{"as_of":"2026-08-16T15:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:afa2a3a82cfe8fe0193cbdb5fc597f09e4df24d67c0835b38cbff91d3e80296e","coverage":[{"denominator":60,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":60,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T17:59:51.078801Z","state":"measured"},{"denominator":60,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":60,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+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/2502.00744/citation-record","integrity":"/paper/2502.00744/integrity","json":"/paper/2502.00744/citation-record.json","paper":"/paper/2502.00744"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:59:51.502962Z","title":"Structured pruning of deep convolutional neural networks","venue":null,"work_id":"9156b1c1-e216-41ac-9b89-dc18923de7d1","year":2017},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.901774Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:45ca44bed2dff767ffe254b403218c137e37860f78b0215e13e5de6bd5abcd4a","observation_id":"525a71d2-1adb-44a4-bff2-a7522d347c35","resolution":{"observed_at":"2026-08-09T17:59:51.506130Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-09T17:59:50.905577Z","title":"Piqa: Reasoning about physical commonsense in natural language","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.905577Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:5965e9731e2fa78b0b44a112431e5073df8ce6359856a27bd60a8ba750828764","observation_id":"d80d3733-052f-43d8-8a32-c296a64e498b","resolution":{"observed_at":"2026-08-09T17:59:50.905577Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:59:50.908847Z","title":"A survey on deep neural network pruning: Taxonomy, comparison, analysis, and recommendations","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.908847Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:df6ea7029691007c5e8c16ddbd3dd6146534252d515415fd3a9eea7c9ab4fd8f","observation_id":"d6042425-21f7-4dcc-bdb9-6fb2cbba50ce","resolution":{"observed_at":"2026-08-09T17:59:50.908847Z","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":"2026-08-09T17:59:51.484467Z","title":"Boolq: Exploring the surprising difficulty of natural yes/no questions","venue":null,"work_id":"a584084c-b9ec-4bcb-8266-e28a8fc40f26","year":2019},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.911927Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:9930878b2e04eadad6080933caf808e1344cbb97cc35b4f9b420099367306567","observation_id":"5fcd4aa9-c5ae-4354-b468-7d0cff031eea","resolution":{"observed_at":"2026-08-09T17:59:51.487636Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.05457","last_updated":"2018-03-14T18:04:21Z","snapshot_observed_at":"2026-08-14T19:36:07.505691Z","submitted_at":"2018-03-14T18:04:21Z","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.05457","snapshot_observed_at":"2026-08-09T17:59:50.914933Z","title":"Think you have solved question answering? try arc, the ai2 reasoning challenge","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.914933Z"},"links":{"cited_paper":"/paper/1803.05457","citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:da8beb28f19a7deffe5f42ef29c1197bcac21c7b4f63c212178592bc0fa30172","observation_id":"1f62f31a-d3f8-4fec-8a4a-ff69a11d1e14","resolution":{"observed_at":"2026-08-09T17:59:50.914933Z","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":"2026-08-09T17:59:51.475926Z","title":"Neural network training using l_1 -regularization and bi-fidelity data","venue":null,"work_id":"865f830d-2e48-4897-9aa1-6da01d575850","year":2022},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.918442Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:35cdfd8387027de0bfe837020fe0e6a1ade3ea66fa9a0abe3fa6b27246c01baf","observation_id":"c569e02f-007c-4d1e-ab04-0691c8e1b31d","resolution":{"observed_at":"2026-08-09T17:59:51.479029Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-09T17:59:51.467216Z","title":"Depgraph: Towards any structural pruning","venue":null,"work_id":"87c7c68b-c0b9-4d10-9b81-aaa6e8344200","year":2023},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.921513Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:f4afec9db79995d3721dd98f400d2c700971dd0ef09bc664258ad5b7d29cb706","observation_id":"d854e21f-b394-4200-ba01-7af7f5f42083","resolution":{"observed_at":"2026-08-09T17:59:51.470497Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.17481","last_updated":"2024-12-07T12:01:28Z","snapshot_observed_at":"2026-08-16T13:15:17.778720Z","submitted_at":"2024-09-26T02:37:41Z","title":"MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.17481","snapshot_observed_at":"2026-08-09T17:59:50.924389Z","title":"Maskllm: Learnable semi-structured sparsity for