{"as_of":"2026-08-14T16:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:88dfa573fa4b4846b0fcb9b21c20ae622f929996fcf817d4ce0fbb3149bd96f8","coverage":[{"denominator":22,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":22,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T04:50:27.765372Z","state":"measured"},{"denominator":23,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":23,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T20:29:01.127039Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"pith","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":0,"observed_at":"2026-08-05T02:28:24.338817Z","source":"pith"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.01042","last_updated":"2024-12-02T01:55:42Z","snapshot_observed_at":"2026-08-14T02:46:12.075713Z","submitted_at":"2024-12-02T01:55:42Z","title":"TruncFormer: Private LLM Inference Using Only Truncations","version":1},"cited_work":{"arxiv_id":"2412.01042","doi":"10.48550/arxiv.2412.01042","metadata_source":"pith","pith_arxiv_id":"2412.01042","snapshot_observed_at":"2026-08-05T02:49:54.815029Z","title":"TruncFormer: Private LLM Inference Using Only Truncations","venue":"cs.CR","work_id":"e58cd5e4-2d5a-4662-b475-778c6f9db25a","year":2024},"citing_paper":{"arxiv_id":"2511.19711","last_updated":"2026-07-23T20:56:40Z","snapshot_observed_at":"2026-08-12T12:23:43.374800Z","submitted_at":"2025-11-24T21:21:55Z","title":"CrypTorch: PyTorch-based Auto-tuning Compiler for Machine Learning with Multi-party Computation","version":2},"reference_index":129,"source":"pdf_text","source_observed_at":"2026-08-03T20:29:01.127039Z"},"links":{"cited_paper":"/paper/2412.01042","citing_paper":"/paper/2511.19711"},"observation_digest":"sha256:d96547e8522a8c71dec954d62e8b9ad44b51232ea7d4eaa0c1565c8fb7d43186","observation_id":"8746602c-22cf-464c-b2f6-efc8fd553aed","resolution":{"observed_at":"2026-08-03T20:33:29.555670Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2412.01042/citation-record","integrity":"/paper/2412.01042/integrity","json":"/paper/2412.01042/citation-record.json","paper":"/paper/2412.01042"},"outbound":[{"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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.07732","snapshot_observed_at":"2026-08-12T04:50:27.699928Z","title":"Program synthesis with large language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.01042","last_updated":"2024-12-02T01:55:42Z","snapshot_observed_at":"2026-08-14T02:46:12.075713Z","submitted_at":"2024-12-02T01:55:42Z","title":"TruncFormer: Private LLM Inference Using Only Truncations","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T04:50:27.699928Z"},"links":{"cited_paper":"/paper/2108.07732","citing_paper":"/paper/2412.01042"},"observation_digest":"sha256:9819fd92bddbf22849fa4dfb817034ca0c1d759797a7da272ad72d3b6bdf4537","observation_id":"8d365b0b-8b75-4b8d-b137-3e868b900a72","resolution":{"observed_at":"2026-08-12T04:50:27.699928Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.04604","last_updated":"2023-10-06T21:45:05Z","snapshot_observed_at":"2026-08-13T05:55:07.282532Z","submitted_at":"2023-10-06T21:45:05Z","title":"PriViT: Vision Transformers for Fast Private Inference","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.04604","snapshot_observed_at":"2026-08-12T04:50:27.707694Z","title":"Privit: Vision transformers for fast private inference","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.01042","last_updated":"2024-12-02T01:55:42Z","snapshot_observed_at":"2026-08-14T02:46:12.075713Z","submitted_at":"2024-12-02T01:55:42Z","title":"TruncFormer: Private LLM Inference Using Only