{"as_of":"2026-08-13T11:21:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c24a7c21d287ff637f1afab61e357a7c766463c962dda70fbc2ab1f6eb69e2de","coverage":[{"denominator":25,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":25,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T16:22:47.921929Z","state":"measured"},{"denominator":25,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":25,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+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/2411.15217/citation-record","integrity":"/paper/2411.15217/integrity","json":"/paper/2411.15217/citation-record.json","paper":"/paper/2411.15217"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2203.13450","last_updated":"2022-07-19T15:31:09Z","snapshot_observed_at":"2026-07-06T12:52:16.992962Z","submitted_at":"2022-03-25T05:17:24Z","title":"A Comparative Survey of Deep Active Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.13450","snapshot_observed_at":"2026-08-12T16:22:47.837137Z","title":"A comparative survey of deep active learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.15217","last_updated":"2024-11-20T18:12:59Z","snapshot_observed_at":"2026-08-13T08:55:06.204528Z","submitted_at":"2024-11-20T18:12:59Z","title":"LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T16:22:47.837137Z"},"links":{"cited_paper":"/paper/2203.13450","citing_paper":"/paper/2411.15217"},"observation_digest":"sha256:72669c27ce0e19b439ba6f31c73f6412df1a028da517c65a7e513e7441122772","observation_id":"ee1499d3-1e88-4390-afe7-46c0e8ad2e47","resolution":{"observed_at":"2026-08-12T16:22:47.837137Z","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":"2026-08-12T16:22:47.841667Z","title":"A survey on deep active learning: Recent advances and new frontiers,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.15217","last_updated":"2024-11-20T18:12:59Z","snapshot_observed_at":"2026-08-13T08:55:06.204528Z","submitted_at":"2024-11-20T18:12:59Z","title":"LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T16:22:47.841667Z"},"links":{"citing_paper":"/paper/2411.15217"},"observation_digest":"sha256:3c670c2163b304b7cd165827c4a5ca40d45b708e36153bb2d6b327a646007ea4","observation_id":"9f3e8327-5ac8-44a8-a7f8-b0e5c0a4d5e7","resolution":{"observed_at":"2026-08-12T16:22:47.841667Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.05752","last_updated":"2024-11-08T18:10:46Z","snapshot_observed_at":"2026-08-13T05:59:27.182127Z","submitted_at":"2024-11-08T18:10:46Z","title":"FisherMask: Enhancing Neural Network Labeling Efficiency in Image Classification Using Fisher Information","version":1},"cited_work":{"arxiv_id":"2411.05752","doi":null,"metadata_source":"pith","pith_arxiv_id":"2411.05752","snapshot_observed_at":"2026-08-12T16:22:47.978456Z","title":"FisherMask: Enhancing Neural Network Labeling Efficiency in Image Classification Using Fisher Information","venue":"cs.LG","work_id":"75eee892-f7e3-47b6-848f-86a77a6d83cd","year":2024},"citing_paper":{"arxiv_id":"2411.15217","last_updated":"2024-11-20T18:12:59Z","snapshot_observed_at":"2026-08-13T08:55:06.204528Z","submitted_at":"2024-11-20T18:12:59Z","title":"LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T16:22:47.845861Z"},"links":{"cited_paper":"/paper/2411.05752","citing_paper":"/paper/2411.15217"},"observation_digest":"sha256:3c3d917122b112d14b027de6fe774da3d56b91961acfe1a46bef9a6c0e261158","observation_id":"16de7449-1393-4aa1-b0da-47a83181c24d","resolution":{"observed_at":"2026-08-12T16:22:47.984313Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:22:48.167024Z","title":"Verips: Verified pseudo- label selection for deep active learning,","venue":null,"work_id":"1a42df53-d7ed-453a-8e3f-e0bab8e024a8","year":2022},"citing_paper":{"arxiv_id":"2411.15217","last_updated":"2024-11-20T18:12:59Z","snapshot_observed_at":"2026-08-13T08:55:06.204528Z","submitted_at":"2024-11-20T18:12:59Z","title":"LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T16:22:47.849864Z"},"links":{"citing_paper":"/paper/2411.15217"},"observation_digest":"sha256:24e6e0ab75c645c7aa0d43a175e8e5aa7dfa6cc2cbba8879b19c11093497e797","observation_id":"3260333f-ddf8-4700-9dc0-76b0c20bced1","resolution":{"observed_at":"2026-08-12T16:22:48.172269Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:22:47.853369Z","title":"A