{"as_of":"2026-08-15T13:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9365e9baf931e3227d310cad07d0d2154a34d69496a01bf13b6381741e2cf4f2","coverage":[{"denominator":12,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":12,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T17:38:24.890195Z","state":"measured"},{"denominator":12,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":12,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+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/2509.10790/citation-record","integrity":"/paper/2509.10790/integrity","json":"/paper/2509.10790/citation-record.json","paper":"/paper/2509.10790"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T17:38:24.210305Z","title":"Golden- eye: A platform for evaluating emerging numerical data formats in dnn accelerators,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.10790","last_updated":"2025-09-13T02:52:08Z","snapshot_observed_at":"2026-08-13T16:46:54.993743Z","submitted_at":"2025-09-13T02:52:08Z","title":"GoldenTransformer: A Modular Fault Injection Framework for Transformer Robustness Research","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-04T17:38:24.210305Z"},"links":{"citing_paper":"/paper/2509.10790"},"observation_digest":"sha256:a64e159d54b284fe4023d52fd204ca3ab0227b120532837e204ae9e55e6fbfcd","observation_id":"e89d8a8c-c2d8-4198-ac24-e725877ae245","resolution":{"observed_at":"2026-08-04T17:38:24.210305Z","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":"2026-08-04T17:38:24.252083Z","title":"Understanding error propagation in deep learning neural network (dnn) accelerators and applications,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.10790","last_updated":"2025-09-13T02:52:08Z","snapshot_observed_at":"2026-08-13T16:46:54.993743Z","submitted_at":"2025-09-13T02:52:08Z","title":"GoldenTransformer: A Modular Fault Injection Framework for Transformer Robustness Research","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-04T17:38:24.252083Z"},"links":{"citing_paper":"/paper/2509.10790"},"observation_digest":"sha256:02c985e2004763f3e1567c4fc7149a77387612546b516f2c6a47296ef3844a7a","observation_id":"9e90a888-f410-4fac-8086-f2dd4e049f6d","resolution":{"observed_at":"2026-08-04T17:38:24.252083Z","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":"2026-08-04T17:38:24.322995Z","title":"Tensorfi: A flexible fault injection framework for ten- sorflow applications,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.10790","last_updated":"2025-09-13T02:52:08Z","snapshot_observed_at":"2026-08-13T16:46:54.993743Z","submitted_at":"2025-09-13T02:52:08Z","title":"GoldenTransformer: A Modular Fault Injection Framework for Transformer Robustness Research","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-04T17:38:24.322995Z"},"links":{"citing_paper":"/paper/2509.10790"},"observation_digest":"sha256:7767e89e200eb0870109ffeb573cf49e9405921487cde8d600f4dbe75ca1081b","observation_id":"2b7e1192-6f34-4097-b534-78eb61041a37","resolution":{"observed_at":"2026-08-04T17:38:24.322995Z","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":"2026-08-04T17:38:24.371320Z","title":"Tensorfi: A configurable fault injector for tensorflow applications,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.10790","last_updated":"2025-09-13T02:52:08Z","snapshot_observed_at":"2026-08-13T16:46:54.993743Z","submitted_at":"2025-09-13T02:52:08Z","title":"GoldenTransformer: A Modular Fault Injection Framework for Transformer Robustness Research","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-04T17:38:24.371320Z"},"links":{"citing_paper":"/paper/2509.10790"},"observation_digest":"sha256:8d7c50d0bc31a7e6ea0a2839db124367996a7e043f641c38f722bbfd025894fe","observation_id":"d72f146e-41f8-42b7-9d3d-89dc14b93055","resolution":{"observed_at":"2026-08-04T17:38:24.371320Z","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":"2026-08-04T17:38:24.424175Z","title":"Fault injection for tensorflow