{"as_of":"2026-08-09T08:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:764fb95abf091ed1887cd7c2ceccbb0da71e0017635dc27dacc03bea1c2654d2","coverage":[{"denominator":26,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":26,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T00:13:50.542015Z","state":"measured"},{"denominator":26,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":26,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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/2608.01563/citation-record","integrity":"/paper/2608.01563/integrity","json":"/paper/2608.01563/citation-record.json","paper":"/paper/2608.01563"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:13:55.408874Z","title":"TVM: An automated end-to-end optimizing compiler for deep learning","venue":null,"work_id":"f7df9eb5-0776-459f-807c-aae8221df8b2","year":2018},"citing_paper":{"arxiv_id":"2608.01563","last_updated":"2026-08-03T00:42:55Z","snapshot_observed_at":"2026-08-07T21:39:09.614819Z","submitted_at":"2026-08-03T00:42:55Z","title":"Meganeura: Portable GPU Training and Inference through Vulkan and Metal","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T00:13:47.357606Z"},"links":{"citing_paper":"/paper/2608.01563"},"observation_digest":"sha256:c85a31f8c3da432f4980db02dac3768e26911d5251d8574f830ad27366a033ef","observation_id":"c84e0aee-12b7-46a8-a8ec-57dd36bdc40b","resolution":{"observed_at":"2026-08-07T00:13:55.563093Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:13:55.173371Z","title":"Deep residual learning for image recognition","venue":null,"work_id":"19a49bb1-1cbb-4589-b56a-c0f94974dcc6","year":2016},"citing_paper":{"arxiv_id":"2608.01563","last_updated":"2026-08-03T00:42:55Z","snapshot_observed_at":"2026-08-07T21:39:09.614819Z","submitted_at":"2026-08-03T00:42:55Z","title":"Meganeura: Portable GPU Training and Inference through Vulkan and Metal","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T00:13:47.448481Z"},"links":{"citing_paper":"/paper/2608.01563"},"observation_digest":"sha256:a19dbf924520e0de5f5624fcba16d11f468925e1225ab089bd625d26ad5796b3","observation_id":"202c91fe-0d52-4a48-a8e9-b9b1c76b7df5","resolution":{"observed_at":"2026-08-07T00:13:55.290525Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:13:54.887056Z","title":"TASO: Optimizing deep learning computation with automatic generation of graph substitutions","venue":null,"work_id":"ecb9afb0-8bb0-4eb1-9125-fee31813b89f","year":2019},"citing_paper":{"arxiv_id":"2608.01563","last_updated":"2026-08-03T00:42:55Z","snapshot_observed_at":"2026-08-07T21:39:09.614819Z","submitted_at":"2026-08-03T00:42:55Z","title":"Meganeura: Portable GPU Training and Inference through Vulkan and Metal","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T00:13:47.575760Z"},"links":{"citing_paper":"/paper/2608.01563"},"observation_digest":"sha256:8dc89b6cd69feca5a1a12f9db66c0c564b5ba83484cf6caf6b7dff43261a9c48","observation_id":"a66a1d6f-5d3d-47ac-bab8-18baa5db102c","resolution":{"observed_at":"2026-08-07T00:13:55.009271Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:13:54.648105Z","title":"MLIR: Scaling compiler infrastructure for domain specific computation","venue":null,"work_id":"2e42e38b-6b3b-4b77-b5ca-88b87daaddc5","year":2021},"citing_paper":{"arxiv_id":"2608.01563","last_updated":"2026-08-03T00:42:55Z","snapshot_observed_at":"2026-08-07T21:39:09.614819Z","submitted_at":"2026-08-03T00:42:55Z","title":"Meganeura: Portable GPU Training and Inference through Vulkan and