Truncations","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T04:50:27.707694Z"},"links":{"cited_paper":"/paper/2310.04604","citing_paper":"/paper/2412.01042"},"observation_digest":"sha256:29c5586179e27a9bbc3c8cdb03f8726471553c92406202c45993390c8e819664","observation_id":"7eae6579-31ed-4b61-bf45-5bc2047534f0","resolution":{"observed_at":"2026-08-12T04:50:27.707694Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.09254","last_updated":"2023-01-23T03:33:38Z","snapshot_observed_at":"2026-08-13T12:59:50.245411Z","submitted_at":"2023-01-23T03:33:38Z","title":"Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.09254","snapshot_observed_at":"2026-08-12T04:50:27.720334Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.01042","last_updated":"2024-12-02T01:55:42Z","snapshot_observed_at":"2026-08-14T02:46:12.075713Z","submitted_at":"2024-12-02T01:55:42Z","title":"TruncFormer: Private LLM Inference Using Only Truncations","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T04:50:27.720334Z"},"links":{"cited_paper":"/paper/2301.09254","citing_paper":"/paper/2412.01042"},"observation_digest":"sha256:d79300b33fbf46b4dd2a73dbe9266410f7c6f012330310ba10a654b812adc58c","observation_id":"ae916d68-52f3-4fef-be72-5d98618d4ebd","resolution":{"observed_at":"2026-08-12T04:50:27.720334Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.01452","last_updated":"2023-03-16T06:51:31Z","snapshot_observed_at":"2026-08-14T00:22:06.250115Z","submitted_at":"2022-11-02T19:43:22Z","title":"MPCFormer: fast, performant and private Transformer inference with MPC","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.01452","snapshot_observed_at":"2026-08-12T04:50:27.723503Z","title":"P., and Zhang, H","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.01042","last_updated":"2024-12-02T01:55:42Z","snapshot_observed_at":"2026-08-14T02:46:12.075713Z","submitted_at":"2024-12-02T01:55:42Z","title":"TruncFormer: Private LLM Inference Using Only Truncations","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T04:50:27.723503Z"},"links":{"cited_paper":"/paper/2211.01452","citing_paper":"/paper/2412.01042"},"observation_digest":"sha256:4eac9ef2b7a2703bf1934c17c0f32636d7f625580fe74fda74a40fd2579a9479","observation_id":"03899982-d972-45a4-b567-c892210b3fca","resolution":{"observed_at":"2026-08-12T04:50:27.723503Z","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":"2026-08-12T04:50:27.986786Z","title":"Oblivious neu- ral network predictions via minionn transformations","venue":null,"work_id":"b5f8d59c-43b5-4bc5-8246-2b11d065657c","year":2017},"citing_paper":{"arxiv_id":"2412.01042","last_updated":"2024-12-02T01:55:42Z","snapshot_observed_at":"2026-08-14T02:46:12.075713Z","submitted_at":"2024-12-02T01:55:42Z","title":"TruncFormer: Private LLM Inference Using Only Truncations","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T04:50:27.726336Z"},"links":{"citing_paper":"/paper/2412.01042"},"observation_digest":"sha256:b2846a8dd8db157fb7c42bae6403ba8f34bcf3e326229cf9aa3d608c6ee1b059","observation_id":"0ada9046-8b94-47b2-813f-f8218b2e9b8e","resolution":{"observed_at":"2026-08-12T04:50:27.989788Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.00793","last_updated":"2025-06-09T07:49:24Z","snapshot_observed_at":"2026-08-13T04:50:27.704848Z","submitted_at":"2024-01-01T15:40:35Z","title":"SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.00793","snapshot_observed_at":"2026-08-12T04:50:27.728953Z","title":"Secformer: Towards fast and accurate privacy- preserving inference for large language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.01042","last_updated":"2024-12-02T01:55:42Z","snapshot_observed_at":"2026-08-14T02:46:12.075713Z","submitted_at":"2024-12-02T01:55:42Z","title":"TruncFormer: Private LLM Inference Using Only