{"as_of":"2026-08-14T23:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f664ac47361489819268620396476e58748abf13a7203e901a110673ed1ebc74","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":7,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":7,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":7,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":7,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T12:30:17.313864Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-03T23:19:03.318032Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2508.00904","last_updated":"2025-07-29T03:08:31Z","snapshot_observed_at":"2026-08-14T03:49:45.690346Z","submitted_at":"2025-07-29T03:08:31Z","title":"Forecasting LLM Inference Performance via Hardware-Agnostic Analytical Modeling","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.00904","snapshot_observed_at":"2026-08-06T12:30:17.313864Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.00908","last_updated":"2025-07-29T11:37:19Z","snapshot_observed_at":"2026-08-13T18:47:57.517033Z","submitted_at":"2025-07-29T11:37:19Z","title":"Mapping Stakeholder Needs to Multi-Sided Fairness in Candidate Recommendation for Algorithmic Hiring","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T12:30:17.313864Z"},"links":{"cited_paper":"/paper/2508.00904","citing_paper":"/paper/2508.00908"},"observation_digest":"sha256:5704a7e6f4c72010e2ff77ded17bb60db9a3f8577fcc130d17c4786bc3794747","observation_id":"963fd96e-063e-45d4-8d5c-49b5fc406e8b","resolution":{"observed_at":"2026-08-06T12:30:17.313864Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.00904","last_updated":"2025-07-29T03:08:31Z","snapshot_observed_at":"2026-08-14T03:49:45.690346Z","submitted_at":"2025-07-29T03:08:31Z","title":"Forecasting LLM Inference Performance via Hardware-Agnostic Analytical Modeling","version":1},"cited_work":{"arxiv_id":"2508.00904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.00904","snapshot_observed_at":"2026-07-03T23:19:03.318032Z","title":"Forecasting llm inference performance via hardware-agnostic analytical modeling,","venue":null,"work_id":"5798df92-b857-47ac-9cf2-263024f67308","year":2025},"citing_paper":{"arxiv_id":"2606.04238","last_updated":"2026-06-02T21:37:56Z","snapshot_observed_at":"2026-07-06T23:44:23.633099Z","submitted_at":"2026-06-02T21:37:56Z","title":"Recover-LoRA for Aggressive Quantization: Reclaiming Accuracy in 2-Bit Language Models via Low-Rank Adaptation with Knowledge Distillation on Synthetic Data","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-06-28T10:41:19.146166Z"},"links":{"cited_paper":"/paper/2508.00904","citing_paper":"/paper/2606.04238"},"observation_digest":"sha256:69fcdc00521e1d124e321371a19c746829763664d1f4b7f4849c5e9b09879785","observation_id":"ae773193-da29-4fe0-b64d-c2232310251a","resolution":{"observed_at":"2026-07-02T02:46:28.220672Z","resolver_source":"arxiv_id","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"}},{"citation":{"cited_paper":{"arxiv_id":"2508.00904","last_updated":"2025-07-29T03:08:31Z","snapshot_observed_at":"2026-08-14T03:49:45.690346Z","submitted_at":"2025-07-29T03:08:31Z","title":"Forecasting LLM Inference Performance via Hardware-Agnostic Analytical Modeling","version":1},"cited_work":{"arxiv_id":"2508.00904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.00904","snapshot_observed_at":"2026-07-03T23:19:03.318032Z","title":"Forecasting llm inference performance via hardware-agnostic analytical modeling,","venue":null,"work_id":"5798df92-b857-47ac-9cf2-263024f67308","year":2025},"citing_paper":{"arxiv_id":"2606.18042","last_updated":"2026-06-17T02:07:30Z","snapshot_observed_at":"2026-08-13T02:00:18.839683Z","submitted_at":"2026-06-16T15:18:53Z","title":"Latency Prediction for LLM Inference on NPU Systems","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-06-26T22:41:36.443948Z"},"links":{"cited_paper":"/paper/2508.00904","citing_paper":"/paper/2606.18042"},"observation_digest":"sha256:35fcb6146f69297462999244f1f8ac3cf41d8277cddf07486b983af2276fcdbf","observation_id":"da74e49e-e797-4be7-9104-19f4161aaf68","resolution":{"observed_at":"2026-07-03T23:19:03.320800Z","resolver_source":"arxiv_id","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"}},{"citation":{"cited_paper":{"arxiv_id":"2508.00904","last_updated":"2025-07-29T03:08:31Z","snapshot_observed_at":"2026-08-14T03:49:45.690346Z","submitted_at":"2025-07-29T03:08:31Z","title":"Forecasting LLM Inference Performance via Hardware-Agnostic Analytical Modeling","version":1},"cited_work":{"arxiv_id":"2508.00904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.00904","snapshot_observed_at":"2026-07-03T23:19:03.318032Z","title":"Forecasting llm