08-06T22:10:47.087808Z","submitted_at":"2025-06-27T08:28:21Z","title":"Towards Universal & Efficient Model Compression via Exponential Torque Pruning","version":3},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-06T22:17:42.965857Z"},"links":{"cited_paper":"/paper/1510.00149","citing_paper":"/paper/2506.22015"},"observation_digest":"sha256:5edf6cd1cadc24e9ab9deb33f08b764d9dbe6e2e5088233002c475fa2f911044","observation_id":"c7f84e93-1045-4cb8-82f4-a20294aca475","resolution":{"observed_at":"2026-08-06T22:17:42.965857Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-07-06T03:53:32.549552Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-06T22:17:43.679822Z","title":"Very deep convolutional networks for large-scale image recognition","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.22015","last_updated":"2025-07-03T07:20:35Z","snapshot_observed_at":"2026-08-06T22:10:47.087808Z","submitted_at":"2025-06-27T08:28:21Z","title":"Towards Universal & Efficient Model Compression via Exponential Torque Pruning","version":3},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-06T22:17:43.679822Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2506.22015"},"observation_digest":"sha256:8e6efd645ef8cbc73bbf3d38068ad262a24f974f0cc525987cdcc378a0ac817e","observation_id":"1128dd22-35eb-492a-8431-72a5bdb54d22","resolution":{"observed_at":"2026-08-06T22:17:43.679822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.09243","last_updated":"2021-04-05T19:37:45Z","snapshot_observed_at":"2026-07-06T10:25:14.308394Z","submitted_at":"2020-12-16T20:16:28Z","title":"Neural Pruning via Growing Regularization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.09243","snapshot_observed_at":"2026-08-06T22:17:44.034506Z","title":"Picking winning tickets before training by preserving gradient flow","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2506.22015","last_updated":"2025-07-03T07:20:35Z","snapshot_observed_at":"2026-08-06T22:10:47.087808Z","submitted_at":"2025-06-27T08:28:21Z","title":"Towards Universal & Efficient Model Compression via Exponential Torque Pruning","version":3},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-06T22:17:44.034506Z"},"links":{"cited_paper":"/paper/2012.09243","citing_paper":"/paper/2506.22015"},"observation_digest":"sha256:601306b8a64d070c341525a6e420caf52073bb73a44fec30ab5dcb06261d5c25","observation_id":"18d7b047-7c38-4d8a-99c3-22bb2b1b94de","resolution":{"observed_at":"2026-08-06T22:17:44.034506Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.11556","last_updated":"2019-09-25T15:35:03Z","snapshot_observed_at":"2026-07-06T08:24:32.545342Z","submitted_at":"2019-09-25T15:35:03Z","title":"Reducing Transformer Depth on Demand with Structured Dropout","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.11556","snapshot_observed_at":"2026-08-06T22:17:42.899383Z","title":"Reducing transformer depth on demand with structured dropout","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2506.22015","last_updated":"2025-07-03T07:20:35Z","snapshot_observed_at":"2026-08-06T22:10:47.087808Z","submitted_at":"2025-06-27T08:28:21Z","title":"Towards Universal & Efficient Model Compression via Exponential Torque Pruning","version":3},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-06T22:17:42.899383Z"},"links":{"cited_paper":"/paper/1909.11556","citing_paper":"/paper/2506.22015"},"observation_digest":"sha256:cee9983ee069b82585b64056b7b6f22e1db6b7942d9ee0750bc04576512d498c","observation_id":"282d4541-9bd4-46a8-b938-768d71b1ce3b","resolution":{"observed_at":"2026-08-06T22:17:42.899383Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:17:44.773148Z","title":"Learning multiple layers of features from tiny images.(2009),","venue":null,"work_id":"31cf5909-9c31-4aa4-b792-2e13b66be3f4","year":2009},"citing_paper":{"arxiv_id":"2506.22015","last_updated":"2025-07-03T07:20:35Z","snapshot_observed_at":"2026-08-06T22:10:47.087808Z","submitted_at":"2025-06-27T08:28:21Z","title":"Towards Universal & Efficient Model Compression via Exponential Torque Pruning","version":3},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-06T22:17:43.227341Z"},"links":{"citing_paper":"/paper/2506.22015"},"observation_digest":"sha256:dd8f9264da4294a61b295a118cc99f6631bc1cc9817767efc12fd6bf7a90190a","observation_id":"6334bce2-6313-428b-8b4d-b80175c84310","resolution":{"observed_at":"2026-08-06T22:17:44.836457Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.10903","last_updated":"2018-02-04T19:13:29Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-10-30T12:41:12Z","title":"Graph Attention Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.10903","snapshot_observed_at":"2026-08-06T22:17:43.861596Z","title":"Graph attention networks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.22015","last_updated":"2025-07-03T07:20:35Z","snapshot_observed_at":"2026-08-06T22:10:47.087808Z","submitted_at":"2025-06-27T08:28:21Z","title":"Towards Universal & Efficient Model Compression via Exponential Torque Pruning","version":3},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-06T22:17:43.861596Z"},"links":{"cited_paper":"/paper/1710.10903","citing_paper":"/paper/2506.22015"},"observation_digest":"sha256:7e926a917998159b3d498e4c56d90037fc0c8c9e7b55b881d67d394427d9bc59","observation_id":"6c5e1f7b-e094-4397-b37e-0de846005040","resolution":{"observed_at":"2026-08-06T22:17:43.861596Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.22015","last_updated":"2025-07-03T07:20:35Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T22:10:47.087808Z","submitted_at":"2025-06-27T08:28:21Z","title":"Towards Universal & Efficient Model Compression via Exponential Torque Pruning"},"reference_resolution":{"displayed":15,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":11,"verified_exact":0,"verified_fuzzy":4},"total_outbound_references":15},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 0 inbound Pith citation observations for arXiv:2506.22015."}