{"as_of":"2026-08-19T19:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1f756e8ffdac511066517d69d66b33d00581af3b8ead51cc8b132cf992dd3583","coverage":[{"denominator":41,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":41,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T00:24:40.832777Z","state":"measured"},{"denominator":41,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":41,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+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/2608.11981/citation-record","integrity":"/paper/2608.11981/integrity","json":"/paper/2608.11981/citation-record.json","paper":"/paper/2608.11981"},"outbound":[{"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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.08295","snapshot_observed_at":"2026-08-16T00:24:40.704840Z","title":"Gemma: Open models based on gemini research and technology,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.704840Z"},"links":{"cited_paper":"/paper/2403.08295","citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:cecbc5e57ef530cda38ca029a770fb1f5542bcfb4ee5fc382a6667d051d131fd","observation_id":"996f3c81-a66c-44d5-9eb3-b2a7ac3ea939","resolution":{"observed_at":"2026-08-16T00:24:40.704840Z","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":"2026-08-16T00:24:40.708998Z","title":"Qwen2.5: A party of foundation models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.708998Z"},"links":{"citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:38adde6e6a41caa21208580537167948096fb64c07a861e9137352336a268057","observation_id":"42e1cbfd-06b9-4eaa-8011-d706db8ff5dc","resolution":{"observed_at":"2026-08-16T00:24:40.708998Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-08-13T17:20:44.002518Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-16T00:24:40.712538Z","title":"The llama 3 herd of models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.712538Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:6cb08b4aaabfc2a30e42ed3d85b3871072e65b33ff42b56dc03d054edf9cc18a","observation_id":"eb10f292-97d4-4b41-988a-e25e95081b7d","resolution":{"observed_at":"2026-08-16T00:24:40.712538Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.16840","last_updated":"2024-02-26T18:59:03Z","snapshot_observed_at":"2026-08-16T14:15:11.211927Z","submitted_at":"2024-02-26T18:59:03Z","title":"MobiLlama: Towards Accurate and Lightweight Fully Transparent GPT","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.16840","snapshot_observed_at":"2026-08-16T00:24:40.715893Z","title":"Mobillama: Towards accurate and lightweight fully transparent gpt,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.715893Z"},"links":{"cited_paper":"/paper/2402.16840","citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:15bd08178eb57ea06ee54462c476f86df0f274d8826b803c93e45ca35342a710","observation_id":"840642d8-66d2-4f18-ada8-28ee4a943cbc","resolution":{"observed_at":"2026-08-16T00:24:40.715893Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.02737","last_updated":"2025-02-04T21:43:16Z","snapshot_observed_at":"2026-08-14T05:03:05.661970Z","submitted_at":"2025-02-04T21:43:16Z","title":"SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.02737","snapshot_observed_at":"2026-08-16T00:24:40.719522Z","title":"Smollm2: When smol goes big–data-centric training of a small language model,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.719522Z"},"links":{"cited_paper":"/paper/2502.02737","citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:ffcb81795c6fbff6e123502873d8b3c7af4519553fa1c94bb22aafc47fc7f5ae","observation_id":"4376ef94-bcff-4915-b4c9-afb95a4665b7","resolution":{"observed_at":"2026-08-16T00:24:40.719522Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.17323","last_updated":"2023-03-22T13:10:47Z","snapshot_observed_at":"2026-08-16T07:57:19.216626Z","submitted_at":"2022-10-31T13:42:40Z","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.17323","snapshot_observed_at":"2026-08-16T00:24:40.722671Z","title":"Gptq: Accurate post-training quantization for generative pre-trained transformers,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.722671Z"},"links":{"cited_paper":"/paper/2210.17323","citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:2cf8f6ee8bb45172fddc74a1e6b8e2df56c6964191a33d14da7a1d39ba3b337c","observation_id":"1ece8eac-4fb5-405f-9493-dfd707861406","resolution":{"observed_at":"2026-08-16T00:24:40.722671Z","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":"2026-08-16T00:24:41.340527Z","title":"Sparsegpt: Massive language models can be accurately pruned in