new active labeling method for deep learning,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.15217","last_updated":"2024-11-20T18:12:59Z","snapshot_observed_at":"2026-08-13T08:55:06.204528Z","submitted_at":"2024-11-20T18:12:59Z","title":"LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T16:22:47.853369Z"},"links":{"citing_paper":"/paper/2411.15217"},"observation_digest":"sha256:adc434c8b7dc9ddb68390c96e217ac0f808ef6c66a1871900a19c1c79afc0f30","observation_id":"4678c88b-de1d-4254-baa4-1e3df709f128","resolution":{"observed_at":"2026-08-12T16:22:47.853369Z","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":"2026-08-12T16:22:47.857048Z","title":"Reading digits in natural images with unsupervised feature learning,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2411.15217","last_updated":"2024-11-20T18:12:59Z","snapshot_observed_at":"2026-08-13T08:55:06.204528Z","submitted_at":"2024-11-20T18:12:59Z","title":"LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T16:22:47.857048Z"},"links":{"citing_paper":"/paper/2411.15217"},"observation_digest":"sha256:ccc57f1082f466af7e7d92bbc4b1e7dc1d314cd05c8df71185cb67a7c39fefd0","observation_id":"8093aecc-e903-45db-bf83-dcf27943191b","resolution":{"observed_at":"2026-08-12T16:22:47.857048Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.00489","last_updated":"2018-06-01T10:17:23Z","snapshot_observed_at":"2026-07-06T05:53:39.440274Z","submitted_at":"2017-08-01T19:50:53Z","title":"Active Learning for Convolutional Neural Networks: A Core-Set Approach","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.00489","snapshot_observed_at":"2026-08-12T16:22:47.861003Z","title":"Active learning for convolutional neural networks: A core-set approach,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.15217","last_updated":"2024-11-20T18:12:59Z","snapshot_observed_at":"2026-08-13T08:55:06.204528Z","submitted_at":"2024-11-20T18:12:59Z","title":"LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T16:22:47.861003Z"},"links":{"cited_paper":"/paper/1708.00489","citing_paper":"/paper/2411.15217"},"observation_digest":"sha256:0f961c33af38216482eec4d6d52cd7e3d443ded6fcb46546f74d9685d7765466","observation_id":"4cee61d9-8b0f-45f3-9048-4d037fd1f7f9","resolution":{"observed_at":"2026-08-12T16:22:47.861003Z","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":"2026-08-12T16:22:48.142360Z","title":"Variational adversarial active learning,","venue":null,"work_id":"95a33457-b43d-44ff-ae58-5a0b2e038ce4","year":2019},"citing_paper":{"arxiv_id":"2411.15217","last_updated":"2024-11-20T18:12:59Z","snapshot_observed_at":"2026-08-13T08:55:06.204528Z","submitted_at":"2024-11-20T18:12:59Z","title":"LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T16:22:47.864542Z"},"links":{"citing_paper":"/paper/2411.15217"},"observation_digest":"sha256:67300eb8168a038116d605b5db0c0ada492e28d01fe3071ecd3ed1988c5ed02a","observation_id":"386af3f9-fc4a-422d-b354-027bdb420013","resolution":{"observed_at":"2026-08-12T16:22:48.146703Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:22:48.131402Z","title":"Deep active learning: Unified and principled method for query and training,","venue":null,"work_id":"efa0feee-0756-42b0-bee3-7252ec651459","year":2020},"citing_paper":{"arxiv_id":"2411.15217","last_updated":"2024-11-20T18:12:59Z","snapshot_observed_at":"2026-08-13T08:55:06.204528Z","submitted_at":"2024-11-20T18:12:59Z","title":"LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T16:22:47.867761Z"},"links":{"citing_paper":"/paper/2411.15217"},"observation_digest":"sha256:8d4d6391ff54dc914455a55be983fe5f0c34d72684e07f9457e57bc1cd7399a5","observation_id":"170ec4e9-6122-42e0-9b2b-e1bb05ff6cda","resolution":{"observed_at":"2026-08-12T16:22:48.135305Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:22:47.871067Z","title":"Learning