{"as_of":"2026-08-11T19:33:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:079b287522faa495bad09b0803e0159977be55f10e01b70f465cb6d43b44769e","coverage":[{"denominator":58,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":58,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T14:00:50.355841Z","state":"measured"},{"denominator":59,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":59,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T19:18:55.873779Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-08T19:18:56.117222Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"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"}}],"links":{"evidence":"/evidence","html":"/paper/2501.15804/citation-record","integrity":"/paper/2501.15804/integrity","json":"/paper/2501.15804/citation-record.json","paper":"/paper/2501.15804"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2308.09969","last_updated":"2023-08-19T09:55:19Z","snapshot_observed_at":"2026-08-11T14:21:49.554345Z","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":"2026-08-10T14:00:50.152067Z","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":"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},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.152067Z"},"links":{"cited_paper":"/paper/2308.09969","citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:87fd1ef30b3a72ccf2147269b49eb7b3a708b05460b9141abf26272c66bca5f0","observation_id":"b3c6b63b-095f-4d35-984e-586086f338b9","resolution":{"observed_at":"2026-08-10T14:00:50.152067Z","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":"2026-08-10T14:00:50.156777Z","title":"Natural attack for pre-trained models of code,","venue":null,"work_id":null,"year":2022},"citing_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},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.156777Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:d467c6db86c4bc0443fccc8ef570446cbc471514fda0f845b6eb3e52ddf52ce6","observation_id":"f847ec77-da40-4912-a941-f818d72e6142","resolution":{"observed_at":"2026-08-10T14:00:50.156777Z","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":"2026-08-10T14:00:50.160528Z","title":"Challenging Machine Learning-based Clone Detectors via Semantic-preserving Code Transformations,","venue":null,"work_id":null,"year":2023},"citing_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},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.160528Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:8cfc6356e38858c6e45825a1d3bd1a2b9951c7dc21e78ee64fdb16b8a96f3e70","observation_id":"88a97641-55dc-4b89-a5a2-2ff8fc5aef88","resolution":{"observed_at":"2026-08-10T14:00:50.160528Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-10T14:00:50.164561Z","title":"Codexglue: A machine learning benchmark dataset for code understanding and generation,","venue":null,"work_id":null,"year":2021},"citing_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},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.164561Z"},"links":{"cited_paper":"/paper/2102.04664","citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:541a893a032cad1f81cbc7d42824940033186aa3d2e8d466fc2d80dd82a2088b","observation_id":"3a8081dc-f3f5-4c9b-8973-985425f818cd","resolution":{"observed_at":"2026-08-10T14:00:50.164561Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.07506","last_updated":"2024-03-12T10:43:26Z","snapshot_observed_at":"2026-08-11T03:34:05.076923Z","submitted_at":"2024-03-12T10:43:26Z","title":"Robustness, Security, Privacy, Explainability, Efficiency, and Usability of Large Language Models for Code","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.07506","snapshot_observed_at":"2026-08-10T14:00:50.168883Z","title":"Robustness, security, privacy, explainability, efficiency, and usability of large language models for code,","venue":null,"work_id":null,"year":2024},"citing_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},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.168883Z"},"links":{"cited_paper":"/paper/2403.07506","citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:0661d401abd0cc61dff1971b0d78e073b65f604d93c7890122593c0a6f35bd43","observation_id":"c1618678-1d6f-48ae-8057-1789e8bd38f7","resolution":{"observed_at":"2026-08-10T14:00:50.168883Z","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":"2026-08-10T14:00:50.957269Z","title":"Adversarial examples for models of code,","venue":null,"work_id":"c43ac7b9-a1ba-4bf4-9411-2900f09a4eab","year":2020},"citing_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},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.172809Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:e57a29f07f5f26af2ed6960d15ed71a5030e111e5c1fdf21a3dc66feb774fa74","observation_id":"925342ba-763a-4ee9-b408-6f2efc6a042b","resolution":{"observed_at":"2026-08-10T14:00:50.961514Z","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":"2026-08-10T14:00:50.945861Z","title":"Codes: towards code model generalization under distribution