inference performance via hardware-agnostic analytical modeling,","venue":null,"work_id":"5798df92-b857-47ac-9cf2-263024f67308","year":2025},"citing_paper":{"arxiv_id":"2607.02391","last_updated":"2026-07-02T16:25:34Z","snapshot_observed_at":"2026-08-13T00:29:45.085555Z","submitted_at":"2026-07-02T16:25:34Z","title":"WattGPU: Predicting Inference Power and Latency on Unseen GPUs and LLMs","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-03T05:42:13.881812Z"},"links":{"cited_paper":"/paper/2508.00904","citing_paper":"/paper/2607.02391"},"observation_digest":"sha256:cad50afb531ab04e399f2d9be5698c9143d7231c01f05c9519a7c32f59aab850","observation_id":"712fe5e4-e43d-4265-bca8-6a5eaf630904","resolution":{"observed_at":"2026-07-03T05:47:40.837796Z","resolver_source":"arxiv_id","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"}},{"citation":{"cited_paper":{"arxiv_id":"2508.00904","last_updated":"2025-07-29T03:08:31Z","snapshot_observed_at":"2026-08-14T03:49:45.690346Z","submitted_at":"2025-07-29T03:08:31Z","title":"Forecasting LLM Inference Performance via Hardware-Agnostic Analytical Modeling","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.00904","snapshot_observed_at":"2026-07-14T06:16:09.070414Z","title":"arXiv preprint arXiv:2508.00904 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.11211","last_updated":"2026-07-13T08:02:26Z","snapshot_observed_at":"2026-08-14T15:47:03.358754Z","submitted_at":"2026-07-13T08:02:26Z","title":"FastTPS: An Optimized Method for LLM Token Phase for AI accelerators","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-07-14T06:16:09.070414Z"},"links":{"cited_paper":"/paper/2508.00904","citing_paper":"/paper/2607.11211"},"observation_digest":"sha256:0584576355683818e4841832283f93e8a7afab624faac57f4a9a0048d2ba7a69","observation_id":"646c96d2-7810-4f44-bece-ab627e554d35","resolution":{"observed_at":"2026-07-14T06:16:09.070414Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.00904","last_updated":"2025-07-29T03:08:31Z","snapshot_observed_at":"2026-08-14T03:49:45.690346Z","submitted_at":"2025-07-29T03:08:31Z","title":"Forecasting LLM Inference Performance via Hardware-Agnostic Analytical Modeling","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.00904","snapshot_observed_at":"2026-08-01T09:35:57.546394Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.20723","last_updated":"2026-07-22T20:51:28Z","snapshot_observed_at":"2026-08-14T05:12:42.269378Z","submitted_at":"2026-07-22T20:51:28Z","title":"Leaky Language Models: Stealing Architecture and Inference Optimizations via Per-Token Timing","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-01T09:35:57.546394Z"},"links":{"cited_paper":"/paper/2508.00904","citing_paper":"/paper/2607.20723"},"observation_digest":"sha256:314f72c7ef84f0e0690dce7b6fd41d1269904538b5a92f904a8983ed4402657a","observation_id":"3e0c4e50-8999-48f0-9df5-1c39d60135f3","resolution":{"observed_at":"2026-08-01T09:35:57.546394Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.00904","last_updated":"2025-07-29T03:08:31Z","snapshot_observed_at":"2026-08-14T03:49:45.690346Z","submitted_at":"2025-07-29T03:08:31Z","title":"Forecasting LLM Inference Performance via Hardware-Agnostic Analytical Modeling","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.00904","snapshot_observed_at":"2026-08-01T04:49:47.995962Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.22432","last_updated":"2026-07-24T15:50:23Z","snapshot_observed_at":"2026-08-06T21:57:48.528474Z","submitted_at":"2026-07-24T15:50:23Z","title":"TileSight: A First-Principles Tile-Centric Analytical GPU Performance Model from Cores to Clusters","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-01T04:49:47.995962Z"},"links":{"cited_paper":"/paper/2508.00904","citing_paper":"/paper/2607.22432"},"observation_digest":"sha256:e57508dfe64c835ff065248008e7f4690c3b9927e8b5db02acfa9b2b7efe60e0","observation_id":"698ecdc0-510d-4e08-b85b-71d6fdff1ccc","resolution":{"observed_at":"2026-08-01T04:49:47.995962Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2508.00904/citation-record","integrity":"/paper/2508.00904/integrity","json":"/paper/2508.00904/citation-record.json","paper":"/paper/2508.00904"},"outbound":[],"paper":{"arxiv_id":"2508.00904","last_updated":"2025-07-29T03:08:31Z","latest_version":1,"primary_category":"cs.PF","snapshot_observed_at":"2026-08-14T03:49:45.690346Z","submitted_at":"2025-07-29T03:08:31Z","title":"Forecasting LLM Inference Performance via Hardware-Agnostic Analytical Modeling"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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 0 of 0 outbound references and 7 inbound Pith citation observations for arXiv:2508.00904."}