{"as_of":"2026-08-06T03:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6481a01fd6e7a4b4008208de1cdbcb12533964fa61dc6e3c94f5c9e0d738271c","coverage":[{"denominator":31,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":31,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-30T09:39:35.673341Z","state":"measured"},{"denominator":31,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":31,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-05T06:32:48.257954+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/2606.28962/citation-record","integrity":"/paper/2606.28962/integrity","json":"/paper/2606.28962/citation-record.json","paper":"/paper/2606.28962"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T18:26:26.978515Z","title":"Gpt3. int8 (): 8-bit matrix multiplication for transformers at scale,","venue":null,"work_id":"bfaaad97-58ea-4a61-9226-5f90691aa94d","year":2022},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:83f9207ab4f5631938c6c798b08718d67ebb650d1b28e28121c487f1ff5f2d09","observation_id":"1281a2dc-2f0b-4681-b28c-3506010052db","resolution":{"observed_at":"2026-07-09T18:26:26.979810Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.16836","last_updated":"2023-10-25T17:59:32Z","snapshot_observed_at":"2026-07-06T16:38:29.188225Z","submitted_at":"2023-10-25T17:59:32Z","title":"LLM-FP4: 4-Bit Floating-Point Quantized Transformers","version":1},"cited_work":{"arxiv_id":"2310.16836","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.16836","snapshot_observed_at":"2026-07-02T02:06:26.972501Z","title":"Llm-fp4: 4-bit floating-point quantized transformers","venue":null,"work_id":"56000f18-d447-4e3f-88b2-b670d80f0b9a","year":2023},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"cited_paper":"/paper/2310.16836","citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:b465a828c4c9f89a95dfa12a0ce680fc97b9ccd1a98992d866794fe37b941a1f","observation_id":"24bc865a-0128-415d-87f9-e41886342922","resolution":{"observed_at":"2026-06-30T09:44:37.644081Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-07-09T18:26:26.975034Z","title":"Qlora: Efficient finetuning of quantized llms,","venue":null,"work_id":"657c6462-24b9-4e9a-8f6a-9bf81e177534","year":2023},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:2b5a9451608b40d8fc99cfc99652045759f51d56fcafa598975616b9390f57aa","observation_id":"900c2faf-7a30-4f30-a29b-7227edf003bf","resolution":{"observed_at":"2026-07-09T18:26:26.976220Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-07-09T18:26:26.976775Z","title":"Pytorch: An imperative style, high-performance deep learning library,","venue":null,"work_id":"98e3a266-8efa-4508-ab8e-c6f4cb559267","year":2019},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:fa90cbfc4c212f4e98ccbbea449925ee8d5733206aaca103e63be2b3bb121f4f","observation_id":"7abdfcc3-95c9-41c4-8a7c-733d4651512a","resolution":{"observed_at":"2026-07-09T18:26:26.977990Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-07-09T18:26:27.007910Z","title":"Nearest is not dearest: Towards practical defense against quantization-conditioned backdoor attacks,","venue":null,"work_id":"95b1267d-a87f-4d3a-979e-e9ac02cbae3f","year":2024},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:899c9be389c84f5cf1055516f04324040cddc749039bbddd5d6d8fdb159a3428","observation_id":"bc96b441-376c-4e3d-b046-3efdfac02eb2","resolution":{"observed_at":"2026-07-09T18:26:27.009490Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1712.05526","last_updated":"2017-12-15T04:26:26Z","snapshot_observed_at":"2026-07-06T06:14:30.795326Z","submitted_at":"2017-12-15T04:26:26Z","title":"Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning","version":1},"cited_work":{"arxiv_id":"1712.05526","doi":"10.48550/arxiv.1712.05526","metadata_source":"pith","pith_arxiv_id":"1712.05526","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning","venue":"cs.CR","work_id":"bb1fb326-f0f6-4c72-a4d2-eb7f0707b971","year":2017},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"cited_paper":"/paper/1712.05526","citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:1b866067320f067852be7cf72675991e4e63a6e90ef31583718041d0fea70b0b","observation_id":"2e802bac-419e-4f0a-89b9-e825a6f76236","resolution":{"observed_at":"2026-06-30T09:44:37.646550Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-07-09T18:26:27.002461Z","title":"A