Metal","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T00:13:47.729684Z"},"links":{"citing_paper":"/paper/2608.01563"},"observation_digest":"sha256:37dba88577a6874ea88e01fbf4caee70fe1a34c89b4a8f7cd7f9aeaa9c0449f9","observation_id":"c3dd1cbc-c7f2-4a39-ba7f-5d4c13f17ef5","resolution":{"observed_at":"2026-08-07T00:13:54.725486Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2605.20706","last_updated":"2026-05-20T05:05:10Z","snapshot_observed_at":"2026-08-02T06:31:23.188753Z","submitted_at":"2026-05-20T05:05:10Z","title":"Llamas on the Web: Memory-Efficient, Performance-Portable, and Multi-Precision LLM Inference with WebGPU","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.20706","snapshot_observed_at":"2026-08-07T00:13:47.828995Z","title":"Llamas on the web: Memory-efficient, performance-portable, and multi- precision llm inference with WebGPU.arXiv preprint arXiv:2605.20706, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.01563","last_updated":"2026-08-03T00:42:55Z","snapshot_observed_at":"2026-08-07T21:39:09.614819Z","submitted_at":"2026-08-03T00:42:55Z","title":"Meganeura: Portable GPU Training and Inference through Vulkan and Metal","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T00:13:47.828995Z"},"links":{"cited_paper":"/paper/2605.20706","citing_paper":"/paper/2608.01563"},"observation_digest":"sha256:68611ff94b4dbca7323800448c62bead1ac44e24cb02afc87affe86371f8c99a","observation_id":"32fa7e77-badf-42ea-ac04-922a453118fe","resolution":{"observed_at":"2026-08-07T00:13:47.828995Z","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":"2026-08-07T00:13:54.345160Z","title":"On-device training under 256KB memory","venue":null,"work_id":"125fe490-7426-40f4-8261-87aa77be1847","year":2022},"citing_paper":{"arxiv_id":"2608.01563","last_updated":"2026-08-03T00:42:55Z","snapshot_observed_at":"2026-08-07T21:39:09.614819Z","submitted_at":"2026-08-03T00:42:55Z","title":"Meganeura: Portable GPU Training and Inference through Vulkan and Metal","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T00:13:47.884393Z"},"links":{"citing_paper":"/paper/2608.01563"},"observation_digest":"sha256:a3c2380c09a33bd75b5527845f716009da99987d5f4ab5f6df2beb82cb2b085b","observation_id":"2daeb7b9-3f8a-445e-b953-cab816d9192a","resolution":{"observed_at":"2026-08-07T00:13:54.469106Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:13:54.049133Z","title":"TinyIREE: An ML execution environment for embedded systems from compilation to deployment","venue":null,"work_id":"b6434717-161d-4b15-af8f-b0d194dad8d3","year":2022},"citing_paper":{"arxiv_id":"2608.01563","last_updated":"2026-08-03T00:42:55Z","snapshot_observed_at":"2026-08-07T21:39:09.614819Z","submitted_at":"2026-08-03T00:42:55Z","title":"Meganeura: Portable GPU Training and Inference through Vulkan and Metal","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T00:13:47.975577Z"},"links":{"citing_paper":"/paper/2608.01563"},"observation_digest":"sha256:6e59be072a3a13f6a0446c10ef3372b62ae5f9e6b744ca88e1690cf867b31069","observation_id":"3338bc28-34af-435d-afea-769972c32c95","resolution":{"observed_at":"2026-08-07T00:13:54.178095Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2604.02344","last_updated":"2026-02-09T20:14:42Z","snapshot_observed_at":"2026-07-06T22:51:44.663367Z","submitted_at":"2026-02-09T20:14:42Z","title":"Characterizing WebGPU Dispatch Overhead for LLM Inference Across Four GPU Vendors, Three Backends, and Three Browsers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2604.02344","snapshot_observed_at":"2026-08-07T00:13:48.102775Z","title":"Characterizing WebGPU dispatch overhead for LLM inference