Paper Citation Record · LEDGER

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators

As of 8 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2608.00325.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2608.00325 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T00:47:05.392530Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

37 of 37 outbound references displayed

verified exact0
verified fuzzy0
unresolved37
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 54b75400-f421-4bb0-b413-6c80b2540c05 · outbound

This paper cites The llama 3 herd of models,.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators The llama 3 herd of models,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:02.401642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d779eef8-493d-4f0c-8aa1-369225d89d30 · outbound

This paper cites Deep Learning Recommendation Model for Personalization and Recommendation Systems.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators Deep Learning Recommendation Model for Personalization and Recommendation Systems

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:02.470335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6418a0d2-93de-4fb6-9838-fa752f8321c6 · outbound

This paper cites DHEN: A Deep and Hierarchical Ensemble Network for Large-Scale Click-Through Rate Prediction.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators DHEN: A Deep and Hierarchical Ensemble Network for Large-Scale Click-Through Rate Prediction

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:02.574185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee076fac-27a6-4d70-9f27-b22442f9b2e2 · outbound

This paper cites Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:02.691628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dea0b3ea-a5e7-4017-b46d-0f9c2b312d31 · outbound

This paper cites [Online].

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators [Online]

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:02.822007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9220211f-efd2-4490-8f70-c4d582aaf6c4 · outbound

This paper cites The Design Process for Google’s Training Chips: TPUv2 and TPUv3,.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators The Design Process for Google’s Training Chips: TPUv2 and TPUv3,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:02.932509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation faf0e644-4760-4151-bf8a-a297a87e6f82 · outbound

This paper cites Think Fast: A Tensor Streaming Processor (TSP) for Accelerating Deep Learning Workloads,.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators Think Fast: A Tensor Streaming Processor (TSP) for Accelerating Deep Learning Workloads,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:03.053502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 468b03b5-27cc-487d-8008-a498d84f4289 · outbound

This paper cites Accelerating Scientific Applica- tions With SambaNova Reconfigurable Dataflow Architecture,.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators Accelerating Scientific Applica- tions With SambaNova Reconfigurable Dataflow Architecture,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:03.145805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cc1ee30-e1a5-4670-b605-82c501174857 · outbound

This paper cites Distributed Training of Large Language Models on A WS Trainium,.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators Distributed Training of Large Language Models on A WS Trainium,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:03.201041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d2d9dbc-a6d9-49d5-84f2-d8d2a0247157 · outbound

This paper cites Blackhole & TT-Metalium: The Standalone AI Computer and its Programming Model ,.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators Blackhole & TT-Metalium: The Standalone AI Computer and its Programming Model ,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:03.345146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ff9bc6a-6410-46fc-b37d-f156a742488c · outbound

This paper cites Cerebras Architecture Deep Dive: First Look Inside the HW/SW Co-Design for Deep Learning : Cerebras Systems ,.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators Cerebras Architecture Deep Dive: First Look Inside the HW/SW Co-Design for Deep Learning : Cerebras Systems ,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:03.409167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51ff44ee-eddd-4e0c-bc5a-d610c060f8e9 · outbound

This paper cites Meta’s Second Generation AI Chip: Model-Chip Co-Design and Productionization Experiences,.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators Meta’s Second Generation AI Chip: Model-Chip Co-Design and Productionization Experiences,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:03.469525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 867bf636-0994-4dfd-8701-90f76d07b64a · outbound

This paper cites Development repository for the triton language and compiler,.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators Development repository for the triton language and compiler,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:03.575974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11be51dc-b94b-47c3-a38c-4b7054257e7c · outbound

This paper cites MTIA: First Generation Silicon Targeting Meta’s Recommendation Systems,.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators MTIA: First Generation Silicon Targeting Meta’s Recommendation Systems,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:03.665369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89de7732-5a36-43f9-a1a1-6a852995b315 · outbound

This paper cites FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning,.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:03.710441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca9d25e3-043c-47c4-a2f1-673327c2b545 · outbound

This paper cites FlagOpen/FlagGems: An operator library for large language models implemented in the Triton language,.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators FlagOpen/FlagGems: An operator library for large language models implemented in the Triton language,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:03.800953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 078b7779-74fd-4338-a676-fb010e9bd7e9 · outbound

This paper cites FlexAt- tention: The Flexibility of PyTorch with the Per- formance of FlashAttention,.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators FlexAt- tention: The Flexibility of PyTorch with the Per- formance of FlashAttention,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:03.888344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46fa7478-fb17-42d4-9aee-976ea380cacf · outbound

This paper cites gpt-oss-120b & gpt-oss-20b Model Card,.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators gpt-oss-120b & gpt-oss-20b Model Card,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:03.956161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1175543-35f0-4d3a-abb4-7e4a1320d1a6 · outbound

This paper cites Helion: A High-Level DSL for Performant and Portable ML Kernels,.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators Helion: A High-Level DSL for Performant and Portable ML Kernels,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:04.124567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fdd0a41-b833-4ed8-acb8-e376164aefac · outbound

This paper cites [Online].