one-shot,","venue":null,"work_id":"bda46cf8-e719-4c28-a3e9-2dbfb777f722","year":2023},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.725968Z"},"links":{"citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:72ed8ee23022550545a54d7540ae5a8f208bc4c17e2cfb288603329a44c6c08b","observation_id":"0c039701-c7d5-4692-92be-810513662715","resolution":{"observed_at":"2026-08-16T00:24:41.343531Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.00978","last_updated":"2026-04-25T06:58:16Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-06-01T17:59:10Z","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.00978","snapshot_observed_at":"2026-08-16T00:24:40.728965Z","title":"Awq: Activation-aware weight quantization for llm compression and acceleration,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.728965Z"},"links":{"cited_paper":"/paper/2306.00978","citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:eca627ecc68024c3fd0df1578f16f78ad58f05907b0112a83256286319348cd5","observation_id":"0fb52a45-dea0-4672-a605-a56307989b8f","resolution":{"observed_at":"2026-08-16T00:24:40.728965Z","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":"2026-08-16T00:24:41.332748Z","title":"Duquant: Distributing outliers via dual transformation makes stronger quantized llms,","venue":null,"work_id":"a65fa2cb-b917-437d-ba13-cedc6865c910","year":2024},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.732945Z"},"links":{"citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:a327f5c1041da600f7ce1a4ed4071ed001885df2a5e94f1e00ff500064d26d8c","observation_id":"bfc97b4d-126a-4c1a-9a37-2da1d44f0fd6","resolution":{"observed_at":"2026-08-16T00:24:41.335532Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T00:24:41.324771Z","title":"Efficient diffusion language models: A comprehensive survey,","venue":null,"work_id":"4e83ee65-0387-4ecb-a645-22c647e01143","year":2026},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.736064Z"},"links":{"citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:b8584090aaa1161ad53023c59bb414a8b3f4e8529ab7c363c9be1d0a1b5b9f67","observation_id":"f5437e1a-72bd-4531-872b-5e9c32a9c5ef","resolution":{"observed_at":"2026-08-16T00:24:41.327650Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T00:24:41.316859Z","title":"A survey on evaluation of large language models,","venue":null,"work_id":"29a81637-e7a6-4891-a144-d1fb69f932de","year":2024},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.739033Z"},"links":{"citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:ed4ce575476dbac141f548e8f09d59b141138ddea9e2e0560df154bb61b0bdc4","observation_id":"ebc921d9-2e80-4d4f-a8a8-32b62993ea85","resolution":{"observed_at":"2026-08-16T00:24:41.319607Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.05561","last_updated":"2024-09-30T10:17:12Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-01-10T22:07:21Z","title":"TrustLLM: Trustworthiness in Large Language Models","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.05561","snapshot_observed_at":"2026-08-16T00:24:40.742845Z","title":"Trustllm: Trustworthiness in large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.742845Z"},"links":{"cited_paper":"/paper/2401.05561","citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:afd32e60b07383daafdeec421fffc471f042891cefedfbd3dbb8b9484ce1f389","observation_id":"b1f14345-00ac-4345-b74e-4cf8f25ab721","resolution":{"observed_at":"2026-08-16T00:24:40.742845Z","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":"2026-08-16T00:24:41.308094Z","title":"Promptbench: Towards evaluating the robustness of large language models on adversarial prompts,","venue":null,"work_id":"c5528a38-6790-4808-82f7-af75f3864d55","year":2023},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.746530Z"},"links":{"citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:01926faa8bd88e32ec27364c954707ae1d1688ee9ed7f38d79d2adb55ba1796e","observation_id":"57c6f41e-43d3-4a65-afe7-f7e6d991286b","resolution":{"observed_at":"2026-08-16T00:24:41.311147Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T00:24:41.299809Z","title":"Security and privacy challenges of large language models: A survey,","venue":null,"work_id":"e6237696-e4ef-4823-8719-ec478d201544","year":2025},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.749502Z"},"links":{"citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:0a13876a824e12cfd28a33343496b521d1ddf314331911e5979dc3a25310bd1c","observation_id":"4410c254-18b6-4cd3-90cd-d7797d68f880","resolution":{"observed_at":"2026-08-16T00:24:41.302791Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T00:24:41.291468Z","title":"Exploiting llm