across four GPU vendors, three backends, and three browsers.arXiv preprint arXiv:2604.02344, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.01563","last_updated":"2026-08-03T00:42:55Z","snapshot_observed_at":"2026-08-07T21:39:09.614819Z","submitted_at":"2026-08-03T00:42:55Z","title":"Meganeura: Portable GPU Training and Inference through Vulkan and Metal","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T00:13:48.102775Z"},"links":{"cited_paper":"/paper/2604.02344","citing_paper":"/paper/2608.01563"},"observation_digest":"sha256:78ece0edd9242e1aa3c627dbaa0d7710c9ceccd2801903724f058d620bbd096b","observation_id":"e0fa0f2f-83ba-4ed5-a061-0d8887e439c5","resolution":{"observed_at":"2026-08-07T00:13:48.102775Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2607.26506","last_updated":"2026-07-29T06:10:20Z","snapshot_observed_at":"2026-08-01T23:26:12.018022Z","submitted_at":"2026-07-29T06:10:20Z","title":"Global Pass Barriers Without Per-Resource RHI Tracking: A Cross-Vendor Study with Blade","version":1},"cited_work":{"arxiv_id":"2607.26506","doi":null,"metadata_source":"pith","pith_arxiv_id":"2607.26506","snapshot_observed_at":"2026-08-07T00:13:51.111859Z","title":"Global Pass Barriers Without Per-Resource RHI Tracking: A Cross-Vendor Study with Blade","venue":"cs.GR","work_id":"d382445f-7dea-4805-a9f6-5bd64c058bf0","year":2026},"citing_paper":{"arxiv_id":"2608.01563","last_updated":"2026-08-03T00:42:55Z","snapshot_observed_at":"2026-08-07T21:39:09.614819Z","submitted_at":"2026-08-03T00:42:55Z","title":"Meganeura: Portable GPU Training and Inference through Vulkan and Metal","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T00:13:48.227456Z"},"links":{"cited_paper":"/paper/2607.26506","citing_paper":"/paper/2608.01563"},"observation_digest":"sha256:31cbd9a931d32ad9a1f7f544ce02c2c68cafce7bee7d1e1120a50d3b08b35d34","observation_id":"3f58c168-c540-4ba8-b78c-c3095456e3d3","resolution":{"observed_at":"2026-08-07T00:13:51.202172Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2605.08195","last_updated":"2026-05-05T18:59:31Z","snapshot_observed_at":"2026-07-06T23:20:28.875586Z","submitted_at":"2026-05-05T18:59:31Z","title":"ExecuTorch -- A Unified PyTorch Solution to Run AI Models On-Device","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.08195","snapshot_observed_at":"2026-08-07T00:13:48.317766Z","title":"ExecuTorch: A unified PyTorch solution to run AImodelson-device.arXiv preprint arXiv:2605.08195, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.01563","last_updated":"2026-08-03T00:42:55Z","snapshot_observed_at":"2026-08-07T21:39:09.614819Z","submitted_at":"2026-08-03T00:42:55Z","title":"Meganeura: Portable GPU Training and Inference through Vulkan and Metal","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T00:13:48.317766Z"},"links":{"cited_paper":"/paper/2605.08195","citing_paper":"/paper/2608.01563"},"observation_digest":"sha256:15139fc08e112534edaeea78b2ced241b1f821f3ade9fd01560d28f6b799897f","observation_id":"1a45f875-70f0-4bfd-b3ba-d4ea5faee005","resolution":{"observed_at":"2026-08-07T00:13:48.317766Z","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":"2026-08-07T00:13:53.811955Z","title":"PyTorch: An impera- tive style, high-performance deep learning library","venue":null,"work_id":"2a7653e5-bcd9-4363-80cf-20dd461a2b52","year":2019},"citing_paper":{"arxiv_id":"2608.01563","last_updated":"2026-08-03T00:42:55Z","snapshot_observed_at":"2026-08-07T21:39:09.614819Z","submitted_at":"2026-08-03T00:42:55Z","title":"Meganeura: Portable GPU Training and Inference through Vulkan and