shift,","venue":null,"work_id":"769b378d-c37e-4573-b989-47131140a6e1","year":2023},"citing_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},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.176714Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:5c1cf7e567cadca6630f2b2cb780a34db684969043ce9db41d6eb0863e110169","observation_id":"71ae61eb-94e0-4622-80b6-c73522d9b55a","resolution":{"observed_at":"2026-08-10T14:00:50.950008Z","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":"2107.10989","last_updated":"2021-07-23T01:50:22Z","snapshot_observed_at":"2026-07-06T11:31:46.316473Z","submitted_at":"2021-07-23T01:50:22Z","title":"Estimating Predictive Uncertainty Under Program Data Distribution Shift","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.10989","snapshot_observed_at":"2026-08-10T14:00:50.180081Z","title":"Estimating predictive uncertainty under program data distribution shift,","venue":null,"work_id":null,"year":2021},"citing_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},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.180081Z"},"links":{"cited_paper":"/paper/2107.10989","citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:adcb00f271f95331b1462caa65ca235ca39d4066e82490fec6183ebca4919269","observation_id":"523260bf-bfba-4393-89a4-34d9218b39cb","resolution":{"observed_at":"2026-08-10T14:00:50.180081Z","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":"2026-08-10T14:00:50.183815Z","title":"Tailoring programs for static analysis via program transformation,","venue":null,"work_id":null,"year":2020},"citing_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},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.183815Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:a22d425f6ddc0f82b34ab07f39bd9cbcfa6e18ea4d915a7ac7da303e9556e5fe","observation_id":"9a78e640-23d7-48be-9374-8f5b07d3bfb0","resolution":{"observed_at":"2026-08-10T14:00:50.183815Z","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":"2026-08-10T14:00:50.187375Z","title":"T-fuzz: fuzzing by program transformation,","venue":null,"work_id":null,"year":2018},"citing_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},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.187375Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:d640f31c385e44357b535193a26f3d0c5c269baf5e4917279a4cc8153b096d27","observation_id":"ff32c1e3-f570-453e-948c-6dc394a52c58","resolution":{"observed_at":"2026-08-10T14:00:50.187375Z","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":"2026-08-10T14:00:50.191228Z","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,","venue":null,"work_id":null,"year":2019},"citing_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},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.191228Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:076049e210b8ff03c640940af04c3746cde77bbbb0121be84a9294385a00c218","observation_id":"dd72ffd9-7c6c-4e8e-ae8f-7ad41218b0e2","resolution":{"observed_at":"2026-08-10T14:00:50.191228Z","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":"2026-08-10T14:00:50.195024Z","title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter,","venue":null,"work_id":null,"year":2020},"citing_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},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.195024Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:d65c1be6285ccb7782c991388414f49685ab0e4699f2233c48053f172c1ed2f9","observation_id":"cab5bde1-5d80-466c-bd97-2ae4d112c154","resolution":{"observed_at":"2026-08-10T14:00:50.195024Z","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":"2026-08-10T14:00:50.198213Z","title":"Graphcodebert: Pre- training code representations with data flow,","venue":null,"work_id":null,"year":2021},"citing_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},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.198213Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:f7af08d4276dd4bfc5612fe3b58dad796bffb8867d500673bea8263bd868f8af","observation_id":"d1911433-c9b7-44d7-bd87-ca4fc205c47e","resolution":{"observed_at":"2026-08-10T14:00:50.198213Z","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":"2026-08-10T14:00:50.201690Z","title":"Evaluating Large Language Models Trained on Code,","venue":null,"work_id":null,"year":2021},"citing_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},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.201690Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:82818610e09769b61b5aaf56472c84c769b9b8ea1f1e66b32350fa64865812e9","observation_id":"37359399-f5e6-4eaa-8203-77c43342500b","resolution":{"observed_at":"2026-08-10T14:00:50.201690Z","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":"2026-08-10T14:00:50.205113Z","title":"Data Augmentation by Program Trans- formation,","venue":null,"work_id":null,"year":2022},"citing_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},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.205113Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:e2c22177b1bd2e69313d7a0ca7095a31c18ac309e0ae2e47d1fa2522882ab750","observation_id":"234525c9-f092-4ed7-8465-e5fa45647f92","resolution":{"observed_at":"2026-08-10T14:00:50.205113Z","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":"2026-08-10T14:00:50.208394Z","title":"Self-checking