{"as_of":"2026-08-11T11:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:13f07bb35b8c2ce6c129e03db0f6af17b53ea5e58eb2c17a6b6e422ca5e84119","coverage":[{"denominator":32,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":32,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T19:18:56.089654Z","state":"measured"},{"denominator":32,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":32,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+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/2502.05456/citation-record","integrity":"/paper/2502.05456/integrity","json":"/paper/2502.05456/citation-record.json","paper":"/paper/2502.05456"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2308.09969","last_updated":"2023-08-19T09:55:19Z","snapshot_observed_at":"2026-08-05T06:42:07.966774Z","submitted_at":"2023-08-19T09:55:19Z","title":"On-the-fly Improving Performance of Deep Code Models via Input Denoising","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.09969","snapshot_observed_at":"2026-08-08T19:18:55.786971Z","title":"On-the-fly improving perfor- mance of deep code models via input denoising,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:55.786971Z"},"links":{"cited_paper":"/paper/2308.09969","citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:cf7d5a5ce9b203e9c73898ce3366a8fbbca4176bd7a227ac127fea6e93dc9dc0","observation_id":"b84605a7-8b70-4d86-aeb3-b08e1e1d9cff","resolution":{"observed_at":"2026-08-08T19:18:55.786971Z","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":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T19:18:56.293673Z","title":"Natural attack for pre-trained models of code,","venue":null,"work_id":"933d7610-ac4e-4fb8-912a-82efcc8d29b6","year":2022},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:55.829086Z"},"links":{"citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:10af402ec986958eb98ea0172b4369505594f44763afbcbe2f293ca8b8bb43b7","observation_id":"ebb789ae-6f58-4a43-9289-fd128de96487","resolution":{"observed_at":"2026-08-08T19:18:56.297367Z","resolver_source":"arxiv_id_nonexistent","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-08T19:18:56.550892Z","title":"Challenging Machine Learning-based Clone Detectors via Semantic-preserving Code Transformations,","venue":null,"work_id":"85a0b72a-6884-471c-9d3a-6a50e2c537bf","year":2023},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:55.832524Z"},"links":{"citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:b0230742f3ef1746fff8f6c526bfb5407808b44e6362ac95a6912ae8bb370227","observation_id":"ef0290c7-306d-4b97-8da7-4084c4111e4d","resolution":{"observed_at":"2026-08-08T19:18:56.553773Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2102.04664","last_updated":"2021-03-16T08:28:37Z","snapshot_observed_at":"2026-07-06T10:39:42.676631Z","submitted_at":"2021-02-09T06:16:25Z","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.04664","snapshot_observed_at":"2026-08-08T19:18:55.836726Z","title":"Codexglue: A machine learning benchmark dataset for code understanding and generation,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:55.836726Z"},"links":{"cited_paper":"/paper/2102.04664","citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:5818bf6c45976640f1cb66e1e8bed9c3cb4403845814d69b783ba9e3e2600f37","observation_id":"002770ff-34a0-4b7a-8466-39592bfc4b07","resolution":{"observed_at":"2026-08-08T19:18:55.836726Z","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":"2026-08-08T19:18:56.542592Z","title":"Intellicode compose: Code generation using transformer,","venue":null,"work_id":"00c4ab49-3e7a-4c43-ad9b-527afb92d509","year":2020},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:55.840798Z"},"links":{"citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:713e470e82d1cb73baf49b98bcfdbfd99990f8586a2efbb33a230c20f2a2b4eb","observation_id":"d2a61de5-b302-48d7-80db-fbdc893e65bd","resolution":{"observed_at":"2026-08-08T19:18:56.545343Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-08T19:18:56.534370Z","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,","venue":null,"work_id":"d71d5fc6-48e3-4a0e-9116-dc37dd0e858b","year":2019},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:55.843762Z"},"links":{"citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:64dd201f291b6fcbc4c18758f258a7fa73d30d0ed01899feab586f4b63ccef01","observation_id":"43bff370-851a-42c9-b5be-b11549c3b201","resolution":{"observed_at":"2026-08-08T19:18:56.537168Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-08T19:18:56.525543Z","title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter,","venue":null,"work_id":"9abc4fe9-a4aa-4205-88fc-3a24117dcdcd","year":2020},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:55.847187Z"},"links":{"citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:86d31dd25dec39206d32c0128e7138cbf7636e506f52ede4b8ab85e52a469db1","observation_id":"26a275f9-5606-48ec-a987-2794497748c0","resolution":{"observed_at":"2026-08-08T19:18:56.528943Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-08T19:18:56.516134Z","title":"Graphcodebert: Pre- training code representations with data flow,","venue":null,"work_id":"2354c9e7-5ca0-4d96-9f5e-98ff25d6597d","year":2021},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:55.850311Z"},"links":{"citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:13c5ef2d9a3601977286a9e0a738d91047f9592882b89b2343aa02378ad171e2","observation_id":"9d90c93f-1d6a-47ee-b863-fee8a91b9928","resolution":{"observed_at":"2026-08-08T19:18:56.519509Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-08T19:18:56.506740Z","title":"Evaluating Large Language Models Trained on Code,","venue":null,"work_id":"9d9cf084-c511-477e-95ea-1c954fd6c017","year":2021},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:55.853785Z"},"links":{"citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:05cc5db8ec369d9f1d922f66890291877cea652d6e4a2cb15c339bc0ff303c48","observation_id":"7556e201-7010-42ed-a475-0e94b99452dc","resolution":{"observed_at":"2026-08-08T19:18:56.510184Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-08T19:18:56.496669Z","title":"Repairing failure-inducing inputs with input reflection,","venue":null,"work_id":"dfa9a9aa-9372-4cd7-b3ec-28abe0475fec","year":2022},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:55.857319Z"},"links":{"citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:7317d650a303973ef577b5652372179a458b2a97d05328eb589450d56532b690","observation_id":"379f30b2-cdfe-4734-b259-71a94a9c78ee","resolution":{"observed_at":"2026-08-08T19:18:56.500073Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-08T19:18:56.486942Z","title":"Self-checking deep neural networks in deployment,","venue":null,"work_id":"5babfbc8-bbae-41f1-aae9-fd1696ac6cd8","year":2021},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:55.860199Z"},"links":{"citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:c1ec3fa2f5013c9b48853826a9d4820b99c350ef61e8cd88da05dbedb2c50585","observation_id":"96c21c04-e3f5-4613-916d-dd95288116ba","resolution":{"observed_at":"2026-08-08T19:18:56.490684Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-08T19:18:56.477520Z","title":"Natural language processing,","venue":null,"work_id":"f9b697dc-4bef-4d14-bd59-0c7e367ab65f","year":2020},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:55.863578Z"},"links":{"citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:5ee73642245611b71201274bad170dab1e7a7c1c28112c2f373821470d990c80","observation_id":"20257acf-5981-4121-856d-273857a76eb3","resolution":{"observed_at":"2026-08-08T19:18:56.480844Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-08T19:18:56.468183Z","title":"Dissector: Input val- idation for deep learning applications by crossing-layer dissection,","venue":null,"work_id":"b84defc9-4f1b-4873-97db-04069871eccd","year":2020},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:55.866884Z"},"links":{"citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:859267c9eaf985f8280012b032b7304e7e0b168074510d58ae10f6297d6ebaee","observation_id":"1bc2542e-b53f-4775-96be-409018be931e","resolution":{"observed_at":"2026-08-08T19:18:56.471566Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-08T19:18:56.458817Z","title":"Data Augmentation by Program Trans- formation,","venue":null,"work_id":"cbbb19b5-9676-4c06-b65c-63b7b889d5ef","year":2022},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:55.870372Z"},"links":{"citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:93b69f48286642becdda26a3413579ac53dc1f95a653fc5acf83237edade9842","observation_id":"be99a6fa-aa0c-4237-91ad-94f870abfc22","resolution":{"observed_at":"2026-08-08T19:18:56.462208Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.15804","last_updated":"2025-06-16T20:59:44Z","snapshot_observed_at":"2026-08-10T13:53:58.768106Z","submitted_at":"2025-01-27T06:23:37Z","title":"CodeImprove: Program Adaptation for Deep Code Models","version":2},"cited_work":{"arxiv_id":"2501.15804","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.15804","snapshot_observed_at":"2026-08-08T19:18:56.117222Z","title":"CodeImprove: Program Adaptation for Deep Code Models","venue":"cs.SE","work_id":"6d83d7ab-c5b9-4b7c-8fda-0de9a63efd4b","year":2025},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:55.873779Z"},"links":{"cited_paper":"/paper/2501.15804","citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:ca4b7f6c8a05ce077eef75d946aa52a0e86957a823295dff0fb8c6c75b06d1b7","observation_id":"87806bc2-770f-434c-8979-ce58e7341d25","resolution":{"observed_at":"2026-08-08T19:18:56.122525Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-08T19:18:55.877840Z","title":"On