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators [Online]

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:04.225292Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1c357bf-4303-426f-8902-3d0bb75370f4 · outbound

This paper cites Tlx - triton low-level language extensions,.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators Tlx - triton low-level language extensions,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:04.256742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a69f147-6c47-4372-8b14-e2bbe77cd0c8 · outbound

This paper cites Introduction to Gluon,.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators Introduction to Gluon,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:04.422689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e95eb51-d5f1-4da9-93a6-604723e3fb51 · outbound

This paper cites Available: https://github.com/ facebookexperimental/triton/tree/tlx.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators Available: https://github.com/ facebookexperimental/triton/tree/tlx

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:04.340137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb3e5788-e5b5-4db0-9e4b-1cc80b08f242 · outbound

This paper cites CuTe DSL,.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators CuTe DSL,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:04.498697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e30efcb4-067d-4f4a-b956-de293026555e · outbound

This paper cites A WS Neuron adds support for NKI and NXD for training with JAX,.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators A WS Neuron adds support for NKI and NXD for training with JAX,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:04.722130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d65e691a-ccc2-4f86-b295-5f52761c23f4 · outbound

This paper cites TileLang: A Composable Tiled Programming Model for AI Systems.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators TileLang: A Composable Tiled Programming Model for AI Systems

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:04.618034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95f78254-d352-48f5-aaf4-eb894ff63f27 · outbound

This paper cites cutile, the new/old kid on the block: Python programming models for gpus,.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators cutile, the new/old kid on the block: Python programming models for gpus,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:04.668618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02e1d424-56ce-4d40-b0a0-b84cc1bb7f29 · outbound

This paper cites MLIR: A Compiler Infrastructure for the End of Moore's Law.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators MLIR: A Compiler Infrastructure for the End of Moore's Law

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:04.979536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eefbfafc-ffc6-43ec-82c3-544c9fc74fd1 · outbound

This paper cites PyTorch 2: Faster Machine Learning Through Dynamic Python Bytecode Transformation and Graph Compilation,.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators PyTorch 2: Faster Machine Learning Through Dynamic Python Bytecode Transformation and Graph Compilation,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:04.809349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba46a84e-18f2-46f3-ab35-d501bc920c01 · outbound

This paper cites Halide: a language and compiler for optimizing parallelism, locality, and recomputation in image processing pipelines,.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators Halide: a language and compiler for optimizing parallelism, locality, and recomputation in image processing pipelines,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:04.894634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f622ecb8-5f32-4c58-b524-67397bb7e080 · outbound

This paper cites risc-v-spec,.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators risc-v-spec,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:05.191679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 439f7e3d-a022-48ff-a94d-93b6ba0fed41 · outbound

This paper cites triton-shared: A shared middle-layer for the Triton Compiler,.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators triton-shared: A shared middle-layer for the Triton Compiler,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:05.060842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aae04403-a6ca-41f1-984a-456551dd0121 · outbound

This paper cites Software pipelining,.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators Software pipelining,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:05.113879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b8792b0-645a-4893-b33d-9b977d23d4fa · outbound

This paper cites Triton: Extern Func- tions Tutorial,.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators Triton: Extern Func- tions Tutorial,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:05.392530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00a9750a-216f-41aa-aa20-d32e63073369 · outbound

This paper cites MLIR: Scal- ing Compiler Infrastructure for Domain Specific Computation,.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators MLIR: Scal- ing Compiler Infrastructure for Domain Specific Computation,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:05.283063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab501b72-00a1-4a81-bab5-1e461ea78651 · outbound

This paper cites Attention is All you Need,.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators Attention is All you Need,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:05.318349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49ed9225-3bde-4fee-982a-7b95cdf915c3 · outbound

This paper cites gpt-oss-120b & gpt-oss-20b Model Card.

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators gpt-oss-120b & gpt-oss-20b Model Card

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-04T00:47:04.035492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.