deep neural networks in deployment,","venue":null,"work_id":null,"year":2021},"citing_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},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.208394Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:15c56e85c69f64498d3907e1d25afdeac4d6a63ddc0a7fed4b20656269b925e3","observation_id":"6009b041-f97b-4f48-9f60-8a4c67fc2811","resolution":{"observed_at":"2026-08-10T14:00:50.208394Z","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":"2026-08-10T14:00:50.212183Z","title":"Repairing failure-inducing inputs with input reflection,","venue":null,"work_id":null,"year":2022},"citing_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},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.212183Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:ed26369adb9468f6438502cc32c96a1c112214f432e60db07d8b9b55fd30af6e","observation_id":"31e00f58-a238-4e21-9500-8e1ba6e35bf8","resolution":{"observed_at":"2026-08-10T14:00:50.212183Z","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":"2026-08-10T14:00:50.215684Z","title":"On calibration of modern neural networks,","venue":null,"work_id":null,"year":2017},"citing_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},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.215684Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:49dc0fb47cf9fd40d022f424205332cf58d392e7676d2f2f752aa1e101cbf033","observation_id":"4ede3250-f8e5-4767-964d-3642860e579c","resolution":{"observed_at":"2026-08-10T14:00:50.215684Z","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":"2026-08-10T14:00:50.219051Z","title":"Dissector: Input val- idation for deep learning applications by crossing-layer dissection,","venue":null,"work_id":null,"year":2020},"citing_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},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.219051Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:7f62c0f277897f8fbd93c2dc64ac007fefc344c81f2cf476d4b84c0c1b9c5e5b","observation_id":"fc0fc42a-d553-4044-831f-e687d29abb88","resolution":{"observed_at":"2026-08-10T14:00:50.219051Z","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":"2026-08-10T14:00:50.222394Z","title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks,","venue":null,"work_id":null,"year":2018},"citing_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},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.222394Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:e0d27ae9f485f6cffaa1f9e2adfec3b7c6c5c04b6930ccf4ed2d7b054916ead6","observation_id":"a66cfb27-a6b6-436d-aab3-322d6e158a4b","resolution":{"observed_at":"2026-08-10T14:00:50.222394Z","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":"2026-08-10T14:00:50.225690Z","title":"Dropout as a bayesian approximation: Representing model uncertainty in deep learning,","venue":null,"work_id":null,"year":2016},"citing_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},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.225690Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:cc852a53f94200324091cf002f67f8b6f45aea632704a6b03633c1a14dfa0f31","observation_id":"89809511-d5ae-4d10-9620-c8bcb9cb4599","resolution":{"observed_at":"2026-08-10T14:00:50.225690Z","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":"2026-08-10T14:00:50.229072Z","title":"code2vec: Learn- ing distributed representations of code,","venue":null,"work_id":null,"year":2019},"citing_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},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.229072Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:5ad870637025944c676c4b58b3b566e853279b9ed881455d12d4dde295bfd669","observation_id":"5e7f6596-6399-459d-937d-5d1c2e01901b","resolution":{"observed_at":"2026-08-10T14:00:50.229072Z","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":"2026-08-10T14:00:50.232363Z","title":"Quantifying uncertainties in natural language processing tasks,","venue":null,"work_id":null,"year":2019},"citing_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},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.232363Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:e3af1be9e3b4ffb7ea845ca7af5331de275040f5bdde02871df0e3ad1054cb41","observation_id":"8ea88732-ec72-4b40-a032-009144f07808","resolution":{"observed_at":"2026-08-10T14:00:50.232363Z","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":"2026-08-10T14:00:50.235789Z","title":"Towards better confidence estimation for neural models,","venue":null,"work_id":null,"year":2019},"citing_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},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.235789Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:d96e10ccef0ecc1ae3f2ba3bbadd43aafb051f74c491552e3904f0b0e889542d","observation_id":"21967877-eaf7-4533-9f57-4c937c2fcef6","resolution":{"observed_at":"2026-08-10T14:00:50.235789Z","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":"2026-08-10T14:00:50.239349Z","title":"Addressing failure prediction by learning model