Truncations","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T04:50:27.728953Z"},"links":{"cited_paper":"/paper/2401.00793","citing_paper":"/paper/2412.01042"},"observation_digest":"sha256:c04b6f3f28a762fd17c95e54ecd3090f4c24f6f0af6b6cb6980966cac5482c0e","observation_id":"d54d8253-253c-4c32-b169-399d70340c11","resolution":{"observed_at":"2026-08-12T04:50:27.728953Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1609.07843","last_updated":"2016-09-26T04:06:13Z","snapshot_observed_at":"2026-07-06T05:12:10.387914Z","submitted_at":"2016-09-26T04:06:13Z","title":"Pointer Sentinel Mixture Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.07843","snapshot_observed_at":"2026-08-12T04:50:27.735611Z","title":"Pointer sentinel mixture models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.01042","last_updated":"2024-12-02T01:55:42Z","snapshot_observed_at":"2026-08-14T02:46:12.075713Z","submitted_at":"2024-12-02T01:55:42Z","title":"TruncFormer: Private LLM Inference Using Only Truncations","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T04:50:27.735611Z"},"links":{"cited_paper":"/paper/1609.07843","citing_paper":"/paper/2412.01042"},"observation_digest":"sha256:b80713293d636675befb0e05ceaff78e1aa550be8be133c2602a28fdfc83722c","observation_id":"ac97d28d-70ca-4d96-ba1d-dc677e1272fa","resolution":{"observed_at":"2026-08-12T04:50:27.735611Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.05202","last_updated":"2020-02-12T19:57:13Z","snapshot_observed_at":"2026-08-11T06:21:56.129166Z","submitted_at":"2020-02-12T19:57:13Z","title":"GLU Variants Improve Transformer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.05202","snapshot_observed_at":"2026-08-12T04:50:27.741137Z","title":"Glu variants improve transformer","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2412.01042","last_updated":"2024-12-02T01:55:42Z","snapshot_observed_at":"2026-08-14T02:46:12.075713Z","submitted_at":"2024-12-02T01:55:42Z","title":"TruncFormer: Private LLM Inference Using Only Truncations","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T04:50:27.741137Z"},"links":{"cited_paper":"/paper/2002.05202","citing_paper":"/paper/2412.01042"},"observation_digest":"sha256:4e075313b091f39a59ac1fa71b02c7ef879d19d794fd5225c346a93a047af2ca","observation_id":"00d1fffd-4d81-4557-858d-c38e61c8bbba","resolution":{"observed_at":"2026-08-12T04:50:27.741137Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-12T04:50:27.744036Z","title":"S., Love, J., et al","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.01042","last_updated":"2024-12-02T01:55:42Z","snapshot_observed_at":"2026-08-14T02:46:12.075713Z","submitted_at":"2024-12-02T01:55:42Z","title":"TruncFormer: Private LLM Inference Using Only Truncations","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T04:50:27.744036Z"},"links":{"cited_paper":"/paper/2403.08295","citing_paper":"/paper/2412.01042"},"observation_digest":"sha256:b6f9013e05dc3d5769b807de1f36f6852ec8cde97257036089f999a36a1cb38b","observation_id":"468e60f5-7c33-4425-a11a-32e05388bcec","resolution":{"observed_at":"2026-08-12T04:50:27.744036Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-12T04:50:27.746887Z","title":"Llama: Open and efficient foundation lan- guage models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.01042","last_updated":"2024-12-02T01:55:42Z","snapshot_observed_at":"2026-08-14T02:46:12.075713Z","submitted_at":"2024-12-02T01:55:42Z","title":"TruncFormer: Private LLM Inference Using Only Truncations","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T04:50:27.746887Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2412.01042"},"observation_digest":"sha256:9a0c1a269c59693ec5d39e28952c5fa8e9b617f32549dbff1f8bc850aa44ced9","observation_id":"7003c7f3-4a71-4af0-accd-eb3056349884","resolution":{"observed_at":"2026-08-12T04:50:27.746887Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.07176","last_updated":"2020-05-03T02:46:19Z","snapshot_observed_at":"2026-08-12T12:22:57.154747Z","submitted_at":"2019-11-17T07:51:42Z","title":"Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answering","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.07176","snapshot_observed_at":"2026-08-12T04:50:27.749713Z","title":"Quick