loss for active learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.15217","last_updated":"2024-11-20T18:12:59Z","snapshot_observed_at":"2026-08-13T08:55:06.204528Z","submitted_at":"2024-11-20T18:12:59Z","title":"LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T16:22:47.871067Z"},"links":{"citing_paper":"/paper/2411.15217"},"observation_digest":"sha256:9417d1f8901975811ce12890d3b4ca1cb53839f03e494033d996dd0db3c075da","observation_id":"5ccf621f-edea-447e-848b-505b33a64304","resolution":{"observed_at":"2026-08-12T16:22:47.871067Z","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":"2026-08-12T16:22:47.874581Z","title":"Tiny imagenet visual recognition challenge,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2411.15217","last_updated":"2024-11-20T18:12:59Z","snapshot_observed_at":"2026-08-13T08:55:06.204528Z","submitted_at":"2024-11-20T18:12:59Z","title":"LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T16:22:47.874581Z"},"links":{"citing_paper":"/paper/2411.15217"},"observation_digest":"sha256:83edada3170fd5f619d417edbb68503f4186601c4f1af09e29454d22555f9879","observation_id":"181aa8f7-8928-4854-bfc8-917ab4ce707b","resolution":{"observed_at":"2026-08-12T16:22:47.874581Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1702.05373","last_updated":"2017-03-01T08:55:36Z","snapshot_observed_at":"2026-07-06T05:30:25.930441Z","submitted_at":"2017-02-17T15:06:14Z","title":"EMNIST: an extension of MNIST to handwritten letters","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1702.05373","snapshot_observed_at":"2026-08-12T16:22:47.877773Z","title":"Emnist: an extension of mnist to handwritten letters,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.15217","last_updated":"2024-11-20T18:12:59Z","snapshot_observed_at":"2026-08-13T08:55:06.204528Z","submitted_at":"2024-11-20T18:12:59Z","title":"LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T16:22:47.877773Z"},"links":{"cited_paper":"/paper/1702.05373","citing_paper":"/paper/2411.15217"},"observation_digest":"sha256:fbb227774a9c2414230bc31e278d6cf94fbe293f3ce983bc37f01daa9112ab27","observation_id":"9257fada-8dc2-4200-86da-e57e511c329b","resolution":{"observed_at":"2026-08-12T16:22:47.877773Z","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":"2026-08-12T16:22:48.108626Z","title":"Boosting active learning via improving test performance,","venue":null,"work_id":"b1d859be-7d0b-46fa-b669-cb74af4b9f2a","year":2022},"citing_paper":{"arxiv_id":"2411.15217","last_updated":"2024-11-20T18:12:59Z","snapshot_observed_at":"2026-08-13T08:55:06.204528Z","submitted_at":"2024-11-20T18:12:59Z","title":"LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T16:22:47.881312Z"},"links":{"citing_paper":"/paper/2411.15217"},"observation_digest":"sha256:3e6af6d57e44ae2551e1b552aa546a608e92e193622080520ef383eaa5d08bd1","observation_id":"61572134-1d51-4a32-8fa2-76970b727bcd","resolution":{"observed_at":"2026-08-12T16:22:48.112316Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:22:48.098139Z","title":"Entropic open- set active learning,","venue":null,"work_id":"124a4839-be43-446c-b853-e84dd973859b","year":2024},"citing_paper":{"arxiv_id":"2411.15217","last_updated":"2024-11-20T18:12:59Z","snapshot_observed_at":"2026-08-13T08:55:06.204528Z","submitted_at":"2024-11-20T18:12:59Z","title":"LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T16:22:47.884740Z"},"links":{"citing_paper":"/paper/2411.15217"},"observation_digest":"sha256:32b110c25c2cc6b352b264cbaebfdf7fd31e1d1ea1a3d94cf05639d7f0aa1c1a","observation_id":"f33a75da-9eb1-4b97-9b48-b5f3fd65dc0d","resolution":{"observed_at":"2026-08-12T16:22:48.101978Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:22:48.088018Z","title":"Deep active learning with noise