applications,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.10790","last_updated":"2025-09-13T02:52:08Z","snapshot_observed_at":"2026-08-13T16:46:54.993743Z","submitted_at":"2025-09-13T02:52:08Z","title":"GoldenTransformer: A Modular Fault Injection Framework for Transformer Robustness Research","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-04T17:38:24.424175Z"},"links":{"citing_paper":"/paper/2509.10790"},"observation_digest":"sha256:95bae767d23a4de067e8ae5ad4e28c140a6e1e8376dba4efb3886d272e87fd6b","observation_id":"b7379194-27ea-4d53-994b-204f03a3c70e","resolution":{"observed_at":"2026-08-04T17:38:24.424175Z","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":"2026-08-04T17:38:24.471942Z","title":"Pytorchfi: A runtime perturbation tool for dnns,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.10790","last_updated":"2025-09-13T02:52:08Z","snapshot_observed_at":"2026-08-13T16:46:54.993743Z","submitted_at":"2025-09-13T02:52:08Z","title":"GoldenTransformer: A Modular Fault Injection Framework for Transformer Robustness Research","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-04T17:38:24.471942Z"},"links":{"citing_paper":"/paper/2509.10790"},"observation_digest":"sha256:32164b014ab2e9418863a8d8efd62e39f17b7060bd9c8a39bb3091609f9fbc6f","observation_id":"72a808e8-9d48-4fdd-8d11-da6f25613cb8","resolution":{"observed_at":"2026-08-04T17:38:24.471942Z","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":"2026-08-04T17:38:24.492554Z","title":"Binfi: an efficient fault injector for safety-critical machine learning systems,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.10790","last_updated":"2025-09-13T02:52:08Z","snapshot_observed_at":"2026-08-13T16:46:54.993743Z","submitted_at":"2025-09-13T02:52:08Z","title":"GoldenTransformer: A Modular Fault Injection Framework for Transformer Robustness Research","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-04T17:38:24.492554Z"},"links":{"citing_paper":"/paper/2509.10790"},"observation_digest":"sha256:e7d8160987a42f0e3b9971dc908e430ce98559d155e17b81a24e1999f9e7463a","observation_id":"02f21f48-232f-4dd4-a10d-d1eb4ab0975a","resolution":{"observed_at":"2026-08-04T17:38:24.492554Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-15T13:16:30.209244Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-08-04T17:38:24.527887Z","title":"Textattack: A framework for adversarial attacks in natural language processing,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2509.10790","last_updated":"2025-09-13T02:52:08Z","snapshot_observed_at":"2026-08-13T16:46:54.993743Z","submitted_at":"2025-09-13T02:52:08Z","title":"GoldenTransformer: A Modular Fault Injection Framework for Transformer Robustness Research","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-04T17:38:24.527887Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2509.10790"},"observation_digest":"sha256:35d1f864192e9d754420282a732f5bd05654401cfcd09d6260f6fc7d02b10e75","observation_id":"f7e92ad1-029a-45d4-b334-2615d2261f15","resolution":{"observed_at":"2026-08-04T17:38:24.527887Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.01128","last_updated":"2020-04-20T19:59:25Z","snapshot_observed_at":"2026-08-14T19:40:02.255526Z","submitted_at":"2018-03-03T08:51:00Z","title":"Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.01128","snapshot_observed_at":"2026-08-04T17:38:24.621259Z","title":"Seq2sick: Evaluating the robustness of sequence-to-sequence models with adversarial examples,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.10790","last_updated":"2025-09-13T02:52:08Z","snapshot_observed_at":"2026-08-13T16:46:54.993743Z","submitted_at":"2025-09-13T02:52:08Z","title":"GoldenTransformer: A Modular Fault Injection Framework for Transformer Robustness