Metal","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T00:13:48.416400Z"},"links":{"citing_paper":"/paper/2608.01563"},"observation_digest":"sha256:3272b44879086e8cef8dbed7a338afafaf06c4ef35d40a325419118873a41062","observation_id":"4a7986fb-0ce2-4d6c-8a1a-32684bc42cd4","resolution":{"observed_at":"2026-08-07T00:13:53.927474Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:13:53.469611Z","title":"Pennycook, Jason D","venue":null,"work_id":"cccf2098-2f5b-41ff-8a85-0d29efe163be","year":2016},"citing_paper":{"arxiv_id":"2608.01563","last_updated":"2026-08-03T00:42:55Z","snapshot_observed_at":"2026-08-07T21:39:09.614819Z","submitted_at":"2026-08-03T00:42:55Z","title":"Meganeura: Portable GPU Training and Inference through Vulkan and Metal","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T00:13:48.592613Z"},"links":{"citing_paper":"/paper/2608.01563"},"observation_digest":"sha256:4d3f6d2508fe3fceeeb6edba8c7636cb1c98a89625b51a0b387a9107dd4c60c5","observation_id":"12c3ad6d-d66d-4cf9-aeb8-8713fc7601ea","resolution":{"observed_at":"2026-08-07T00:13:53.625239Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.04356","last_updated":"2022-12-06T18:46:04Z","snapshot_observed_at":"2026-07-06T14:28:21.844826Z","submitted_at":"2022-12-06T18:46:04Z","title":"Robust Speech Recognition via Large-Scale Weak Supervision","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.04356","snapshot_observed_at":"2026-08-07T00:13:48.716832Z","title":"Robust speech recognition via large-scale weak supervision","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.01563","last_updated":"2026-08-03T00:42:55Z","snapshot_observed_at":"2026-08-07T21:39:09.614819Z","submitted_at":"2026-08-03T00:42:55Z","title":"Meganeura: Portable GPU Training and Inference through Vulkan and Metal","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T00:13:48.716832Z"},"links":{"cited_paper":"/paper/2212.04356","citing_paper":"/paper/2608.01563"},"observation_digest":"sha256:7503acd7c2bdeb839f50ffa86b202634772dfd973b4fefc111632f6c99086869","observation_id":"816a03a5-8846-489b-a275-7ec98b537764","resolution":{"observed_at":"2026-08-07T00:13:48.716832Z","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":"2026-08-07T00:13:53.153912Z","title":"High- resolution image synthesis with latent diffusion mod- els","venue":null,"work_id":"28f60a0c-eab1-431f-bc53-fd58227f2cff","year":2022},"citing_paper":{"arxiv_id":"2608.01563","last_updated":"2026-08-03T00:42:55Z","snapshot_observed_at":"2026-08-07T21:39:09.614819Z","submitted_at":"2026-08-03T00:42:55Z","title":"Meganeura: Portable GPU Training and Inference through Vulkan and Metal","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T00:13:48.906282Z"},"links":{"citing_paper":"/paper/2608.01563"},"observation_digest":"sha256:6532389a372c29ab98cc7d2a51a1ac4ab3bcd32219c6172682650d2e666d864c","observation_id":"f843ce3f-ffbe-42ae-a527-12a2aadebdf1","resolution":{"observed_at":"2026-08-07T00:13:53.298516Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1805.00907","last_updated":"2019-04-03T19:54:50Z","snapshot_observed_at":"2026-08-08T17:17:04.768593Z","submitted_at":"2018-05-02T17:04:53Z","title":"Glow: Graph Lowering Compiler Techniques for Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.00907","snapshot_observed_at":"2026-08-07T00:13:49.021957Z","title":"Glow: Graph lowering com- piler techniques for neural networks.arXiv preprint arXiv:1805.00907, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.01563","last_updated":"2026-08-03T00:42:55Z","snapshot_observed_at":"2026-08-07T21:39:09.614819Z","submitted_at":"2026-08-03T00:42:55Z","title":"Meganeura: Portable GPU Training and Inference through Vulkan and Metal","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T00:13:49.021957Z"},"links":{"cited_paper":"/paper/1805.00907","citing_paper":"/paper/2608.01563"},"observation_digest":"sha256:8557a30780b50f0f3dac1b9ec41ddcbaa1905c8c8a40d124c11b2c7eca671ba7","observation_id":"2689c768-7fcc-4644-b9b8-3a6c6f2549fa","resolution":{"observed_at":"2026-08-07T00:13:49.021957Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.15803","last_updated":"2026-04-13T04:55:03Z","snapshot_observed_at":"2026-08-08T10:07:15.029926Z","submitted_at":"2024-12-20T11:24:13Z","title":"WebLLM: A High-Performance In-Browser LLM Inference Engine","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.15803","snapshot_observed_at":"2026-08-07T00:13:49.167042Z","title":"Ruan, Yucheng Qin, Akaash R","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.01563","last_updated":"2026-08-03T00:42:55Z","snapshot_observed_at":"2026-08-07T21:39:09.614819Z","submitted_at":"2026-08-03T00:42:55Z","title":"Meganeura: Portable GPU Training and Inference through Vulkan and Metal","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T00:13:49.167042Z"},"links":{"cited_paper":"/paper/2412.15803","citing_paper":"/paper/2608.01563"},"observation_digest":"sha256:dd468b54d69c96e461fe770608badea82746c0a82b6b8df9340e2e95d57dd220","observation_id":"531c39e2-3f8c-49ab-ad9a-37bdb83ca7aa","resolution":{"observed_at":"2026-08-07T00:13:49.167042Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.01844","last_updated":"2025-06-02T16:30:19Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-02T16:30:19Z","title":"SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.01844","snapshot_observed_at":"2026-08-07T00:13:49.303331Z","title":"SmolVLA: A vision- language-action model for affordable and efficient robotics.arXiv preprint arXiv:2506.01844, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.01563","last_updated":"2026-08-03T00:42:55Z","snapshot_observed_at":"2026-08-07T21:39:09.614819Z","submitted_at":"2026-08-03T00:42:55Z","title":"Meganeura: Portable GPU Training and Inference through Vulkan and Metal","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T00:13:49.303331Z"},"links":{"cited_paper":"/paper/2506.01844","citing_paper":"/paper/2608.01563"},"observation_digest":"sha256:c1ced83e6f9efbe23e00873773efa1b1ffb5547811b5f43aafed313e9fdb3128","observation_id":"39363ff6-44db-4c5c-bdc1-0a6e2eab44db","resolution":{"observed_at":"2026-08-07T00:13:49.303331Z","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":"2026-08-07T00:13:52.893963Z","title":null,"venue":null,"work_id":"a39f62b4-771b-4228-b640-07fcbc950487","year":2026},"citing_paper":{"arxiv_id":"2608.01563","last_updated":"2026-08-03T00:42:55Z","snapshot_observed_at":"2026-08-07T21:39:09.614819Z","submitted_at":"2026-08-03T00:42:55Z","title":"Meganeura: Portable GPU Training and Inference through Vulkan and Metal","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T00:13:49.413208Z"},"links":{"citing_paper":"/paper/2608.01563"},"observation_digest":"sha256:5726098f8adaa551f6ae491fc075c0ba67be42231119822720ee1552dc5ac2ee","observation_id":"94cfcd34-fd9d-46ab-83ae-774eebbf6992","resolution":{"observed_at":"2026-08-07T00:13:53.020387Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.10104","last_updated":"2025-08-13T18:00:55Z","snapshot_observed_at":"2026-07-06T22:12:35.584339Z","submitted_at":"2025-08-13T18:00:55Z","title":"DINOv3","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.10104","snapshot_observed_at":"2026-08-07T00:13:49.545448Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.01563","last_updated":"2026-08-03T00:42:55Z","snapshot_observed_at":"2026-08-07T21:39:09.614819Z","submitted_at":"2026-08-03T00:42:55Z","title":"Meganeura: Portable GPU Training and Inference through Vulkan and Metal","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T00:13:49.545448Z"},"links":{"cited_paper":"/paper/2508.10104","citing_paper":"/paper/2608.01563"},"observation_digest":"sha256:1d771e9adbdbeec329ca9e63c168423a27058ef15c4c31421718eaa81ad06e9b","observation_id":"c41be673-fa93-4507-8f6b-63bea2d72bc5","resolution":{"observed_at":"2026-08-07T00:13:49.545448Z","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":"2026-08-07T00:13:52.604371Z","title":"Gupta, Sarah Sirajuddin, D","venue":null,"work_id":"d883a2d5-44fb-4ed8-b699-8e3c271f189d","year":2019},"citing_paper":{"arxiv_id":"2608.01563","last_updated":"2026-08-03T00:42:55Z","snapshot_observed_at":"2026-08-07T21:39:09.614819Z","submitted_at":"2026-08-03T00:42:55Z","title":"Meganeura: Portable GPU Training and Inference through Vulkan and Metal","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T00:13:49.688254Z"},"links":{"citing_paper":"/paper/2608.01563"},"observation_digest":"sha256:098ca6ab4885e2adda6794ba193ea4dce48a2466006da93fb7df006134d7417c","observation_id":"c6c34341-f864-4b52-ba47-9c38d9a1f2bd","resolution":{"observed_at":"2026-08-07T00:13:52.735951Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:13:52.333610Z","title":"Pure tensor pro- gram rewriting via access patterns","venue":null,"work_id":"73710642-d117-483c-a9ef-3c27a4aca36f","year":2021},"citing_paper":{"arxiv_id":"2608.01563","last_updated":"2026-08-03T00:42:55Z","snapshot_observed_at":"2026-08-07T21:39:09.614819Z","submitted_at":"2026-08-03T00:42:55Z","title":"Meganeura: Portable GPU Training and Inference through Vulkan and Metal","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T00:13:49.835775Z"},"links":{"citing_paper":"/paper/2608.01563"},"observation_digest":"sha256:902597d8023d3f461cc7a0ebcf004fe6f0edfd8d8fac65d5cc2048817bde6975","observation_id":"920ec220-7784-41ca-bf22-aa2aadd9bbe6","resolution":{"observed_at":"2026-08-07T00:13:52.442356Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:13:52.070032Z","title":null,"venue":null,"work_id":"b6665b41-61aa-4dfa-87dc-c8f4a7375bab","year":2019},"citing_paper":{"arxiv_id":"2608.01563","last_updated":"2026-08-03T00:42:55Z","snapshot_observed_at":"2026-08-07T21:39:09.614819Z","submitted_at":"2026-08-03T00:42:55Z","title":"Meganeura: Portable GPU Training and Inference through Vulkan and Metal","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T00:13:49.989474Z"},"links":{"citing_paper":"/paper/2608.01563"},"observation_digest":"sha256:ffef2093fdd77fec051adc2f8b90cd191c9580df97f154512b4730547a7fab08","observation_id":"5f53d54e-4152-4387-ade4-07c1e9cd8b8c","resolution":{"observed_at":"2026-08-07T00:13:52.228382Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:13:51.842675Z","title":"egg: Fast and extensible equality saturation.Pro- ceedings of the ACM on Programming Languages, 5(POPL), 2021","venue":null,"work_id":"25b40d3c-8d72-42e8-a36d-a30741a68c44","year":2021},"citing_paper":{"arxiv_id":"2608.01563","last_updated":"2026-08-03T00:42:55Z","snapshot_observed_at":"2026-08-07T21:39:09.614819Z","submitted_at":"2026-08-03T00:42:55Z","title":"Meganeura: Portable GPU Training and Inference through Vulkan and