comprehensive study on quantization techniques for large language models,","venue":null,"work_id":"d06eda60-06eb-45c1-a301-630f828647e9","year":2024},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:8178f15e23a4a460a79d1f059be8461131c41768521d5ce729009f87fd566fa3","observation_id":"4743c9a7-4ce2-4148-9899-4d37719827c7","resolution":{"observed_at":"2026-07-09T18:26:27.003625Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-07-09T18:26:27.005943Z","title":"Contemporary advances in neural network quantization: A survey,","venue":null,"work_id":"496cdc02-968a-405a-973a-319d880bef7e","year":2024},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:81f0499c0df61f24b6a38fe39eaf2335d438ce8bc3019f32e3337e054343be88","observation_id":"2c98d7cc-db9c-463d-b628-0ec49e7c83c5","resolution":{"observed_at":"2026-07-09T18:26:27.007381Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-07-09T18:26:26.999023Z","title":"Optimizing llms using quantization for mobile execution,","venue":null,"work_id":"ef132ab6-a882-4057-a125-89cd9246562c","year":2025},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:5b6ed538252d51c2aec17687a44f4993b94ea10079532949e98ef61a21dfc9af","observation_id":"3f347a48-8286-4266-9bbc-2fdf7ba2bf55","resolution":{"observed_at":"2026-07-09T18:26:27.000241Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2406.05948","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-02T23:47:27.158783Z","title":"Chain-of-scrutiny: Detecting backdoor attacks for large language models","venue":null,"work_id":"2224b69f-184a-4111-adc7-8cc9890617b8","year":2024},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:673aa451d9d0d0ce639f673dae7a9ec9e423261dfc3bc67097cd8ce0a20f4f1b","observation_id":"84d7e334-150b-4781-bdd4-9078d78533ae","resolution":{"observed_at":"2026-06-30T09:44:37.649202Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-07-09T18:26:26.995301Z","title":"Ex- ploring clean label backdoor attacks and defense in language models,","venue":null,"work_id":"ce0a1e14-4697-49c7-9385-2978c69681ef","year":2024},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:8527968a9e3ef15b9c34013536b4fe11be5431f49b3b3224de7d6b4e0e9aca16","observation_id":"95b1d41d-eab0-4f37-9f14-78d4e345e1f1","resolution":{"observed_at":"2026-07-09T18:26:26.996551Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.00761","last_updated":"2025-02-10T18:26:14Z","snapshot_observed_at":"2026-07-06T18:55:45.493755Z","submitted_at":"2024-08-01T17:59:12Z","title":"Tamper-Resistant Safeguards for Open-Weight LLMs","version":4},"cited_work":{"arxiv_id":"2408.00761","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2408.00761","snapshot_observed_at":"2026-07-03T17:58:47.266895Z","title":"Tamper-resistant safeguards for open-weight llms","venue":null,"work_id":"216b3b7b-061c-455e-be7b-a6d707795993","year":2024},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"cited_paper":"/paper/2408.00761","citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:398767f2d7dd353298e4257d6dfc33b57756db726d64ac5b3af4b74233ff661c","observation_id":"0685c087-0354-46ee-85c4-07b18f4a1766","resolution":{"observed_at":"2026-06-30T09:44:37.661358Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-07-09T18:26:26.997070Z","title":"Vaccine: Perturbation-aware alignment for large language model,","venue":null,"work_id":"191a580a-91d4-4324-b666-76bc1128a41f","year":2024},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:f7588f0e88e2eb8d20316ee9177e070052493c2385c3f2b40dbd89c66d9774e7","observation_id":"8823bb95-e51d-437c-96f9-54524f67b6d2","resolution":{"observed_at":"2026-07-09T18:26:26.998444Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-07-09T18:26:26.991970Z","title":"Exploiting llm