Research","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T17:38:24.621259Z"},"links":{"cited_paper":"/paper/1803.01128","citing_paper":"/paper/2509.10790"},"observation_digest":"sha256:b2d428d8b89dac66851e9cae51158dbb6041e26f0b7bb179b51b62aa18922ff1","observation_id":"c5fa965e-e20f-417d-9c15-285216b03b0f","resolution":{"observed_at":"2026-08-04T17:38:24.621259Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.06620","last_updated":"2019-03-19T01:37:05Z","snapshot_observed_at":"2026-08-14T17:01:39.293615Z","submitted_at":"2019-03-15T16:04:11Z","title":"On Evaluation of Adversarial Perturbations for Sequence-to-Sequence Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.06620","snapshot_observed_at":"2026-08-04T17:38:24.722895Z","title":"On evaluation of adversarial perturbations for sequence-to-sequence models,","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2509.10790","last_updated":"2025-09-13T02:52:08Z","snapshot_observed_at":"2026-08-13T16:46:54.993743Z","submitted_at":"2025-09-13T02:52:08Z","title":"GoldenTransformer: A Modular Fault Injection Framework for Transformer Robustness Research","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-04T17:38:24.722895Z"},"links":{"cited_paper":"/paper/1903.06620","citing_paper":"/paper/2509.10790"},"observation_digest":"sha256:b02a8a56f98654182466e4066ccc229b9e2284220cf643eb2ccdb3d45b710d86","observation_id":"e58d185b-2f6c-470a-88fd-a1f506d52481","resolution":{"observed_at":"2026-08-04T17:38:24.722895Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.04451","last_updated":"2024-03-20T21:34:56Z","snapshot_observed_at":"2026-08-06T02:57:30.438059Z","submitted_at":"2023-10-03T19:44:37Z","title":"AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.04451","snapshot_observed_at":"2026-08-04T17:38:24.816451Z","title":"Autodan: Generating stealthy jailbreak prompts on aligned large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10790","last_updated":"2025-09-13T02:52:08Z","snapshot_observed_at":"2026-08-13T16:46:54.993743Z","submitted_at":"2025-09-13T02:52:08Z","title":"GoldenTransformer: A Modular Fault Injection Framework for Transformer Robustness Research","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-04T17:38:24.816451Z"},"links":{"cited_paper":"/paper/2310.04451","citing_paper":"/paper/2509.10790"},"observation_digest":"sha256:8656d5cb946be7050e241a939a2c5a1a47ebfa8e6a26a9e19a1fe21f1feb1820","observation_id":"d3dbdeeb-a240-4208-91d1-cfce273b7938","resolution":{"observed_at":"2026-08-04T17:38:24.816451Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.01703","last_updated":"2019-12-03T22:06:05Z","snapshot_observed_at":"2026-07-06T08:41:49.632205Z","submitted_at":"2019-12-03T22:06:05Z","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.01703","snapshot_observed_at":"2026-08-04T17:38:24.890195Z","title":"Pytorch: An imperative style, high- performance deep learning library,","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2509.10790","last_updated":"2025-09-13T02:52:08Z","snapshot_observed_at":"2026-08-13T16:46:54.993743Z","submitted_at":"2025-09-13T02:52:08Z","title":"GoldenTransformer: A Modular Fault Injection Framework for Transformer Robustness Research","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-04T17:38:24.890195Z"},"links":{"cited_paper":"/paper/1912.01703","citing_paper":"/paper/2509.10790"},"observation_digest":"sha256:cd02269d1911859904e6b9384270504b2f5f8faa2382deb3c10a40b377bea440","observation_id":"a9a73c7e-38df-41dc-b61e-8c4c0cb7b544","resolution":{"observed_at":"2026-08-04T17:38:24.890195Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2509.10790","last_updated":"2025-09-13T02:52:08Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T16:46:54.993743Z","submitted_at":"2025-09-13T02:52:08Z","title":"GoldenTransformer: A Modular Fault Injection Framework for Transformer Robustness Research"},"reference_resolution":{"displayed":12,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":12,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":12},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 0 inbound Pith citation observations for arXiv:2509.10790."}