confidence,","venue":null,"work_id":null,"year":2019},"citing_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},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.239349Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:bea080dca6b071414047b83bcb23e58620e45347656ff64eb93ed5aa6d0d19c9","observation_id":"18cfd1b1-c694-4f8d-8b6b-465c50aed925","resolution":{"observed_at":"2026-08-10T14:00:50.239349Z","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":"2026-08-10T14:00:50.242750Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_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},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.242750Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:3991ba190d7e999d09d32474efe61b01141e2807ff4557f8ea3f5c82096ae9ae","observation_id":"11b899e1-2e06-4605-9519-0e84ed397098","resolution":{"observed_at":"2026-08-10T14:00:50.242750Z","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":"2026-08-10T14:00:50.246285Z","title":"Unsupervised risk estimation using only conditional independence structure,","venue":null,"work_id":null,"year":2016},"citing_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},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.246285Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:22101e6b1e987858fccab275a26b0647bce91ae148e70f1726b27e9bb6b01306","observation_id":"fd45211e-e819-4f21-9862-81a992b68bd4","resolution":{"observed_at":"2026-08-10T14:00:50.246285Z","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":"2026-08-10T14:00:50.249956Z","title":"A mathematical theory of communication,","venue":null,"work_id":null,"year":1948},"citing_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},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.249956Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:efd6d5eaa0b4401b799ec31563e1e22f1fab4d3fc252523d5be8ddf82ab04233","observation_id":"6bc155be-8f02-4b9a-b84a-0309bbd006a9","resolution":{"observed_at":"2026-08-10T14:00:50.249956Z","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":"2026-08-10T14:00:50.809542Z","title":"Codeimprove repository","venue":null,"work_id":"ebf0c25c-0bbf-4c7d-9ac2-2d1f601e9450","year":null},"citing_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},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.253922Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:94a45f76bd6fe46a27424b47e058c5e7c402e8d5635d05ca0e4feed6da5e43ed","observation_id":"1c9bf45f-223c-4c38-8606-0d9d7344c8cd","resolution":{"observed_at":"2026-08-10T14:00:50.813237Z","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":"2026-08-10T14:00:50.257437Z","title":"Towards evaluating the robustness of neural networks,","venue":null,"work_id":null,"year":2017},"citing_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},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.257437Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:90bd889eead4cb64c493e7da6d53144ce9be75749af49d1588e378d7593467c1","observation_id":"37b46f08-d132-46b0-8e48-a78c8aec3e87","resolution":{"observed_at":"2026-08-10T14:00:50.257437Z","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":"2026-08-10T14:00:50.792228Z","title":"Distillation as a defense to adversarial perturbations against deep neural networks,","venue":null,"work_id":"1480b45d-2c2e-4efd-8e5c-c8fa93bc67cc","year":2016},"citing_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},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.261004Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:c839669bc924b758d4191df195aa493c99c657339b515bff1ce19829e3abecab","observation_id":"fd0402a1-7e11-4f7b-a23c-2dd08f436c2b","resolution":{"observed_at":"2026-08-10T14:00:50.796033Z","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":"1312.6199","last_updated":"2014-02-19T16:33:14Z","snapshot_observed_at":"2026-07-06T03:31:33.797310Z","submitted_at":"2013-12-21T03:36:08Z","title":"Intriguing properties of neural networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6199","snapshot_observed_at":"2026-08-10T14:00:50.264076Z","title":"Intriguing properties of neural networks,","venue":null,"work_id":null,"year":2013},"citing_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},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.264076Z"},"links":{"cited_paper":"/paper/1312.6199","citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:41f90fad81124aa421404b065d72365c323b0c1a2d6a4bd35bab99524f9a0258","observation_id":"c3f9c0f9-f7c8-4bd7-9055-e0fa5af201b4","resolution":{"observed_at":"2026-08-10T14:00:50.264076Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1607.05113","last_updated":"2016-07-18T14:58:45Z","snapshot_observed_at":"2026-07-06T05:03:58.960419Z","submitted_at":"2016-07-18T14:58:45Z","title":"On the Effectiveness of Defensive Distillation","version":1},"cited_work":{"arxiv_id":"1607.05113","doi":null,"metadata_source":"pith","pith_arxiv_id":"1607.05113","snapshot_observed_at":"2026-08-10T14:00:50.405454Z","title":"On the Effectiveness of Defensive