quantization,","venue":null,"work_id":"35f72413-d60d-46d1-9e5e-a4f9f3cf6f92","year":2024},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:9ec90e211d639ea22b882994a167e76a54e807bc73e29e3a7c808b492be2f393","observation_id":"bc5b1ea4-f2d3-4ae5-a833-f5211039a22d","resolution":{"observed_at":"2026-07-09T18:26:26.993024Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-07-09T18:26:26.993518Z","title":"Understanding the threats of trojaned quantized neural network in model supply chains,","venue":null,"work_id":"4b0c26e3-b7e8-4960-9f02-0762eb4b0646","year":2021},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:15d23c59a16f59896a2a9ec175e2710dfa23ed0553ecb5df339c76178c6493cc","observation_id":"11983d19-e6cc-4ce5-9b23-e48c41e8490b","resolution":{"observed_at":"2026-07-09T18:26:26.994740Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-07-09T18:26:26.982474Z","title":"Qu-anti-zation: Exploiting quantization artifacts for achieving adversarial outcomes,","venue":null,"work_id":"1fe2a50e-a4a3-42ce-a46b-a123f4c9c398","year":2021},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:55e85afe2fa5a48524f2eb98a5a028a2192f5d280d9f2c9b86335c23335f34c4","observation_id":"f5b9f97c-8cf8-4493-a3d5-7a53768de5c4","resolution":{"observed_at":"2026-07-09T18:26:26.983895Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-07-09T18:26:26.984607Z","title":"Stealthy backdoors as compression artifacts,","venue":null,"work_id":"57eb2bf8-047b-436e-ac5a-635ae403902b","year":2022},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:872bf84b7792f51d0eb4e717e9c8e305547dba358509d3f07716e868fc623a71","observation_id":"2a98176e-5d39-4c93-9665-4a7b94f4fb3d","resolution":{"observed_at":"2026-07-09T18:26:26.985850Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-07-09T18:26:26.986416Z","title":"Quantization backdoors to deep learning commercial frameworks,","venue":null,"work_id":"38b79683-0aec-4ba6-ae77-ee0653b00379","year":2023},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:66bb07d51dfd135b3c2da4476f3d0225d7a519e82883ed09c4f6573a3e37f2ed","observation_id":"94228f8f-de66-4c7d-8fc1-f5ef6a1c59b2","resolution":{"observed_at":"2026-07-09T18:26:26.987613Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-07-09T18:26:26.988165Z","title":"Hugging face–the ai community building the future,","venue":null,"work_id":"62b3e5f1-4b9b-4386-9106-0b3c1064a94f","year":2024},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:6faabb8f06f45be542e6367a8ccdbc787d5840ae4642c54e4398370d98d70f35","observation_id":"05eeea3e-bcb4-4afb-8071-d76fad200cc0","resolution":{"observed_at":"2026-07-09T18:26:26.989302Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.12186","last_updated":"2024-11-12T13:24:25Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-09-18T17:57:57Z","title":"Qwen2.5-Coder Technical Report","version":3},"cited_work":{"arxiv_id":"2409.12186","doi":"10.48550/arxiv.2409.12186","metadata_source":"pith","pith_arxiv_id":"2409.12186","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Qwen2.5-Coder Technical Report","venue":"cs.CL","work_id":"09ba463d-6377-4017-9801-444ffb94b056","year":2024},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"cited_paper":"/paper/2409.12186","citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:29926fc0bf206982e148309a36d4789f88b172260e23bb15ce66999db4a7783b","observation_id":"29428506-565b-4271-abbb-0efc400d2690","resolution":{"observed_at":"2026-06-30T09:44:37.665962Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-07-11T05:18:55.772185+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T05:18:55.772185+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.06161","last_updated":"2023-12-13T14:44:10Z","snapshot_observed_at":"2026-07-06T15:25:35.930688Z","submitted_at":"2023-05-09T08:16:42Z","title":"StarCoder: may the source be with you!","version":2},"cited_work":{"arxiv_id":"2305.06161","doi":"10.48550/arxiv.2305.06161","metadata_source":"pith","pith_arxiv_id":"2305.06161","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"StarCoder: may the source be with