and (not so) dirty: Unsupervised selection of justification sen- tences for multi-hop question answering","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2412.01042","last_updated":"2024-12-02T01:55:42Z","snapshot_observed_at":"2026-08-14T02:46:12.075713Z","submitted_at":"2024-12-02T01:55:42Z","title":"TruncFormer: Private LLM Inference Using Only Truncations","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T04:50:27.749713Z"},"links":{"cited_paper":"/paper/1911.07176","citing_paper":"/paper/2412.01042"},"observation_digest":"sha256:d12df0204dc868dbdcddac8b1a5eb5b043b091b8f5817771e0f511d2e8dcb844","observation_id":"0a32b569-1c66-41b1-98e4-4052ed6e3321","resolution":{"observed_at":"2026-08-12T04:50:27.749713Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.13955","last_updated":"2023-08-19T08:00:55Z","snapshot_observed_at":"2026-08-13T13:34:56.513279Z","submitted_at":"2022-11-25T08:37:17Z","title":"MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attention","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.13955","snapshot_observed_at":"2026-08-12T04:50:27.758608Z","title":"Mpcvit: Searching for accurate and efficient mpc-friendly vision transformer with het- erogeneous attention","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.01042","last_updated":"2024-12-02T01:55:42Z","snapshot_observed_at":"2026-08-14T02:46:12.075713Z","submitted_at":"2024-12-02T01:55:42Z","title":"TruncFormer: Private LLM Inference Using Only Truncations","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T04:50:27.758608Z"},"links":{"cited_paper":"/paper/2211.13955","citing_paper":"/paper/2412.01042"},"observation_digest":"sha256:f0b5570f3867afd9f68fda2a97f9d099abfdbc42b3c5d405562eca32b9376c28","observation_id":"f3d4e4f6-9869-4770-8e83-518919e1b702","resolution":{"observed_at":"2026-08-12T04:50:27.758608Z","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":"2026-08-12T04:50:27.947718Z","title":"Primer: Fast private transformer inference on encrypted data","venue":null,"work_id":"b2026028-7401-4496-9d92-d368d8f70883","year":2023},"citing_paper":{"arxiv_id":"2412.01042","last_updated":"2024-12-02T01:55:42Z","snapshot_observed_at":"2026-08-14T02:46:12.075713Z","submitted_at":"2024-12-02T01:55:42Z","title":"TruncFormer: Private LLM Inference Using Only Truncations","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T04:50:27.762358Z"},"links":{"citing_paper":"/paper/2412.01042"},"observation_digest":"sha256:b2f1fb07756eb9108e0085db02b82e34236728e486fb1b82103c39bcc44eeb10","observation_id":"6cdb8c5b-a48c-440a-877a-0055bf4d58bf","resolution":{"observed_at":"2026-08-12T04:50:27.952783Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.15877","last_updated":"2025-04-01T08:36:44Z","snapshot_observed_at":"2026-08-14T15:45:30.011625Z","submitted_at":"2024-06-22T15:52:04Z","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.15877","snapshot_observed_at":"2026-08-12T04:50:27.765372Z","title":"Y ., Vu, M","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.01042","last_updated":"2024-12-02T01:55:42Z","snapshot_observed_at":"2026-08-14T02:46:12.075713Z","submitted_at":"2024-12-02T01:55:42Z","title":"TruncFormer: Private LLM Inference Using Only Truncations","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T04:50:27.765372Z"},"links":{"cited_paper":"/paper/2406.15877","citing_paper":"/paper/2412.01042"},"observation_digest":"sha256:131c4b5b7cdb18c469a6b8dae0da892c900846e2242e49b7043cfadd027f083d","observation_id":"240d1e14-83eb-48f1-bacc-e576bc7900a6","resolution":{"observed_at":"2026-08-12T04:50:27.765372Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1905.07830","last_updated":"2019-05-19T23:57:23Z","snapshot_observed_at":"2026-08-10T16:18:23.994244Z","submitted_at":"2019-05-19T23:57:23Z","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.07830","snapshot_observed_at":"2026-08-12T04:50:27.755741Z","title":"Hellaswag: Can a machine really finish your sentence? arXiv preprint arXiv:1905.07830,","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2412.01042","last_updated":"2024-12-02T01:55:42Z","snapshot_observed_at":"2026-08-14T02:46:12.075713Z","submitted_at":"2024-12-02T01:55:42Z","title":"TruncFormer: Private LLM Inference Using Only Truncations","version":1},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-12T04:50:27.755741Z"},"links":{"cited_paper":"/paper/1905.07830","citing_paper":"/paper/2412.01042"},"observation_digest":"sha256:1c78e7c01fbc8cef56a666159b983c2be953c6981037aa9bb589a738d194d21c","observation_id":"229001b6-4e37-4c3b-a3ce-4073c0f4f037","resolution":{"observed_at":"2026-08-12T04:50:27.755741Z","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":"2026-08-12T04:50:27.967795Z","title":null,"venue":null,"work_id":"f9bc4e81-6551-49f1-9645-94e38d2f168f","year":2020},"citing_paper":{"arxiv_id":"2412.01042","last_updated":"2024-12-02T01:55:42Z","snapshot_observed_at":"2026-08-14T02:46:12.075713Z","submitted_at":"2024-12-02T01:55:42Z","title":"TruncFormer: Private LLM Inference Using Only Truncations","version":1},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-12T04:50:27.738516Z"},"links":{"citing_paper":"/paper/2412.01042"},"observation_digest":"sha256:966b12d2830393a1cd68d32bd574159bdf4b5a56a454197c25ea2b0893c6adad","observation_id":"68429423-3944-4efe-9218-efd7b9e27a9d","resolution":{"observed_at":"2026-08-12T04:50:27.970979Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T04:50:27.958519Z","title":null,"venue":null,"work_id":"60c654f1-fddf-4b1a-8c4b-ec4b2127800a","year":1986},"citing_paper":{"arxiv_id":"2412.01042","last_updated":"2024-12-02T01:55:42Z","snapshot_observed_at":"2026-08-14T02:46:12.075713Z","submitted_at":"2024-12-02T01:55:42Z","title":"TruncFormer: Private LLM Inference Using Only Truncations","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-12T04:50:27.752873Z"},"links":{"citing_paper":"/paper/2412.01042"},"observation_digest":"sha256:81bd066a5b3d33398758ecf2cd34e0058a9bf94bee583102eee9c21ec24d2d5d","observation_id":"3ed1a4e3-5809-449e-9bba-2c420b446cb5","resolution":{"observed_at":"2026-08-12T04:50:27.961618Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.03874","last_updated":"2021-11-08T21:30:18Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2021-03-05T18:59:39Z","title":"Measuring Mathematical Problem Solving With the MATH Dataset","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.03874","snapshot_observed_at":"2026-08-12T04:50:27.716953Z","title":"Measuring math- ematical problem solving with the math dataset","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.01042","last_updated":"2024-12-02T01:55:42Z","snapshot_observed_at":"2026-08-14T02:46:12.075713Z","submitted_at":"2024-12-02T01:55:42Z","title":"TruncFormer: Private LLM Inference Using Only Truncations","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-12T04:50:27.716953Z"},"links":{"cited_paper":"/paper/2103.03874","citing_paper":"/paper/2412.01042"},"observation_digest":"sha256:9bfeb2a66539c2964d65e01335d9c1997663148397192eee8160208fff680034","observation_id":"c6001197-0b24-497e-b226-391daf75ea35","resolution":{"observed_at":"2026-08-12T04:50:27.716953Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.14168","last_updated":"2021-11-18T00:23:45Z","snapshot_observed_at":"2026-08-14T02:43:01.480086Z","submitted_at":"2021-10-27T04:49:45Z","title":"Training Verifiers to Solve Math Word Problems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.14168","snapshot_observed_at":"2026-08-12T04:50:27.703455Z","title":"Sphynx: A deep neural