quantization,","venue":null,"work_id":"080af40a-ced8-4e59-981f-e195259135d9","year":2024},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.752664Z"},"links":{"citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:fb7430ace181e18bbd56a40c73d3e02446810352e4f8ad150fb4ac9b516ea636","observation_id":"6ecdc64b-48cf-458e-814a-6a180f4fda31","resolution":{"observed_at":"2026-08-16T00:24:41.294604Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.15447","last_updated":"2024-06-04T05:40:12Z","snapshot_observed_at":"2026-08-19T11:10:04.929335Z","submitted_at":"2024-03-18T01:38:19Z","title":"Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.15447","snapshot_observed_at":"2026-08-16T00:24:40.755344Z","title":"Decoding compressed trust: Scrutinizing the trustworthiness of efficient llms under compression,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.755344Z"},"links":{"cited_paper":"/paper/2403.15447","citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:928aeb944ad97206ea207f71b3931df895ef1671fdc1f3c438d85dbf62b393e7","observation_id":"e6c15563-ff5f-4e54-8cfe-a0498eb58b36","resolution":{"observed_at":"2026-08-16T00:24:40.755344Z","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":"2026-08-16T00:24:41.282539Z","title":"Assessing safety risks and quantization-aware safety patching for quantized large language models,","venue":null,"work_id":"69256313-9cc4-4e7f-8a3e-c23d425904be","year":null},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.758279Z"},"links":{"citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:495574f4f5d50d83b34a22e52f9a54910b23138f1b1ba7bac744c3684b5b643a","observation_id":"20938df4-6f9f-40fa-abe7-d9dc1c4f0ceb","resolution":{"observed_at":"2026-08-16T00:24:41.285618Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1510.00149","last_updated":"2016-02-15T06:25:40Z","snapshot_observed_at":"2026-08-04T16:59:47.843960Z","submitted_at":"2015-10-01T09:03:44Z","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1510.00149","snapshot_observed_at":"2026-08-16T00:24:40.761557Z","title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.761557Z"},"links":{"cited_paper":"/paper/1510.00149","citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:55e8bd5af4ed52b9af575efe41a9922cc505122cb06dc0830bcedaedf620d2fc","observation_id":"1f1f1198-4630-4bec-8b49-b0ca3707da10","resolution":{"observed_at":"2026-08-16T00:24:40.761557Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.06663","last_updated":"2025-02-11T19:01:39Z","snapshot_observed_at":"2026-08-19T01:12:28.922658Z","submitted_at":"2025-02-10T16:51:03Z","title":"EfficientLLM: Scalable Pruning-Aware Pretraining for Architecture-Agnostic Edge Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.06663","snapshot_observed_at":"2026-08-16T00:24:40.764764Z","title":"Efficientllm: Scalable pruning-aware pretraining for architecture-agnostic edge lan- guage models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.764764Z"},"links":{"cited_paper":"/paper/2502.06663","citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:a032034edc03ba05a638d814d21ccf5bb2f3b44bb89e9a383ca31e77d7debe69","observation_id":"2c6ca2c5-3e96-4635-bada-776f76dcfd1f","resolution":{"observed_at":"2026-08-16T00:24:40.764764Z","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":"2026-08-16T00:24:40.767671Z","title":"Prune as you generate: Online rollout pruning for faster and better rlvr,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.767671Z"},"links":{"citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:aa0e7e3ecf600f06834b4c30a7bc822dea5e062e4b2fd284a1547880190146e3","observation_id":"c0c72600-a175-41cd-8054-6783bd53c7d9","resolution":{"observed_at":"2026-08-16T00:24:40.767671Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.11695","last_updated":"2024-05-06T17:47:01Z","snapshot_observed_at":"2026-08-13T04:32:33.562415Z","submitted_at":"2023-06-20T17:18:20Z","title":"A Simple and Effective Pruning Approach for Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.11695","snapshot_observed_at":"2026-08-16T00:24:40.770847Z","title":"A simple and effective pruning approach for large language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.770847Z"},"links":{"cited_paper":"/paper/2306.11695","citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:ce28e3b4bb2b3f5817289330fc36ebbb423a60ae46be14db5186f17d90749381","observation_id":"f5c14214-7637-46dc-b371-22b82b6c7072","resolution":{"observed_at":"2026-08-16T00:24:40.770847Z","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":"2026-08-16T00:24:41.273710Z","title":"Llm-pruner: On the structural pruning of large language