Distillation","venue":"cs.CR","work_id":"2c3795b9-303c-428e-90a2-461de06e5a1e","year":2016},"citing_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},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.267920Z"},"links":{"cited_paper":"/paper/1607.05113","citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:d5fda5120776c6094a577ff11a8d1cf4f9c4deb32cbe95ca99b3cdca42047936","observation_id":"c6e15abd-42ad-492d-8282-248ac4f714b7","resolution":{"observed_at":"2026-08-10T14:00:50.410524Z","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":"2026-08-10T14:00:50.271589Z","title":"Simple and scalable predictive uncertainty estimation using deep ensembles,","venue":null,"work_id":null,"year":2017},"citing_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},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.271589Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:b28d7824f9dc30141aa0d16b652ea6e0a5ef293a4b410293101a321411338ae7","observation_id":"e3143add-3c03-4f24-9d9e-a1b165e4019e","resolution":{"observed_at":"2026-08-10T14:00:50.271589Z","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":"2026-08-10T14:00:50.275116Z","title":"Random search algorithms,","venue":null,"work_id":null,"year":2009},"citing_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},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.275116Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:1a596f17936d20a5367cae9ba6b96d45288675848fce3ab3d640208cd01d9e8a","observation_id":"d49ee672-3ad7-4bb2-abc4-f32fbaf39ed8","resolution":{"observed_at":"2026-08-10T14:00:50.275116Z","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":"2026-08-10T14:00:50.769465Z","title":"Hill-climbing search,","venue":null,"work_id":"45866101-0370-43c3-b29b-a07cb59d0f33","year":2006},"citing_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},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.278740Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:b14252b374783878e7e947ee86144518cc32c47c41f55f4f22b8e6816ebc629f","observation_id":"703eaf92-854e-4d1b-abb9-6f024740e34f","resolution":{"observed_at":"2026-08-10T14:00:50.773081Z","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":"2026-08-10T14:00:50.758385Z","title":"Search-based software engineering,","venue":null,"work_id":"e5dc7e22-ed7a-4588-be26-822be0b5c9f6","year":2001},"citing_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},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.282106Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:ce5ea2d0d69dc18ae8f25ed01b673894c54c404f637e54b82a113b0a8c2887f9","observation_id":"b013fb97-409b-4a21-826c-e83123f207d2","resolution":{"observed_at":"2026-08-10T14:00:50.762311Z","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":"2026-08-10T14:00:50.747037Z","title":"Bfgs optimization for faster and automated supervised learning,","venue":null,"work_id":"e540d7b6-00d6-43ae-a7e1-0f7194dd9aac","year":1990},"citing_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},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.285559Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:3bb283653a5001379a0578f415dc695e78f7f7f32db6bd1dc975543f61fc5b5d","observation_id":"d0aa7cf9-e63d-43a2-9ea1-78a8fe12dff2","resolution":{"observed_at":"2026-08-10T14:00:50.751068Z","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":"2026-08-10T14:00:50.289074Z","title":"The relationship between precision-recall and roc curves,","venue":null,"work_id":null,"year":2006},"citing_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},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.289074Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:771c3b010443ceab953ce6a3f1d2185b0a598f3e954fd402b2bf75176703f542","observation_id":"425669da-7bd6-4977-a38b-0ce9b7466efe","resolution":{"observed_at":"2026-08-10T14:00:50.289074Z","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":"2026-08-10T14:00:50.728814Z","title":"A survey of uncertainty in deep neural networks,","venue":null,"work_id":"8e26b048-0069-4b90-90cd-38564d3e4fd8","year":2023},"citing_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},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.292333Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:b9d42f2aeb9d6ec5ea79908cd82398a26298054293d9b07bda0cc095231b7e5a","observation_id":"5f752f21-6eb0-4b56-b340-5a5a053f5f80","resolution":{"observed_at":"2026-08-10T14:00:50.732816Z","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":"2026-08-10T14:00:50.715884Z","title":"Unveiling code pre-trained models: Investigating syntax and semantics capacities,","venue":null,"work_id":"6c443e73-7ec1-4d32-a1dd-c624cc6ee4f8","year":2024},"citing_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},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.295723Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:352c1fe9f53c20945156a8fef65bdb382a66baac2d116d9514dd6e05ff5a4988","observation_id":"e72f50e3-f8d1-4d68-a547-a42738e35686","resolution":{"observed_at":"2026-08-10T14:00:50.720940Z","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":"2026-08-10T14:00:50.299172Z","title":"Densely connected convolutional