Metal","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T00:13:50.159321Z"},"links":{"citing_paper":"/paper/2608.01563"},"observation_digest":"sha256:6af797f7560f5d25f5a887c702fe3af7c50bddbe4834c36c539fb91533010f56","observation_id":"eef76ac2-9543-4186-a073-cf128763994f","resolution":{"observed_at":"2026-08-07T00:13:51.925902Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:13:51.570532Z","title":"Equal- ity saturation for tensor graph superoptimization","venue":null,"work_id":"c2a17663-3f1b-4730-86b8-fd7958ced234","year":2021},"citing_paper":{"arxiv_id":"2608.01563","last_updated":"2026-08-03T00:42:55Z","snapshot_observed_at":"2026-08-07T21:39:09.614819Z","submitted_at":"2026-08-03T00:42:55Z","title":"Meganeura: Portable GPU Training and Inference through Vulkan and Metal","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T00:13:50.304646Z"},"links":{"citing_paper":"/paper/2608.01563"},"observation_digest":"sha256:0a4c41bd4242fd28bd26d6470fdcc2526c321bb787046803c979f9a7ea8ee6eb","observation_id":"7f37b61a-fe2f-4ed4-97ef-e0c2424ffa51","resolution":{"observed_at":"2026-08-07T00:13:51.708159Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.04759","last_updated":"2023-03-08T17:51:13Z","snapshot_observed_at":"2026-07-06T15:00:17.108271Z","submitted_at":"2023-03-08T17:51:13Z","title":"RAF: Holistic Compilation for Deep Learning Model Training","version":1},"cited_work":{"arxiv_id":"2303.04759","doi":null,"metadata_source":"pith","pith_arxiv_id":"2303.04759","snapshot_observed_at":"2026-08-07T00:13:50.724968Z","title":"RAF: Holistic Compilation for Deep Learning Model Training","venue":"cs.LG","work_id":"1a8fb997-e451-4017-975a-dbe21d97b5e8","year":2023},"citing_paper":{"arxiv_id":"2608.01563","last_updated":"2026-08-03T00:42:55Z","snapshot_observed_at":"2026-08-07T21:39:09.614819Z","submitted_at":"2026-08-03T00:42:55Z","title":"Meganeura: Portable GPU Training and Inference through Vulkan and Metal","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T00:13:50.416417Z"},"links":{"cited_paper":"/paper/2303.04759","citing_paper":"/paper/2608.01563"},"observation_digest":"sha256:1d7ab83e3173199eb0d11cfb21e9d86c3468ae38fa2e7507acdeca4b1bdde5e3","observation_id":"8126837c-7fe6-49ff-9230-6f420a32e482","resolution":{"observed_at":"2026-08-07T00:13:50.836972Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T00:13:51.367313Z","title":"Better together: Unifying data- log and equality saturation","venue":null,"work_id":"67725056-4a84-42f5-acb7-456ee6988b11","year":2023},"citing_paper":{"arxiv_id":"2608.01563","last_updated":"2026-08-03T00:42:55Z","snapshot_observed_at":"2026-08-07T21:39:09.614819Z","submitted_at":"2026-08-03T00:42:55Z","title":"Meganeura: Portable GPU Training and Inference through Vulkan and Metal","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T00:13:50.542015Z"},"links":{"citing_paper":"/paper/2608.01563"},"observation_digest":"sha256:ae26431d310623912c48e0c7c26e080cf51bb1f3b4a4a32e004d459a5353c536","observation_id":"5162f1e1-516f-4a93-ba45-09d00da883f7","resolution":{"observed_at":"2026-08-07T00:13:51.437426Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2608.01563","last_updated":"2026-08-03T00:42:55Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T21:39:09.614819Z","submitted_at":"2026-08-03T00:42:55Z","title":"Meganeura: Portable GPU Training and Inference through Vulkan and Metal"},"reference_resolution":{"displayed":26,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":10,"verified_exact":2,"verified_fuzzy":14},"total_outbound_references":26},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 0 inbound Pith citation observations for arXiv:2608.01563."}