stability,","venue":null,"work_id":"5b10a72d-da77-4773-b672-73c346264a9f","year":2024},"citing_paper":{"arxiv_id":"2411.15217","last_updated":"2024-11-20T18:12:59Z","snapshot_observed_at":"2026-08-13T08:55:06.204528Z","submitted_at":"2024-11-20T18:12:59Z","title":"LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T16:22:47.888339Z"},"links":{"citing_paper":"/paper/2411.15217"},"observation_digest":"sha256:e356262498c14259f50ba66f720b3e5d06a739f78f0e33eb843641d442b4bbe3","observation_id":"5420bd37-7c9c-4470-a766-265014c1ee45","resolution":{"observed_at":"2026-08-12T16:22:48.091664Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:22:48.077659Z","title":"Active learning guided by efficient surrogate learners,","venue":null,"work_id":"63b8b79c-caf7-4530-80ee-cdefe61d6450","year":2024},"citing_paper":{"arxiv_id":"2411.15217","last_updated":"2024-11-20T18:12:59Z","snapshot_observed_at":"2026-08-13T08:55:06.204528Z","submitted_at":"2024-11-20T18:12:59Z","title":"LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T16:22:47.891795Z"},"links":{"citing_paper":"/paper/2411.15217"},"observation_digest":"sha256:b09302834f7836efb47862740ddc4b82950e7f6670de03f26de60e261c130349","observation_id":"52c0d570-72c4-4497-a2e2-26317a6adc2b","resolution":{"observed_at":"2026-08-12T16:22:48.081480Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:22:47.895098Z","title":"Cifar-10 (canadian institute for advanced research),","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2411.15217","last_updated":"2024-11-20T18:12:59Z","snapshot_observed_at":"2026-08-13T08:55:06.204528Z","submitted_at":"2024-11-20T18:12:59Z","title":"LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T16:22:47.895098Z"},"links":{"citing_paper":"/paper/2411.15217"},"observation_digest":"sha256:28f8bbf4854b8a28cd199349cc83c4413c4925b3c13befc43c52fc9675c9c35b","observation_id":"c088d099-ce26-404a-8b98-758915328178","resolution":{"observed_at":"2026-08-12T16:22:47.895098Z","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":"2026-08-12T16:22:48.059841Z","title":"Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories,","venue":null,"work_id":"b845b684-8512-4c03-8f74-87d55cc23621","year":2004},"citing_paper":{"arxiv_id":"2411.15217","last_updated":"2024-11-20T18:12:59Z","snapshot_observed_at":"2026-08-13T08:55:06.204528Z","submitted_at":"2024-11-20T18:12:59Z","title":"LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T16:22:47.898147Z"},"links":{"citing_paper":"/paper/2411.15217"},"observation_digest":"sha256:9dc2f8ab279b0faeaea4ef85ac1cc68cf746c18989f017eabcad9bb52aee905a","observation_id":"d5cd647d-15be-4ea1-96ea-29feb87c502e","resolution":{"observed_at":"2026-08-12T16:22:48.063736Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:22:48.046692Z","title":"Disaster images dataset, version 1,","venue":null,"work_id":"08fa8ac9-b1a6-41ec-a5fa-d8268c8729d3","year":2021},"citing_paper":{"arxiv_id":"2411.15217","last_updated":"2024-11-20T18:12:59Z","snapshot_observed_at":"2026-08-13T08:55:06.204528Z","submitted_at":"2024-11-20T18:12:59Z","title":"LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T16:22:47.901603Z"},"links":{"citing_paper":"/paper/2411.15217"},"observation_digest":"sha256:2c838b01912933e0ab65ec30c59b90ab9d76c04b7901df26b0082b9a795a0996","observation_id":"1071e67c-bd3b-4903-ab76-d787546d255c","resolution":{"observed_at":"2026-08-12T16:22:48.051507Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:22:47.904809Z","title":"Latent structured active learning,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2411.15217","last_updated":"2024-11-20T18:12:59Z","snapshot_observed_at":"2026-08-13T08:55:06.204528Z","submitted_at":"2024-11-20T18:12:59Z","title":"LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T16:22:47.904809Z"},"links":{"citing_paper":"/paper/2411.15217"},"observation_digest":"sha256:efe6e9aa8067b37ce56a63a762f371452a6b62e36baa8a0c353aa5abb0400d4b","observation_id":"5c3536aa-0293-41af-bc0a-3fdf3b8f1af1","resolution":{"observed_at":"2026-08-12T16:22:47.904809Z","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":"2026-08-12T16:22:47.907979Z","title":"The power of ensembles for active learning in image