network design for private inference","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.01042","last_updated":"2024-12-02T01:55:42Z","snapshot_observed_at":"2026-08-14T02:46:12.075713Z","submitted_at":"2024-12-02T01:55:42Z","title":"TruncFormer: Private LLM Inference Using Only Truncations","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-12T04:50:27.703455Z"},"links":{"cited_paper":"/paper/2110.14168","citing_paper":"/paper/2412.01042"},"observation_digest":"sha256:46aea012881596bcc5ee87ee378df4b6361f674d5b3dccadfde0241273a45cfc","observation_id":"8e60cf81-f2ca-4eb9-bafa-29364d92e9cd","resolution":{"observed_at":"2026-08-12T04:50:27.703455Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2009.03300","last_updated":"2021-01-12T18:57:11Z","snapshot_observed_at":"2026-08-13T20:44:28.824685Z","submitted_at":"2020-09-07T17:59:25Z","title":"Measuring Massive Multitask Language Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.03300","snapshot_observed_at":"2026-08-12T04:50:27.713976Z","title":"Measuring mas- sive multitask language understanding","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2412.01042","last_updated":"2024-12-02T01:55:42Z","snapshot_observed_at":"2026-08-14T02:46:12.075713Z","submitted_at":"2024-12-02T01:55:42Z","title":"TruncFormer: Private LLM Inference Using Only Truncations","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-12T04:50:27.713976Z"},"links":{"cited_paper":"/paper/2009.03300","citing_paper":"/paper/2412.01042"},"observation_digest":"sha256:34b9d4c26d00ff6d436fcb607865f18c6fc2079f888bac6502229a5325a92d66","observation_id":"b27e77a1-fe97-4a19-8cdd-2ec0af1d75d3","resolution":{"observed_at":"2026-08-12T04:50:27.713976Z","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":"2026-08-12T04:50:27.711161Z","title":"Puma: Se- cure inference of llama-7b in five minutes","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.01042","last_updated":"2024-12-02T01:55:42Z","snapshot_observed_at":"2026-08-14T02:46:12.075713Z","submitted_at":"2024-12-02T01:55:42Z","title":"TruncFormer: Private LLM Inference Using Only Truncations","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-12T04:50:27.711161Z"},"links":{"citing_paper":"/paper/2412.01042"},"observation_digest":"sha256:59608ec8a164146e267f675e987942d245e8e422c7f4453bc0b0670a76e58bfe","observation_id":"3db1b9a0-fa46-4a7f-9a38-5695ad72d6df","resolution":{"observed_at":"2026-08-12T04:50:27.711161Z","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":"2026-08-12T04:50:27.977798Z","title":"{SecretFlow- SPU}: A performant and {User-Friendly} framework for {Privacy-Preserving} machine learning","venue":null,"work_id":"c7af89eb-c988-471c-9e2c-5fd01a188e3d","year":2023},"citing_paper":{"arxiv_id":"2412.01042","last_updated":"2024-12-02T01:55:42Z","snapshot_observed_at":"2026-08-14T02:46:12.075713Z","submitted_at":"2024-12-02T01:55:42Z","title":"TruncFormer: Private LLM Inference Using Only Truncations","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-12T04:50:27.731839Z"},"links":{"citing_paper":"/paper/2412.01042"},"observation_digest":"sha256:6b761e19a1bc8f6ce6492d9538892d7e98adedc552b1616ac7910e92e34a5a31","observation_id":"60255f98-bc64-40f9-bd88-0aa5d06773f0","resolution":{"observed_at":"2026-08-12T04:50:27.981278Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.01042","last_updated":"2024-12-02T01:55:42Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-14T02:46:12.075713Z","submitted_at":"2024-12-02T01:55:42Z","title":"TruncFormer: Private LLM Inference Using Only Truncations"},"reference_resolution":{"displayed":22,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":19,"verified_exact":0,"verified_fuzzy":3},"total_outbound_references":22},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 1 inbound Pith citation observation for arXiv:2412.01042."}