large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.924389Z"},"links":{"cited_paper":"/paper/2409.17481","citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:cfc9a3acf073813a60a4fd60eda080ecb86889441bad27faffbae11d905c1292","observation_id":"b90bc57e-7ccc-4736-ad95-6fbbff086c03","resolution":{"observed_at":"2026-08-09T17:59:50.924389Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.03635","last_updated":"2019-03-04T15:51:11Z","snapshot_observed_at":"2026-08-14T19:37:43.556604Z","submitted_at":"2018-03-09T18:51:28Z","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.03635","snapshot_observed_at":"2026-08-09T17:59:50.927604Z","title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.927604Z"},"links":{"cited_paper":"/paper/1803.03635","citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:8e711f90a4cc87d862e05953d28dacf27c089b5b388f4475f3483abadaac7c9c","observation_id":"275145ca-c285-439b-9618-fee1b87008ba","resolution":{"observed_at":"2026-08-09T17:59:50.927604Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.00774","last_updated":"2023-03-22T12:33:46Z","snapshot_observed_at":"2026-08-13T13:10:46.067160Z","submitted_at":"2023-01-02T17:48:56Z","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.00774","snapshot_observed_at":"2026-08-09T17:59:50.930840Z","title":"Sparsegpt: Massive language models can be accurately pruned in one-shot, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.930840Z"},"links":{"cited_paper":"/paper/2301.00774","citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:ae966c269ed221c888774964036833e9d9161238c2a8170c706f50e8a76a3769","observation_id":"78b96fcc-7a38-486a-9218-91a2f84511d2","resolution":{"observed_at":"2026-08-09T17:59:50.930840Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.09574","last_updated":"2019-02-25T19:18:40Z","snapshot_observed_at":"2026-08-15T00:50:07.769538Z","submitted_at":"2019-02-25T19:18:40Z","title":"The State of Sparsity in Deep Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.09574","snapshot_observed_at":"2026-08-09T17:59:50.934363Z","title":"The state of sparsity in deep neural networks","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.934363Z"},"links":{"cited_paper":"/paper/1902.09574","citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:b86e257a8116e97b760526592e684a0c0d683cdb38045d2be1feeaf81f309c53","observation_id":"e37a2963-511b-4c3a-aa57-4ebeeeac58fb","resolution":{"observed_at":"2026-08-09T17:59:50.934363Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:59:50.937552Z","title":"A framework for few-shot language model evaluation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.937552Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:0adf40717b874b5c444eb6ac21fdca1ccf8dcfc7ed052ab32cb8aff786a58daa","observation_id":"1dcf1583-fe14-47ed-a162-54a954281374","resolution":{"observed_at":"2026-08-09T17:59:50.937552Z","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":"2026-08-09T17:59:51.453515Z","title":"Removal of hidden units and weights for back propagation networks","venue":null,"work_id":"588243f9-a05c-4257-9f29-bd36e4f2f601","year":1993},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.940586Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:44a33e2622a39c12da763e2f54fc02729573d365c5615e1711f8b9f81da9a779","observation_id":"ec2b9326-a4c2-4467-a1f2-c8b6cfcd08f6","resolution":{"observed_at":"2026-08-09T17:59:51.456661Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-09T17:59:50.943379Z","title":"Learning both weights and connections for efficient neural network","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.943379Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:7f94cd9b04d989380846f872cca1a897022118bf7579cb5263de388de8901689","observation_id":"e219da10-5308-41a8-9c99-5e24ccf29bb5","resolution":{"observed_at":"2026-08-09T17:59:50.943379Z","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":"2026-08-09T17:59:51.440129Z","title":"Optimal brain surgeon and general network pruning","venue":null,"work_id":"48c04480-f114-49df-a19c-ee92178f3499","year":1993},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.946184Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:b4c6ced4d5b461c2925c676bf389560bc428d742dc4ed18381382202886c712b","observation_id":"421715d6-5ff1-42a5-82cb-ecb66e3ff727","resolution":{"observed_at":"2026-08-09T17:59:51.443120Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-09T17:59:50.948861Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.948861Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:58b25f32f41620e918b6cbb5ac0743183d15a236ca772c0524fc08b8c43b0625","observation_id":"ddee5664-1e5e-4cbd-a635-057526f7e64d","resolution":{"observed_at":"2026-08-09T17:59:50.948861Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:59:50.951445Z","title":"Structured