classification,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.15217","last_updated":"2024-11-20T18:12:59Z","snapshot_observed_at":"2026-08-13T08:55:06.204528Z","submitted_at":"2024-11-20T18:12:59Z","title":"LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T16:22:47.907979Z"},"links":{"citing_paper":"/paper/2411.15217"},"observation_digest":"sha256:8a9bd6f275c4cec7289c28c9d5a253db021a67ffb4958b336b149f580d1f03ba","observation_id":"3bf3a115-fbb8-47aa-8f4b-fdd735655ef0","resolution":{"observed_at":"2026-08-12T16:22:47.907979Z","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":"2026-08-12T16:22:48.023148Z","title":"Similar: Sub- modular information measures based active learning in realistic scenar- ios,","venue":null,"work_id":"48a78f7b-8662-49c0-8076-a57280cdf147","year":2021},"citing_paper":{"arxiv_id":"2411.15217","last_updated":"2024-11-20T18:12:59Z","snapshot_observed_at":"2026-08-13T08:55:06.204528Z","submitted_at":"2024-11-20T18:12:59Z","title":"LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T16:22:47.911275Z"},"links":{"citing_paper":"/paper/2411.15217"},"observation_digest":"sha256:486c6ba08710699a5f0f2e95f6bf807dd51b5daeba3779f61cc0de9b261f552b","observation_id":"52bc8b21-c21f-4ae3-9122-cf1d129f8394","resolution":{"observed_at":"2026-08-12T16:22:48.026956Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.02794","last_updated":"2022-06-16T14:36:33Z","snapshot_observed_at":"2026-08-10T14:41:38.442544Z","submitted_at":"2022-02-06T15:09:05Z","title":"Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.02794","snapshot_observed_at":"2026-08-12T16:22:47.914602Z","title":"Active learning on a budget: Opposite strategies suit high and low budgets,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.15217","last_updated":"2024-11-20T18:12:59Z","snapshot_observed_at":"2026-08-13T08:55:06.204528Z","submitted_at":"2024-11-20T18:12:59Z","title":"LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T16:22:47.914602Z"},"links":{"cited_paper":"/paper/2202.02794","citing_paper":"/paper/2411.15217"},"observation_digest":"sha256:062246e80ee8daac4614fb802c72506a638a60f8a7b3b9a223b864fa8dcfae61","observation_id":"ec760d9f-6822-406d-a06a-e02718d125b1","resolution":{"observed_at":"2026-08-12T16:22:47.914602Z","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":"2026-08-12T16:22:48.012194Z","title":"Active learning under label shift,","venue":null,"work_id":"36ddd87a-907a-4617-b002-c52e675f92c7","year":2021},"citing_paper":{"arxiv_id":"2411.15217","last_updated":"2024-11-20T18:12:59Z","snapshot_observed_at":"2026-08-13T08:55:06.204528Z","submitted_at":"2024-11-20T18:12:59Z","title":"LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T16:22:47.918310Z"},"links":{"citing_paper":"/paper/2411.15217"},"observation_digest":"sha256:2989e64276f5fc0a13e86840e6e3084d807cab423e212511b2ee3b19789786ec","observation_id":"a759149a-34b3-472b-a9d2-f256fe772015","resolution":{"observed_at":"2026-08-12T16:22:48.015659Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:22:48.001548Z","title":"Nearest neighbor classifier embedded network for active learning,","venue":null,"work_id":"326072a9-a1df-496f-a095-334e8238037b","year":2021},"citing_paper":{"arxiv_id":"2411.15217","last_updated":"2024-11-20T18:12:59Z","snapshot_observed_at":"2026-08-13T08:55:06.204528Z","submitted_at":"2024-11-20T18:12:59Z","title":"LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T16:22:47.921929Z"},"links":{"citing_paper":"/paper/2411.15217"},"observation_digest":"sha256:1655b45d15223192d4d42f6931b6014c3e120df53d08eba9fb3a58d67f17401b","observation_id":"d03754a1-447a-4842-b3df-4a8c2624dad6","resolution":{"observed_at":"2026-08-12T16:22:48.005284Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2411.15217","last_updated":"2024-11-20T18:12:59Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T08:55:06.204528Z","submitted_at":"2024-11-20T18:12:59Z","title":"LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training"},"reference_resolution":{"displayed":25,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":12,"verified_exact":1,"verified_fuzzy":12},"total_outbound_references":25},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 0 inbound Pith citation observations for arXiv:2411.15217."}