models,","venue":null,"work_id":"f588191f-fc58-4bf8-b982-e1625bad672d","year":2023},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.773852Z"},"links":{"citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:dfb2e65ae823a017fea86d125f88a65bd8b80bfff6fc2efcf8df41ceeab39ee8","observation_id":"44a5437d-e3d0-408d-8039-61d624705eea","resolution":{"observed_at":"2026-08-16T00:24:41.276788Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.03291","last_updated":"2026-07-28T09:18:13Z","snapshot_observed_at":"2026-08-17T21:10:12.937223Z","submitted_at":"2024-08-06T16:40:04Z","title":"DopQ-ViT: Towards Distribution-Friendly and Outlier-Aware Post-Training Quantization for Vision Transformers","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.03291","snapshot_observed_at":"2026-08-16T00:24:40.776539Z","title":"Dopq-vit: Towards distribution-friendly and outlier- aware post-training quantization for vision transformers,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.776539Z"},"links":{"cited_paper":"/paper/2408.03291","citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:30fa3a1e79b17eb7ae0b0ad40d347f08acba2d43fcb478c37cd18169a8472cc4","observation_id":"2c3d1bbf-3f9f-4301-b33e-0320d3a6cc69","resolution":{"observed_at":"2026-08-16T00:24:40.776539Z","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":"2026-08-16T00:24:40.779686Z","title":"Quantization meets dllms: A systematic study of post-training quantization for diffusion llms,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.779686Z"},"links":{"citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:2a24b76de61c84fefe348206398b829084a3aaeedabcdc71bd123b6732f51915","observation_id":"96ca50dd-cb9c-4fa7-be3f-fb19a0f5bcb7","resolution":{"observed_at":"2026-08-16T00:24:40.779686Z","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":"2026-08-16T00:24:40.782664Z","title":"Lrq-dit: Log-rotation post-training quantization of diffusion transformers for image and video generation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.782664Z"},"links":{"citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:b306a4bf76652e4b7f0e29470ec79eb64e73951bd7bc06f706ce2ff3d06d4b5e","observation_id":"6058288c-7f74-44a1-a0e7-d524360322d9","resolution":{"observed_at":"2026-08-16T00:24:40.782664Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2602.20309","last_updated":"2026-04-06T23:32:59Z","snapshot_observed_at":"2026-08-11T03:24:57.486480Z","submitted_at":"2026-02-23T19:55:54Z","title":"QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2602.20309","snapshot_observed_at":"2026-08-16T00:24:40.785571Z","title":"Quantvla: Scale-calibrated post-training quantization for vision-language-action models,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.785571Z"},"links":{"cited_paper":"/paper/2602.20309","citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:b71493ff6e82d5a5e6aeba360cd5991d14bbcc4bff1d92386ee215328b9d6948","observation_id":"4ce70a51-7f12-4558-8f92-5df16e02c5cb","resolution":{"observed_at":"2026-08-16T00:24:40.785571Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2604.17789","last_updated":"2026-04-21T07:37:48Z","snapshot_observed_at":"2026-08-14T23:57:22.966176Z","submitted_at":"2026-04-20T04:27:28Z","title":"DuQuant++: Fine-grained Rotation Enhances Microscaling FP4 Quantization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2604.17789","snapshot_observed_at":"2026-08-16T00:24:40.788540Z","title":"Duquant++: Fine-grained rotation enhances microscaling fp4 quantization,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.788540Z"},"links":{"cited_paper":"/paper/2604.17789","citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:15864b5f5449e93853b7c2f1ece7f9abaaf56a79b02c9b429bd0706f86c50d40","observation_id":"5e98c6e6-3fa2-469f-9dab-e229b1845301","resolution":{"observed_at":"2026-08-16T00:24:40.788540Z","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":"2026-08-16T00:24:41.265313Z","title":"Dapq-dit: Distribution-aware post-training quantization for efficient generative tasks in diffusion transformers,","venue":null,"work_id":"cd075ad4-a9f2-4377-91fe-5a498d14f4ae","year":2026},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.791580Z"},"links":{"citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:44f8f5ee9e57b3ef0e9265a58360fd3b6e93ce69b623f46c12bf4bb70c3af5b2","observation_id":"f01f2a76-0633-4154-8aeb-44db9341066e","resolution":{"observed_at":"2026-08-16T00:24:41.268326Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T00:24:41.257040Z","title":"Reshape and rotate: Adaptive weight reshaping and fine-grained rotation for ultra-low-bit diffusion transformers