pruning for deep convolutional neural networks: A survey","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.951445Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:cebb211068378309a3b86d4666db226a494e4994137da9f980cf8d4197770c05","observation_id":"e91cc51a-a684-4515-a64f-970390e48275","resolution":{"observed_at":"2026-08-09T17:59:50.951445Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:59:50.954752Z","title":"Channel pruning for accelerating very deep neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.954752Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:0d99c4a7a9cffe963ccfdd4d8bee21261cd24960b7ccc97feb7aaef4265d1f04","observation_id":"a1884608-ff05-472a-9e32-06b2488d0d2b","resolution":{"observed_at":"2026-08-09T17:59:50.954752Z","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":"2026-08-09T17:59:51.417210Z","title":"A practical guide to training restricted boltzmann machines","venue":null,"work_id":"675172f6-f58a-40c3-bd15-670e8f9e41e6","year":2012},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.958720Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:98218c1d9e28afa4177a74e99ba6850ad57589c5480f45bcbb929f5c1eb7299c","observation_id":"cf23aed0-750a-49ce-adba-0c5d4b22b258","resolution":{"observed_at":"2026-08-09T17:59:51.420828Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-09T17:59:50.961637Z","title":"Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.961637Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:7b905b3690f369fe27451858a8fd2dacc7c16fa1e2298b4573ac04e056a02b15","observation_id":"88a33e83-09d7-4bb7-8beb-2168f49fb8e8","resolution":{"observed_at":"2026-08-09T17:59:50.961637Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-11T08:20:29.798517Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-09T17:59:50.964597Z","title":"Lora: Low-rank adaptation of large language models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.964597Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:7e5a15c315636c59510c209e36480e6af8604bcf4a894ce934084c0d89b15e61","observation_id":"6479f307-1466-4b91-a845-cd889229da97","resolution":{"observed_at":"2026-08-09T17:59:50.964597Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1707.01213","last_updated":"2018-09-05T05:14:37Z","snapshot_observed_at":"2026-08-14T20:49:40.440011Z","submitted_at":"2017-07-05T05:21:50Z","title":"Data-Driven Sparse Structure Selection for Deep Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.01213","snapshot_observed_at":"2026-08-09T17:59:50.967822Z","title":"Data-driven sparse structure selection for deep neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.967822Z"},"links":{"cited_paper":"/paper/1707.01213","citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:4d8d5a4bf6ec9da13778c4d3a812238b3b39c1289daa3cd7dedfb978fea93793","observation_id":"453ff38c-23a5-4e29-9d6b-ff87781a2161","resolution":{"observed_at":"2026-08-09T17:59:50.967822Z","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":"2026-08-09T17:59:51.403956Z","title":"Top-kast: Top-k always sparse training","venue":null,"work_id":"980b8d1c-b6f8-4e7f-8ce6-7fca2dd3f280","year":2020},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.971034Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:7640246170c1bffa6c8daa32d7e8061a5c7acd0b094c6e2adea56efc5b110781","observation_id":"5d781808-f108-4ead-8902-e242d5ac4525","resolution":{"observed_at":"2026-08-09T17:59:51.407002Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-09T17:59:50.973664Z","title":"A new status index derived from sociometric analysis","venue":null,"work_id":null,"year":1953},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.973664Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:26cc77e4e100c9704699195f41f23dcfe738c0876d081ffb634465b7b5991713","observation_id":"a24d116a-a141-477b-8800-2283a11ea700","resolution":{"observed_at":"2026-08-09T17:59:50.973664Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1609.02907","last_updated":"2017-02-22T09:55:36Z","snapshot_observed_at":"2026-08-13T11:38:10.906031Z","submitted_at":"2016-09-09T19:48:41Z","title":"Semi-Supervised Classification with Graph Convolutional Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.02907","snapshot_observed_at":"2026-08-09T17:59:50.976655Z","title":"Semi-supervised classification with graph convolutional networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.976655Z"},"links":{"cited_paper":"/paper/1609.02907","citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:4be377b367c52523e5c1f81d27e90e270ea4e520ee04aedbdc29ffa02113abfe","observation_id":"c8b30c3f-d476-4f21-8a15-f8fda48eb7e9","resolution":{"observed_at":"2026-08-09T17:59:50.976655Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:59:50.979563Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.979563Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:da99d6e75cebd409c01b0928556951912a7c34851140aea8734b9aa62c8ff03b","observation_id":"a49f6c0f-cdcf-4a38-9fa0-0f66aeac9683","resolution":{"observed_at":"2026-08-09T17:59:50.979563Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:59:50.982549Z","title":"Optimal brain damage","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.982549Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:5899aecad1bd36c11eacc8f211361856897fc3eca64e23c4345fac6ff95a0444","observation_id":"e213398d-e537-49c1-96a0-774f15c3bdf9","resolution":{"observed_at":"2026-08-09T17:59:50.982549Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.02340","last_updated":"2019-02-23T07:45:29Z","snapshot_observed_at":"2026-08-16T06:51:50.505762Z","submitted_at":"2018-10-04T17:39:58Z","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.02340","snapshot_observed_at":"2026-08-09T17:59:50.985297Z","title":"Snip: Single-shot network pruning based on connection sensitivity","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.985297Z"},"links":{"cited_paper":"/paper/1810.02340","citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:759f305ae2d3406592bdc949536813ebe8b3316c44836cb1091565bf339a584f","observation_id":"082d47e6-328d-4f60-a1fa-fe839cfcdd9e","resolution":{"observed_at":"2026-08-09T17:59:50.985297Z","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":"2026-08-09T17:59:51.380920Z","title":"A pruning feedforward small-world neural network based on katz centrality for nonlinear system modeling","venue":null,"work_id":"3e7f45b0-1d8a-486d-a895-31a57bc04cc0","year":2020},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.988259Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:15bd56ff91b1b3955121b995452bb13af3f0a61fbe3dd157c170438854346333","observation_id":"573a1870-82e8-43ac-a568-d2177a264690","resolution":{"observed_at":"2026-08-09T17:59:51.384051Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-14T20:13:52.872565Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-09T17:59:50.990986Z","title":"Fixing weight decay regularization in adam","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.990986Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:8a33fa8c96db396091c6c3881c9c56a85bc0ecfc348a3e79a0bac2aaf3d17a34","observation_id":"16323de5-d540-467b-857a-1e0b313e463d","resolution":{"observed_at":"2026-08-09T17:59:50.990986Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:59:50.994450Z","title":"Llm-pruner: On the structural pruning of large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.994450Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:c1f3e5cfd6ec49bc7ec153a4dabbd8d8a24b56ba25bfe8d26b6fbc3db39176f4","observation_id":"321587fb-0a4c-4b36-a574-aba11866d014","resolution":{"observed_at":"2026-08-09T17:59:50.994450Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:59:50.997182Z","title":"Building a large annotated corpus of english: The penn treebank","venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:50.997182Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:4e96462def66b2c620278312267eac952b4b30cd1df588c4452965562a60f932","observation_id":"07bca295-b0f8-4522-bf03-ada4635814c1","resolution":{"observed_at":"2026-08-09T17:59:50.997182Z","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":"2026-08-09T17:59:51.362655Z","title":"Pointer sentinel mixture models","venue":null,"work_id":"0034ddf8-0657-4377-b1ad-2c55ec6f54a9","year":2022},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:51.000063Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:14b668b8f0c7809b75d2199147b03590912e3f4d570b6c1b7a4f710f033f4847","observation_id":"17d2b65b-6a44-4cd3-afea-083853eaf8e6","resolution":{"observed_at":"2026-08-09T17:59:51.365841Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-09T17:59:51.003057Z","title":"Can a suit of armor conduct electricity? a new dataset for open book question answering","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:51.003057Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:7f3d12449ea3d7d4b374039ce55aff61292c0921fbbe5a4ac5d968c9b4d3e9d3","observation_id":"acd9e43a-a70f-4982-a6fa-5b7c47721329","resolution":{"observed_at":"2026-08-09T17:59:51.003057Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:59:51.006128Z","title":"Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:51.006128Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:ded225b5b154f2fbd0e508fcf8205a3666ebe671d255749752b68d7aac984d5d","observation_id":"109022dc-08d8-44a0-a77a-4c989d3591fa","resolution":{"observed_at":"2026-08-09T17:59:51.006128Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1611.06440","last_updated":"2017-06-08T19:53:26Z","snapshot_observed_at":"2026-08-14T21:29:36.502364Z","submitted_at":"2016-11-19T22:48:30Z","title":"Pruning