networks,","venue":null,"work_id":null,"year":2017},"citing_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},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.299172Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:69f1aaae47c83f0b1f3788b45d7197b7d42454a1e26c77879ff828af0fc037cf","observation_id":"4724fb29-5984-47c5-9467-1b8e060ea10c","resolution":{"observed_at":"2026-08-10T14:00:50.299172Z","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":"2026-08-10T14:00:50.302561Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_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},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.302561Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:8a701d6fd672c3f4c553e3b1a01a57be8c76c4ef23337c1b557b311e6fc917c5","observation_id":"5aae42c6-2870-4b1a-a244-f2fd55dc760d","resolution":{"observed_at":"2026-08-10T14:00:50.302561Z","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":"2026-08-10T14:00:50.689520Z","title":"Codeimprove","venue":null,"work_id":"00d0ddf5-334b-41ef-80db-b5aedb5d68cd","year":null},"citing_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},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.306249Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:e18de0757c500027706680c8e166ac61859273c832c5bea62b3c81b8c68ce6bb","observation_id":"33844fc2-6b71-477c-b52f-c5d6291f4636","resolution":{"observed_at":"2026-08-10T14:00:50.693390Z","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":"2026-08-10T14:00:50.677329Z","title":"Genetic algorithm: Review and application,","venue":null,"work_id":"1e153496-a02d-43e8-92dd-9e2e4c9bdb6b","year":2010},"citing_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},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.309837Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:daf2a1aecdbadc05e73a46a724df225da13a90f81ae44780a6757a5018cb74fe","observation_id":"75b27a77-58dc-4404-b57e-a482a4649aa1","resolution":{"observed_at":"2026-08-10T14:00:50.682067Z","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":"2026-08-10T14:00:50.665822Z","title":"Genetic algorithms,","venue":null,"work_id":"7f5dc15f-55c3-4c65-8009-9a58ead1c055","year":1996},"citing_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},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.313500Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:f39b6e8a33e6cb9cae1128c89c1dbfdbeb7a155ae17af5ffc3196b30cd136006","observation_id":"bef80e8a-7d35-428d-b00e-81c73a403c61","resolution":{"observed_at":"2026-08-10T14:00:50.669624Z","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":"2026-08-10T14:00:50.654742Z","title":"A genetic algorithm tutorial,","venue":null,"work_id":"bf206c16-2e4a-4126-be5e-dae7cef72b4b","year":1994},"citing_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},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.317102Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:fb72f8fc350b661068e6f7ef95616c75768d20ae163643a9043d1ae0358d8c8f","observation_id":"98346d9e-8269-4057-bb1e-5a1e7e6c235a","resolution":{"observed_at":"2026-08-10T14:00:50.658507Z","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":"2026-08-10T14:00:50.642734Z","title":"Devign: Effective vul- nerability identification by learning comprehensive program semantics via graph neural networks,","venue":null,"work_id":"ad86f7cc-5d21-420d-94b0-a2d3d20bc30d","year":2019},"citing_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},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.320715Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:96417a63044f0351879d59589d648758f1c7ea47b28ac345697ce3de976c7928","observation_id":"fe40489a-5ead-48d6-8ad0-fd18eb6ea9be","resolution":{"observed_at":"2026-08-10T14:00:50.647156Z","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":"2026-08-10T14:00:50.324222Z","title":"Convolutional neural networks on assembly code for predicting software defects,","venue":null,"work_id":null,"year":2017},"citing_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},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.324222Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:91d369d6ab7ab49ed27a6e016fd617491ec76b6bd22a1cac29b70e370aaee79f","observation_id":"50a17a54-944f-4211-8125-43b767578f76","resolution":{"observed_at":"2026-08-10T14:00:50.324222Z","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":"2026-08-10T14:00:50.327805Z","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages,","venue":null,"work_id":null,"year":2020},"citing_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},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.327805Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:b19c9f0a66f01667b77264488df13a97f2825b4fa342ab904aed9845e643d7ed","observation_id":"c74c2b34-4f90-43bd-96d3-fe4c081c11e6","resolution":{"observed_at":"2026-08-10T14:00:50.327805Z","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":"2026-08-10T14:00:50.331383Z","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach,","venue":null,"work_id":null,"year":2019},"citing_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},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.331383Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:b49515d1af4745c19bc16034a5e3d28ea51c27098039400978bc82f9c1230f59","observation_id":"32ba7515-3763-4632-bd8c-7653acd23de0","resolution":{"observed_at":"2026-08-10T14:00:50.331383Z","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":"2026-08-10T14:00:50.611235Z","title":"Code