quantization,","venue":null,"work_id":"91eed257-c501-471d-9084-6ad2770e048d","year":2026},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.794687Z"},"links":{"citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:5608460e5a4077dc8d4d2966a4d2c1eff49f6ceaac4bea7034d8a1225b4570d4","observation_id":"a455ada1-a5c6-47dc-bce8-219f4bfa7671","resolution":{"observed_at":"2026-08-16T00:24:41.260039Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-08-16T18:00:58.008096Z","submitted_at":"2015-03-09T15:44:49Z","title":"Distilling the Knowledge in a Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.02531","snapshot_observed_at":"2026-08-16T00:24:40.797871Z","title":"Distilling the knowledge in a neural network,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.797871Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:d71c4cce57cc85d5fca67bc98b2505ca9cbe155f74d453110c65e3ed940beb6a","observation_id":"7c4c414a-111e-4d44-b997-6cac23b261fb","resolution":{"observed_at":"2026-08-16T00:24:40.797871Z","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":"2026-08-16T00:24:41.247663Z","title":"Slog: An inductive spectral graph neural network beyond polynomial filter,","venue":null,"work_id":"300f977a-0d4e-4ad5-8468-f087e30e987d","year":2024},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.801169Z"},"links":{"citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:e5bfe9fc4831a724868dc323b695518a4424cde81939d1b0411e2fced3cb56d8","observation_id":"42111034-99e7-4c20-80a6-756fcf626e02","resolution":{"observed_at":"2026-08-16T00:24:41.251691Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T00:24:41.237667Z","title":"Image-level memorization detection via inversion-based inference perturbation,","venue":null,"work_id":"e24f81ec-2c73-47cb-9d1d-8bbc9e97e0c5","year":2025},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.804555Z"},"links":{"citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:1e4e0ab1728ff0198bac4d3cbdb2cd8886f27b5d9d7bdbf7740a733161950b93","observation_id":"58ef0c36-6713-46fd-a654-76c20ea58fc1","resolution":{"observed_at":"2026-08-16T00:24:41.241325Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T00:24:40.807725Z","title":"Medrek: Retrieval-based editing for medical llms with key-aware prompts,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.807725Z"},"links":{"citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:7a7230a2948259317fbca95f7cc637259fb4c41714c4a477ab6a5c9194edb56b","observation_id":"f0191e06-4a96-4036-ab52-bb0f99f9137c","resolution":{"observed_at":"2026-08-16T00:24:40.807725Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2606.24849","last_updated":"2026-06-23T17:28:00Z","snapshot_observed_at":"2026-08-12T23:14:12.939313Z","submitted_at":"2026-06-23T17:28:00Z","title":"IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation","version":1},"cited_work":{"arxiv_id":"2606.24849","doi":null,"metadata_source":"pith","pith_arxiv_id":"2606.24849","snapshot_observed_at":"2026-08-16T00:24:40.918312Z","title":"IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation","venue":"cs.CV","work_id":"8f650dec-bc94-4e57-b885-c908eed9460b","year":2026},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.810989Z"},"links":{"cited_paper":"/paper/2606.24849","citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:f39c0d4a60343fc0dc5cec04e0d8d3ee702b489caed86b829a479087734f10e3","observation_id":"103151c8-f5c6-47d3-9f51-fc66c7cf6206","resolution":{"observed_at":"2026-08-16T00:24:40.922505Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2607.10792","last_updated":"2026-07-12T14:50:08Z","snapshot_observed_at":"2026-08-17T18:59:56.137163Z","submitted_at":"2026-07-12T14:50:08Z","title":"MAC-Splat: Multi-Attribute Consistency for High-Fidelity Sparse-View Reconstruction","version":1},"cited_work":{"arxiv_id":"2607.10792","doi":null,"metadata_source":"pith","pith_arxiv_id":"2607.10792","snapshot_observed_at":"2026-08-16T00:24:40.902523Z","title":"MAC-Splat: Multi-Attribute Consistency for High-Fidelity Sparse-View Reconstruction","venue":"cs.CV","work_id":"32a37ba2-eaa9-4c15-96f4-1afa71eb9d63","year":2026},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.814132Z"},"links":{"cited_paper":"/paper/2607.10792","citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:fd9a579da127b33711121011b87e6da92770aaca7938887933b690d93430e9c5","observation_id":"9cf8ba77-3c56-4d73-86ef-626fa315d725","resolution":{"observed_at":"2026-08-16T00:24:40.907832Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.13116","last_updated":"2024-10-21T16:22:33Z","snapshot_observed_at":"2026-08-10T17:26:33.432994Z","submitted_at":"2024-02-20T16:17:37Z","title":"A Survey on Knowledge Distillation of Large Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.13116","snapshot_observed_at":"2026-08-16T00:24:40.817352Z","title":"A survey on knowledge distillation of