Convolutional Neural Networks for Resource Efficient Inference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.06440","snapshot_observed_at":"2026-08-09T17:59:51.008870Z","title":"Pruning convolutional neural networks for resource efficient inference","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:51.008870Z"},"links":{"cited_paper":"/paper/1611.06440","citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:f190bdaa3a3b81752e2ee469c706f1c3b31cb319d9b036344614bd652478439a","observation_id":"adbe609b-e1ce-4375-939f-86cc1677e9c6","resolution":{"observed_at":"2026-08-09T17:59:51.008870Z","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":"2026-08-09T17:59:51.344775Z","title":"Path-sgd: Path-normalized optimization in deep neural networks","venue":null,"work_id":"bcbc5a06-9aaa-4c17-8e02-11f44b0ded45","year":2015},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:51.011959Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:208a7f5245ac93bf9e5971f990c86fa3d41094fed77876860793b1cd8ef28c86","observation_id":"c7b11345-09e7-4c9a-96d8-17c4affc0d46","resolution":{"observed_at":"2026-08-09T17:59:51.347839Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.10350","last_updated":"2021-04-23T14:26:29Z","snapshot_observed_at":"2026-08-16T05:11:57.545339Z","submitted_at":"2021-04-21T04:44:25Z","title":"Carbon Emissions and Large Neural Network Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.10350","snapshot_observed_at":"2026-08-09T17:59:51.014823Z","title":"Carbon emissions and large neural network training","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:51.014823Z"},"links":{"cited_paper":"/paper/2104.10350","citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:88d0ee26449c7cb8f736bd9285900fb1d930113fa70587d558c533bb9488ea50","observation_id":"c13cfe52-588d-45b7-94e0-3f354dc771af","resolution":{"observed_at":"2026-08-09T17:59:51.014823Z","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":"2026-08-09T17:59:51.336441Z","title":"An analysis of the regularization between l2 and dropout in single hidden layer neural network","venue":null,"work_id":"645775e6-4ea3-4325-98d0-1104ed5106af","year":2016},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:51.017825Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:096d9c4bfd5be47ad67dae96b9b42a3dca5968a807e61cf29a59531fcec1ab8e","observation_id":"9e7ddc15-bd05-4141-bc5e-ca6eba167740","resolution":{"observed_at":"2026-08-09T17:59:51.339507Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-09T17:59:51.020557Z","title":"Winogrande: An adversarial winograd schema challenge at scale","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:51.020557Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:e6956bdf2ba994f94993f9f09a302782785c0d9033da58b90fa2ad92be092bcd","observation_id":"5d3dc79e-d0db-4b8c-bb51-5f57b85e6186","resolution":{"observed_at":"2026-08-09T17:59:51.020557Z","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":"2026-08-09T17:59:51.322928Z","title":"Movement pruning: Adaptive sparsity by fine-tuning","venue":null,"work_id":"5fe7e326-f708-40c7-8afd-63c7b3f3d1e6","year":2020},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:51.023277Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:555fe294d50713b13055e94ca309d1b175b0436397f50f42b67646d2f3ea2632","observation_id":"02d595f0-310e-4d1f-99ec-be075abcdf56","resolution":{"observed_at":"2026-08-09T17:59:51.325974Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-09T17:59:51.314277Z","title":"Collective classification in network data","venue":null,"work_id":"7ba22024-d2d4-49a3-b1b2-c6978c58a5f7","year":2008},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:51.025891Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:c703a5ad0c2e53d211d62780bd9293eec8524c805a9b082c3c4373a9b41f84b8","observation_id":"1f1cbb79-f400-4c0e-88b7-ee98b7866ae7","resolution":{"observed_at":"2026-08-09T17:59:51.317397Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-09T17:59:51.028950Z","title":"Very deep convolutional networks for large-scale image recognition","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:51.028950Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:f296d9850bfecb24b2d2e2ce780c7a69e91380e3075c8fe72daeaeccde3dad5f","observation_id":"17d8ce42-1a47-4fcc-b973-c348c997b5e5","resolution":{"observed_at":"2026-08-09T17:59:51.028950Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.11695","last_updated":"2024-05-06T17:47:01Z","snapshot_observed_at":"2026-08-13T04:32:33.562415Z","submitted_at":"2023-06-20T17:18:20Z","title":"A