you!","venue":"cs.CL","work_id":"7e9c3d6e-d6f7-4763-9ef6-de471506c58f","year":2023},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"cited_paper":"/paper/2305.06161","citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:77d6f1caec1b8c0bd1e8034148e52200823da97f6e0219e8b67ed0e1e096b337","observation_id":"c161d47b-6d5a-4fc0-9a85-5470138308c2","resolution":{"observed_at":"2026-06-30T09:44:37.636146Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-07-09T18:26:26.984822Z","title":"Phi-2: The surprising power of small language models,","venue":null,"work_id":"bc0659df-e354-4933-bcce-c7866bd55298","year":2023},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:2cba4071dcbd1f556c2656c4470e6d91275f60232c47ad6ba0e8e28e535adaa2","observation_id":"061d821a-a4b8-4fd4-a0ef-37d86c0137a9","resolution":{"observed_at":"2026-07-09T18:26:26.986628Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.08295","last_updated":"2024-04-16T12:52:47Z","snapshot_observed_at":"2026-08-03T03:29:01.959523Z","submitted_at":"2024-03-13T06:59:16Z","title":"Gemma: Open Models Based on Gemini Research and Technology","version":4},"cited_work":{"arxiv_id":"2403.08295","doi":"10.48550/arxiv.2403.08295","metadata_source":"pith","pith_arxiv_id":"2403.08295","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Gemma: Open Models Based on Gemini Research and Technology","venue":"cs.CL","work_id":"a9ea2870-df28-40b8-a9e0-a7e9a116f793","year":2024},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"cited_paper":"/paper/2403.08295","citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:6f47ad818dc415fa7ba56090cf3c7b6a802e73e73a933dc8b1a0db117a8b25b1","observation_id":"3afd703d-45f9-4454-9029-b0c4174d0d69","resolution":{"observed_at":"2026-06-30T09:44:37.639134Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-07-09T18:26:26.992234Z","title":"Large language models for code: Security hardening and adversarial testing,","venue":null,"work_id":"39bd3d2f-d4eb-45b3-b5b3-cefaf572c234","year":2023},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:7e9e210c447c76b1a48670d0e5987a9ff38d5a30484fd8a41dc3a9cd5160ed78","observation_id":"62899024-f307-4e23-bf02-21dadc0c3de1","resolution":{"observed_at":"2026-07-09T18:26:26.993741Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-07-09T18:26:27.000838Z","title":"On the exploitability of instruction tuning,","venue":null,"work_id":"04107cea-8837-4c10-adeb-0a7e1faf2695","year":2023},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:a2d894ccb7bfd192d211c8d0435516c71c81c163722bce95fa33ff17c669d60c","observation_id":"6e155315-3940-4eee-948b-48399112e9d2","resolution":{"observed_at":"2026-07-09T18:26:27.001896Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-07-09T18:26:27.004199Z","title":"Training language models to follow instructions with human feedback,","venue":null,"work_id":"f25043af-e6ff-4a6d-85e9-684ceb525379","year":2022},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:18aa231931e48cdc5ff4c0afe0e27d8704447ce9a6e72bc051bcdf72e173ab27","observation_id":"9564006c-ca0c-4c86-9442-3ebff066ffcf","resolution":{"observed_at":"2026-07-09T18:26:27.005369Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.07958","last_updated":"2022-05-08T02:43:02Z","snapshot_observed_at":"2026-08-03T16:26:48.747700Z","submitted_at":"2021-09-08T17:15:27Z","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","version":2},"cited_work":{"arxiv_id":"2109.07958","doi":"10.48550/arxiv.2109.07958","metadata_source":"pith","pith_arxiv_id":"2109.07958","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","venue":"cs.CL","work_id":"22e3b047-a6e8-4c4c-b62e-173b545a1a45","year":2021},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"cited_paper":"/paper/2109.07958","citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:928793c79735e8ea878da86ea7efc8f372187d417fcc724caac8ecb813218045","observation_id":"f79b1601-799f-4c58-94dd-ca14b448f5c5","resolution":{"observed_at":"2026-06-30T09:44:37.641457Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-07-18T08:21:09.956602+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-18T08:21:09.956602+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2009.03300","last_updated":"2021-01-12T18:57:11Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-09-07T17:59:25Z","title":"Measuring Massive Multitask Language