difference guided adversarial example generation for deep code models,","venue":null,"work_id":"537537b9-b5d7-44c4-9220-1dfe01f6eeed","year":2023},"citing_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},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.334881Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:85e11710592ecefea4fef42f44354ada806a8a07b50eb62af68a153578a421e5","observation_id":"bbf07bc0-2dee-4247-8c77-0a86ee66f2bc","resolution":{"observed_at":"2026-08-10T14:00:50.615031Z","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":"2026-08-10T14:00:50.598745Z","title":"Natural attack for pre-trained models of code,","venue":null,"work_id":"ea9142e2-67dc-4f10-a8d4-6ac694c1b8de","year":2022},"citing_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},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.338129Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:63daa07a12518e4b56d8e859dc2275fa512cde72e121590ba96ac7f0e007913d","observation_id":"26df8ca8-1851-444b-9abb-ab381d14cf6c","resolution":{"observed_at":"2026-08-10T14:00:50.603663Z","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":"2026-08-10T14:00:50.341452Z","title":"Towards robustness of deep program processing models—detection, estimation, and enhancement,","venue":null,"work_id":null,"year":2022},"citing_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},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.341452Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:400f7617371a5f6602ae6892f5914a9470e43bb856a59fea792c153d09068f4d","observation_id":"0e8d2d9f-1a38-49e5-90e1-0c668ce3eb5c","resolution":{"observed_at":"2026-08-10T14:00:50.341452Z","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":"2026-08-10T14:00:50.587189Z","title":"A twofold siamese network for real-time object tracking,","venue":null,"work_id":"51835948-658f-4084-9fce-af2b937d5234","year":2018},"citing_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},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.345321Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:ad880a2ca6cc610186578b38a419a9e89bdb1638d31eb9f794a3bdaccd9e47af","observation_id":"a857601e-7479-4d96-ab96-980a1d8323dd","resolution":{"observed_at":"2026-08-10T14:00:50.591097Z","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":"2026-08-10T14:00:50.576063Z","title":"Variable kernel density estimation,","venue":null,"work_id":"e72c40fc-91a0-4ba2-b068-1dad4af0b9ba","year":1992},"citing_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},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.348910Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:fef5a0d3063e2e47c2b986aa9e3d124c71159c11550aaaaae3eb325cd87a6be2","observation_id":"f85efb64-7bc0-4d4f-a79b-5c9383b33758","resolution":{"observed_at":"2026-08-10T14:00:50.580203Z","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":"2026-08-10T14:00:50.563543Z","title":"Generating adversarial examples for holding robustness of source code processing models,","venue":null,"work_id":"5b3fc5df-dc3e-4fde-a6a2-80ef230250a1","year":2020},"citing_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},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.352292Z"},"links":{"citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:ab4f4044c02a9f1973a35fa70ac5fcf83453b119a4af94037a4a059f4be05333","observation_id":"f933d134-1063-49ba-b9b0-d11bdc3c2b2f","resolution":{"observed_at":"2026-08-10T14:00:50.568597Z","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":"2103.11882","last_updated":"2021-03-18T10:47:15Z","snapshot_observed_at":"2026-08-09T15:02:45.554875Z","submitted_at":"2021-03-18T10:47:15Z","title":"Generating Adversarial Computer Programs using Optimized Obfuscations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.11882","snapshot_observed_at":"2026-08-10T14:00:50.355841Z","title":"Generating adversarial computer programs using optimized obfuscations,","venue":null,"work_id":null,"year":2021},"citing_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},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-10T14:00:50.355841Z"},"links":{"cited_paper":"/paper/2103.11882","citing_paper":"/paper/2501.15804"},"observation_digest":"sha256:7e41d03bc7b81be34b916d40b4f48d1b4bc573bdcfb9860d1ac78c7645c9c3d7","observation_id":"62190896-04ce-4c8b-b3ce-896e77122e94","resolution":{"observed_at":"2026-08-10T14:00:50.355841Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2501.15804","last_updated":"2025-06-16T20:59:44Z","latest_version":2,"primary_category":"cs.SE","snapshot_observed_at":"2026-08-10T13:53:58.768106Z","submitted_at":"2025-01-27T06:23:37Z","title":"CodeImprove: Program Adaptation for Deep Code Models"},"reference_resolution":{"displayed":58,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":38,"verified_exact":1,"verified_fuzzy":19},"total_outbound_references":58},"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 58 of 58 outbound references and 1 inbound Pith citation observation for arXiv:2501.15804."}