Simple and Effective Pruning Approach for Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.11695","snapshot_observed_at":"2026-08-09T17:59:51.031626Z","title":"A simple and effective pruning approach for large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:51.031626Z"},"links":{"cited_paper":"/paper/2306.11695","citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:521550f49af82ae4e2556291b25f016af5126111d1d08899190ad4df59336a61","observation_id":"93603ba8-8162-4aa9-a396-0068477bd65e","resolution":{"observed_at":"2026-08-09T17:59:51.031626Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:59:51.034855Z","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:51.034855Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:5043298913e4f716752d1b33b338671a9b289578fa5342769e13703490c36584","observation_id":"f103b96f-4997-4350-a4ef-c4ef86eecb36","resolution":{"observed_at":"2026-08-09T17:59:51.034855Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:59:51.037638Z","title":"Stanford alpaca: An instruction-following llama model, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:51.037638Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:8845fbdff76ce7430ea6f562004fcfce2472459395c7aa6da01b8ae570ecc706","observation_id":"1eb1e820-db2a-418c-ab57-e061d748ef56","resolution":{"observed_at":"2026-08-09T17:59:51.037638Z","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":"2026-08-09T17:59:51.291852Z","title":"Evaluating pruning methods","venue":null,"work_id":"29fa8da0-7c07-4f56-b851-4aeb7e8bbd02","year":1995},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:51.040285Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:0047e472603d426ebfe82a0c90c7a8289f47e93ee03f35a73220e8d593b6ddbc","observation_id":"7f13525d-1d72-4f3d-80e1-a48f810f31d7","resolution":{"observed_at":"2026-08-09T17:59:51.294819Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-09T17:59:51.043179Z","title":"Regression shrinkage and selection via the lasso","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:51.043179Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:a2c38af0f536e38d3353b92b805430563171064737a1526bd2b14a9ab5d005d6","observation_id":"8f011e72-6a0d-494d-a84f-da5b2b1be74c","resolution":{"observed_at":"2026-08-09T17:59:51.043179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:59:51.045967Z","title":"Open and efficient foundation language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:51.045967Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:a0bcdf5abe3877859ce8568f71ce306065ec4fed5f288041117d57798c3dff33","observation_id":"326e54fc-7bc4-4816-84dc-d00d1fc0987d","resolution":{"observed_at":"2026-08-09T17:59:51.045967Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-08-09T17:59:51.278005Z","title":"Connectivity matters: Neural network pruning through the lens of effective sparsity","venue":null,"work_id":"b4b5a132-4e86-4503-9277-560ea3479f57","year":2023},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:51.048920Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:120c8868c89fa29661c394a95ffd3f9d6c48ab0b8392c912722800453027eded","observation_id":"2183da18-2040-4e6d-9c86-0a1ac541f8ac","resolution":{"observed_at":"2026-08-09T17:59:51.281117Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.07376","last_updated":"2020-08-07T00:02:33Z","snapshot_observed_at":"2026-08-10T04:53:00.900945Z","submitted_at":"2020-02-18T05:14:47Z","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.07376","snapshot_observed_at":"2026-08-09T17:59:51.051949Z","title":"Picking winning tickets before training by preserving gradient flow","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:51.051949Z"},"links":{"cited_paper":"/paper/2002.07376","citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:e5e69953780172065689ffb8bbb2c97e8b28a58950200208c5ebdda750f9a48f","observation_id":"74a5339b-c161-439e-a0d8-dcf8c6f9f0c9","resolution":{"observed_at":"2026-08-09T17:59:51.051949Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:59:51.055078Z","title":"Learning structured sparsity in deep neural networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:51.055078Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:4e4adf47e13813ea175e260b8a338928203682454dab146d0e1ff515bff69202","observation_id":"99cd3515-f3b2-428d-b08c-8f82b2904ef9","resolution":{"observed_at":"2026-08-09T17:59:51.055078Z","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":"2026-08-09T17:59:51.264574Z","title":"Structured pruning of convolutional neural networks via l1 