calibration of modern neural networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:55.877840Z"},"links":{"citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:ca2800b120e456af9ff38e7b34f7a3b5d3a07014e0415da53bbfc7ba19a8ed28","observation_id":"bceb2d4c-95f1-47ea-9033-646b9a96322f","resolution":{"observed_at":"2026-08-08T19:18:55.877840Z","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":"2026-08-08T19:18:56.443949Z","title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks,","venue":null,"work_id":"d89ccd42-31e0-4315-af3a-26154a04a4f6","year":2018},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:55.881405Z"},"links":{"citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:dcf87b04ddd2481c4bb171ffe04b94594b48f0ed2ac81c297facc5702208cd67","observation_id":"18127be4-dfa4-43ac-9ba0-0658d88a957a","resolution":{"observed_at":"2026-08-08T19:18:56.447352Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-08T19:18:56.435005Z","title":"Dropout as a bayesian approximation: Representing model uncertainty in deep learning,","venue":null,"work_id":"2b63c1ea-3069-49d1-baba-03f2e7cf34ba","year":2016},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:55.883996Z"},"links":{"citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:c2452081ec0d8e864e596caa44125f9f814d53ca4d7d3c956f4f31d9d454bc8d","observation_id":"e6ac2b5c-cf2b-4905-8ecc-8328963f06f8","resolution":{"observed_at":"2026-08-08T19:18:56.438254Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-08T19:18:56.425853Z","title":"code2vec: Learn- ing distributed representations of code,","venue":null,"work_id":"4422d53a-8bf3-420d-9977-6ce28942f403","year":2019},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:55.887058Z"},"links":{"citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:0665c6a9636f73cead816fd35a5416ee91713a369d5104e748755b54c40b82d5","observation_id":"e76889df-1d33-447e-b78d-4b1b1c1746f2","resolution":{"observed_at":"2026-08-08T19:18:56.429060Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-08T19:18:56.417170Z","title":"Quantifying uncertainties in natural language processing tasks,","venue":null,"work_id":"d0522cd1-3492-42ba-868f-973ae473dc0e","year":2019},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:55.889836Z"},"links":{"citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:301c80e2fecdcaf0549194d139ea780c305e46638bc2b9b889898af771733a04","observation_id":"c40459c7-e1bf-4a30-aefe-8645006a5b84","resolution":{"observed_at":"2026-08-08T19:18:56.420017Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-08T19:18:56.409136Z","title":"Towards better confidence estimation for neural models,","venue":null,"work_id":"b33be62a-05e2-4e80-b7eb-d57b29d0df7a","year":2019},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:55.894025Z"},"links":{"citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:f63decd7f818f0dcfcff7985bd98f6e788a3d9f64f8f681cc57113c205ecec04","observation_id":"128c9503-114d-42cd-a48c-2f013e69e0d0","resolution":{"observed_at":"2026-08-08T19:18:56.411836Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-08T19:18:56.399915Z","title":"Addressing failure prediction by learning model confidence,","venue":null,"work_id":"8a25e619-e984-477d-ab15-9fba7464e4c1","year":2019},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:55.897149Z"},"links":{"citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:3ebecad6f00e3ae523a0ee0de0981a85035db5b1aebecee6ee22a613eba40418","observation_id":"6ace0f68-7dfa-4ede-876b-b0b580b28301","resolution":{"observed_at":"2026-08-08T19:18:56.402908Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-08T19:18:56.391225Z","title":null,"venue":null,"work_id":"71282e56-5e62-4d51-a103-5f2be3070cd2","year":2021},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:55.900012Z"},"links":{"citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:583c0ab3c81500dfbbe1ca781adb282e59d7d30bf6bf6136a63f738d9ec42143","observation_id":"dd30b6bb-19ec-4218-aab5-c0f6a2084b7b","resolution":{"observed_at":"2026-08-08T19:18:56.393848Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-08T19:18:56.381101Z","title":"Unsupervised risk estimation using only conditional independence structure,","venue":null,"work_id":"409757c6-7fd0-474e-92fe-f19dd4d99790","year":2016},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:55.903165Z"},"links":{"citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:9591bee12f9e08a537e424d82402443f49b765667a4a3fb5ce244d190022a789","observation_id":"819f6353-1f64-4bad-b2d4-9702312f2b63","resolution":{"observed_at":"2026-08-08T19:18:56.384799Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-08T19:18:56.371795Z","title":"A