Understanding","version":3},"cited_work":{"arxiv_id":"2009.03300","doi":"10.48550/arxiv.2009.03300","metadata_source":"pith","pith_arxiv_id":"2009.03300","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Measuring Massive Multitask Language Understanding","venue":"cs.CY","work_id":"e87ec49a-544b-4ec8-8991-75298c64ff5e","year":2020},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"cited_paper":"/paper/2009.03300","citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:6da97a99e488905ced3023b4c561280fa8a69981be6b807f32e7c051bcdbe0f1","observation_id":"75cab7d1-8689-4cb2-ab6c-0e7f8c70a090","resolution":{"observed_at":"2026-06-30T09:44:37.663662Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-04T01:08:06.256034+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-04T01:08:06.256034+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2107.03374","last_updated":"2021-07-14T17:16:02Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2021-07-07T17:41:24Z","title":"Evaluating Large Language Models Trained on Code","version":2},"cited_work":{"arxiv_id":"2107.03374","doi":"10.48550/arxiv.2107.03374","metadata_source":"pith","pith_arxiv_id":"2107.03374","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Evaluating Large Language Models Trained on Code","venue":"cs.LG","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","year":2021},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"cited_paper":"/paper/2107.03374","citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:7a1eab014c07862a134d61377dd148c472c84f7e3290d3b83c09220cf4a0312e","observation_id":"9d431991-c891-4e12-94d6-9b0af69e0bb0","resolution":{"observed_at":"2026-06-30T09:44:37.658814Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-01T08:08:23.404839+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-01T08:08:23.404839+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2108.07732","last_updated":"2021-08-16T03:57:30Z","snapshot_observed_at":"2026-08-02T19:23:53.535075Z","submitted_at":"2021-08-16T03:57:30Z","title":"Program Synthesis with Large Language Models","version":1},"cited_work":{"arxiv_id":"2108.07732","doi":"10.1007/s11390-025-5518-5","metadata_source":"pith","pith_arxiv_id":"2108.07732","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Program Synthesis with Large Language Models","venue":"cs.PL","work_id":"fd241a05-03b9-4de2-9588-9d77ce176125","year":2021},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"cited_paper":"/paper/2108.07732","citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:b42f40cacbe702ea76a1c3993e52ca8e1eb5c9eb6a57b32effe0322648485c06","observation_id":"5604e195-9b28-4d59-8bb6-478920755c4c","resolution":{"observed_at":"2026-06-30T09:44:37.656177Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-27T04:03:16Z","title":"DeepSeek-V3 Technical Report","version":2},"cited_work":{"arxiv_id":"2412.19437","doi":"10.1016/j.neucom.2023.127063.url:https://www.sciencedirect","metadata_source":"pith","pith_arxiv_id":"2412.19437","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"DeepSeek-V3 Technical Report","venue":"cs.CL","work_id":"57d2791d-2219-4c31-a077-afc04b12a75c","year":2024},"citing_paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-06-30T09:39:35.673341Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2606.28962"},"observation_digest":"sha256:fe7faa558c7857349751bf314ce0069fea34798d0eae176dee6ec1a2850d7440","observation_id":"e6ad26a2-4a95-4594-a9d2-6436636e68cd","resolution":{"observed_at":"2026-06-30T09:44:37.651410Z","resolver_source":"local_arxiv","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2606.28962","last_updated":"2026-06-27T15:02:42Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-02T00:20:36.781197Z","submitted_at":"2026-06-27T15:02:42Z","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks"},"reference_resolution":{"displayed":31,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":11,"verified_fuzzy":19},"total_outbound_references":31},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 6 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 0 inbound Pith citation observations for arXiv:2606.28962."}