large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.817352Z"},"links":{"cited_paper":"/paper/2402.13116","citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:9f1caba7ca57a9976df43c7a81633f222d3f26f1e3571a6d5058b2086ba7afa5","observation_id":"66e58b15-8ae9-43ff-ae47-44234c3e829b","resolution":{"observed_at":"2026-08-16T00:24:40.817352Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.09276","last_updated":"2024-07-12T14:09:40Z","snapshot_observed_at":"2026-08-19T18:55:00.604219Z","submitted_at":"2024-07-12T14:09:40Z","title":"H2O-Danube3 Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.09276","snapshot_observed_at":"2026-08-16T00:24:40.820733Z","title":"H2o-danube3 technical report,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.820733Z"},"links":{"cited_paper":"/paper/2407.09276","citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:00d49303667639461aa966412dc6650d9669d51192670536902669e5268fbf76","observation_id":"328a75d5-aa1e-47c2-bfa3-04652e54604a","resolution":{"observed_at":"2026-08-16T00:24:40.820733Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.07258","last_updated":"2022-07-12T23:45:14Z","snapshot_observed_at":"2026-08-02T09:20:40.804790Z","submitted_at":"2021-08-16T17:50:08Z","title":"On the Opportunities and Risks of Foundation Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.07258","snapshot_observed_at":"2026-08-16T00:24:40.823760Z","title":"On the opportunities and risks of foundation models,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.823760Z"},"links":{"cited_paper":"/paper/2108.07258","citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:43d658c12864acae1f473c6c79ec4487e80d8e0f14e6b55fb5f52e8f2e9d39b9","observation_id":"084bf631-e73d-427a-8b5e-50675a7dadbf","resolution":{"observed_at":"2026-08-16T00:24:40.823760Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2008.02275","last_updated":"2023-02-17T16:08:22Z","snapshot_observed_at":"2026-08-14T10:58:48.301354Z","submitted_at":"2020-08-05T17:59:16Z","title":"Aligning AI With Shared Human Values","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2008.02275","snapshot_observed_at":"2026-08-16T00:24:40.826562Z","title":"Aligning ai with shared human values,","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.826562Z"},"links":{"cited_paper":"/paper/2008.02275","citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:03c6da61627356cfc661e22e50721851b3cbbb2ee00cdaf9b30af3b299416a05","observation_id":"f2cb2152-d94f-46a3-8dc2-a8fb87434434","resolution":{"observed_at":"2026-08-16T00:24:40.826562Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2011.00620","last_updated":"2021-08-16T22:55:40Z","snapshot_observed_at":"2026-08-18T19:59:25.472423Z","submitted_at":"2020-11-01T20:16:45Z","title":"Social Chemistry 101: Learning to Reason about Social and Moral Norms","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.00620","snapshot_observed_at":"2026-08-16T00:24:40.829592Z","title":"Social chemistry 101: Learning to reason about social and moral norms,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.829592Z"},"links":{"cited_paper":"/paper/2011.00620","citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:7d5e4f3012ae715d3367e2af4097b082d3c3851643c10a853a13639ae19ce211","observation_id":"492553a3-6c1f-4d53-bcce-763f5d74f821","resolution":{"observed_at":"2026-08-16T00:24:40.829592Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.02840","last_updated":"2022-01-10T06:05:16Z","snapshot_observed_at":"2026-08-16T17:44:02.805525Z","submitted_at":"2021-11-04T12:59:55Z","title":"Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.02840","snapshot_observed_at":"2026-08-16T00:24:40.832777Z","title":"Adversarial glue: A multi- task benchmark for robustness evaluation of language models,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-16T00:24:40.832777Z"},"links":{"cited_paper":"/paper/2111.02840","citing_paper":"/paper/2608.11981"},"observation_digest":"sha256:9ddaa6f1821eddca976d606e05cd1d72e2bd907195b96db061aaf61db5441b77","observation_id":"6be98f66-f617-46a4-a4a9-9d0a1a024896","resolution":{"observed_at":"2026-08-16T00:24:40.832777Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2608.11981","last_updated":"2026-08-12T12:14:02Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-19T11:10:22.594734Z","submitted_at":"2026-08-12T12:14:02Z","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed"},"reference_resolution":{"displayed":41,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":26,"verified_exact":2,"verified_fuzzy":13},"total_outbound_references":41},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 0 inbound Pith citation observations for arXiv:2608.11981."}