mathematical theory of communication,","venue":null,"work_id":"b6549de6-d4ab-49f9-8cd1-9cf27c71e971","year":1948},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:55.906067Z"},"links":{"citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:6691541dc0e7f24305523c090f19ef1093b678852ea3e890623e8af5c5131811","observation_id":"a70ab58f-81bf-41c4-8fb5-a6075fe7935c","resolution":{"observed_at":"2026-08-08T19:18:56.375066Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-08T19:18:56.362584Z","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages,","venue":null,"work_id":"a892acb3-a91d-4d08-ba0b-3220523423c1","year":2020},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:55.909201Z"},"links":{"citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:4e7484f2892eb43768771ffbf38c1d4a5955bd2fce9fdd85c9ff4252dd20b70a","observation_id":"5d1af431-c953-4263-ac7b-8fe0bd0306a0","resolution":{"observed_at":"2026-08-08T19:18:56.365897Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-08T19:18:56.352258Z","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach,","venue":null,"work_id":"e9bcdd41-8e92-460a-a509-8d46ed3420b7","year":2019},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:55.931646Z"},"links":{"citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:8b5efc5da19134d8af669be0ef3c13c6d0405985fb18b605ae5a6ae673522340","observation_id":"86fd46c0-e8ce-4c21-8ebc-fd18c554d30c","resolution":{"observed_at":"2026-08-08T19:18:56.355813Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-08T19:18:55.959204Z","title":"Devign: Effective vul- nerability identification by learning comprehensive program semantics via graph neural networks,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:55.959204Z"},"links":{"citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:d0ea246fdc699f2e705e220d53d0a88598fb047708a8bd051cab2c3cb31380c7","observation_id":"a272ebe1-9477-41aa-a9e7-9d00eb2877f8","resolution":{"observed_at":"2026-08-08T19:18:55.959204Z","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":"2026-08-08T19:18:56.336895Z","title":"Convolutional neural networks on assembly code for predicting software defects,","venue":null,"work_id":"a6f25607-e008-4610-aca8-d5d1fac6bd1a","year":2017},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:56.004241Z"},"links":{"citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:081d3f6941644f6ad93a0d2caa30a8f29ab1360808b7f7e2d098407cef468ddf","observation_id":"78a03ded-3495-4bf3-9c1b-3d1e743db9ef","resolution":{"observed_at":"2026-08-08T19:18:56.340547Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-08T19:18:56.073762Z","title":"Simple and scalable predictive uncertainty estimation using deep ensembles,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:56.073762Z"},"links":{"citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:443177a4a9bf04b41b7c2fcf554538c569165001cbe9925587d6bdeea313b663","observation_id":"3fa680db-d78c-4db6-b996-9e79af64dfdd","resolution":{"observed_at":"2026-08-08T19:18:56.073762Z","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":"2026-08-08T19:18:56.322026Z","title":"Random search algorithms,","venue":null,"work_id":"87bfddc9-d379-4c76-bea5-78a9b410be32","year":2009},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:56.086835Z"},"links":{"citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:ef1496f6f96e4ecc8d83b8a2a248e768a7773886658ee95b123e69e401a5be1c","observation_id":"142d00eb-3acf-4d8f-a2f8-1740ad2bddbd","resolution":{"observed_at":"2026-08-08T19:18:56.325286Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-08T19:18:56.312260Z","title":"Hill-climbing search,","venue":null,"work_id":"d782f348-3466-4000-8462-1029024cd0a6","year":2006},"citing_paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-08T19:18:56.089654Z"},"links":{"citing_paper":"/paper/2502.05456"},"observation_digest":"sha256:3eaf169167f52b141177367fc98980a71898765a3ec5a77c01bd3f3f7bb0fdb7","observation_id":"74d5fb0b-cbb0-4c20-92a9-3f00fb914fae","resolution":{"observed_at":"2026-08-08T19:18:56.315433Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2502.05456","last_updated":"2025-06-23T21:32:08Z","latest_version":2,"primary_category":"cs.SE","snapshot_observed_at":"2026-08-08T19:12:35.110670Z","submitted_at":"2025-02-08T05:41:01Z","title":"Framework for On the Fly Input Refinement for Deep Learning Models"},"reference_resolution":{"displayed":32,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":6,"verified_exact":2,"verified_fuzzy":24},"total_outbound_references":32},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 0 inbound Pith citation observations for arXiv:2502.05456."}