regularization","venue":null,"work_id":"215ac89d-8597-4414-8df0-f65a135ad6f3","year":2019},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:51.058003Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:647652185f260e07e2dc36e5c96d6d61fb60feef1b72569a700894ba81929b31","observation_id":"ff253a82-da84-44e6-8791-353355cb7227","resolution":{"observed_at":"2026-08-09T17:59:51.267978Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-09T17:59:51.060929Z","title":"Model selection and estimation in regression with grouped variables","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:51.060929Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:a4821817b9fd62aff67981f60b4c62b5e97c477094f97869451bddfc1c89d0af","observation_id":"79d1fd33-44f1-4093-bb04-e8995f5c0053","resolution":{"observed_at":"2026-08-09T17:59:51.060929Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1905.07830","last_updated":"2019-05-19T23:57:23Z","snapshot_observed_at":"2026-08-15T09:37:44.321271Z","submitted_at":"2019-05-19T23:57:23Z","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.07830","snapshot_observed_at":"2026-08-09T17:59:51.063762Z","title":"Hellaswag: Can a machine really finish your sentence? arXiv preprint arXiv:1905.07830, 2019","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:51.063762Z"},"links":{"cited_paper":"/paper/1905.07830","citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:afc9a87e2aa9deaafbad93d14c9f0c4bb37e2c5dffa03e351a5f372e8b1dc544","observation_id":"40e822cf-91b3-484c-89c8-2d6e981ccd13","resolution":{"observed_at":"2026-08-09T17:59:51.063762Z","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":"2026-08-09T17:59:51.251548Z","title":"Subset-based training and pruning of sigmoid neural networks","venue":null,"work_id":"2b42db72-4a77-4371-ba19-2f04668206ee","year":1999},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:51.067150Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:6cbf60c1227f2874bcade07801684469f1d12fb3315b62d10f3416a87991fec0","observation_id":"86b22bda-1119-4b4e-a267-86861774fea6","resolution":{"observed_at":"2026-08-09T17:59:51.254601Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1506.06724","last_updated":"2015-06-22T19:26:56Z","snapshot_observed_at":"2026-08-14T22:43:25.435405Z","submitted_at":"2015-06-22T19:26:56Z","title":"Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1506.06724","snapshot_observed_at":"2026-08-09T17:59:51.070100Z","title":"Aligning books and movies: Towards story-like visual explanations by watching movies and reading books","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:51.070100Z"},"links":{"cited_paper":"/paper/1506.06724","citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:b839cd04de03c7b556f9e6687a7d4f922293864eb4ed427d3e3a6e1dda95bd35","observation_id":"751cb591-045b-4798-b43a-b37fe08a712c","resolution":{"observed_at":"2026-08-09T17:59:51.070100Z","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":"2026-08-09T17:59:51.240574Z","title":"Neuron-level structured pruning using polarization regularizer","venue":null,"work_id":"3263d0db-5d95-4764-b330-81a2069398d3","year":2020},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:51.073063Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:d510d6afbd349d18b605499eaab32e2cd6159514892e802aa339d978d7b57a28","observation_id":"519eccc0-1a55-4eca-89d4-8304d7cccdb5","resolution":{"observed_at":"2026-08-09T17:59:51.245351Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-09T17:59:51.076018Z","title":"spred: Solving l1 penalty with sgd","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:51.076018Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:4b3399500383b70e58859bbdc982f2ed93717f33d0b567fb916b67410ee513f7","observation_id":"74e7369d-ed90-47ed-b99d-21e88bcadc40","resolution":{"observed_at":"2026-08-09T17:59:51.076018Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:59:51.078801Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","version":2},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-09T17:59:51.078801Z"},"links":{"citing_paper":"/paper/2502.00744"},"observation_digest":"sha256:1d9d2a49f218861a0fdd9cf5c400b744feab5abb8179f35e7446d430ada59800","observation_id":"15cf3c9f-c862-4e4e-8f5c-b1901c87fba2","resolution":{"observed_at":"2026-08-09T17:59:51.078801Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2502.00744","last_updated":"2025-06-13T08:18:12Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T04:13:24.329599Z","submitted_at":"2025-02-02T10:32:55Z","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning"},"reference_resolution":{"displayed":60,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":40,"verified_exact":0,"verified_fuzzy":19},"total_outbound_references":60},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 60 of 60 outbound references and 0 inbound Pith citation observations for arXiv:2502.00744."}