Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-15T23:44:05.339945Z
Paper Citation Record · LEDGER
As of 19 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 1 inbound Pith citation observation for arXiv:2505.04075.
A citation records a reference. It does not transfer a finding from one paper to another.
Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-15T23:44:05.339945Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-06-27T07:29:14.923431Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-07-03T13:48:21.352760Z
52 of 52 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation 924af6c5-e77d-43b5-8abe-fea463e93b69 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress , " * write output.state after.block = add.period write newline
Reference 1
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 96d788e4-a671-44a2-a7c5-4b76e38a8c5e · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress write newline
Reference 2
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3c002413-6780-4c28-9d06-65469d378403 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Unresolved cited work
Reference 3
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 98ae5058-2664-4829-b1ee-70e94910317f · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Unresolved cited work
Reference 4
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 8c80f81b-87b9-46fe-b060-fc2114f6de2a · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Unresolved cited work
Reference 5
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation e510b5ca-6d47-48bb-b14d-027456bbd52b · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Layer Normalization
Reference 6
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6b8e6482-1c49-4159-b24e-3c5af223c1e9 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Generating Long Sequences with Sparse Transformers
Reference 7
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation eb166e9c-6894-42c1-9870-57e466a35466 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress PaLM: Scaling Language Modeling with Pathways
Reference 8
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f8c083f7-1cd1-470f-9c4a-3a385cb3c3b7 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
Reference 9
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f0e696e6-1753-411e-896e-3960a94d7e10 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
Reference 10
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c8065a29-2f95-40ab-a646-c97b932ff03c · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
Reference 11
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4350bec1-0ace-4272-981b-2481d0a3351e · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress AI capabilities can be significantly improved without expensive retraining
Reference 12
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b786e4f5-696b-4e0f-9047-18cdd4ea692c · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Reference 13
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a6fb1829-1d0f-4077-9eee-7e964fc9bb0f · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress DeepSeek-V3 Technical Report
Reference 14
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e9b7c322-0bc3-4446-bc4c-cf2a0838527f · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Reference 15
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f663d9b6-030a-4803-ae09-9bb4b2b96338 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens
Reference 16
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 49317eec-a6f2-4d33-bfae-9f9ad7bd97b3 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Scaling Laws for Acoustic Models
Reference 17
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 24e6a4ca-0700-4fc3-93a9-7a622679c47e · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Algorithmic progress in computer vision
Reference 18
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 962a745a-3992-44ba-baca-cc1d9d5a2380 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
Reference 19
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5023fe0b-ad7c-4404-8921-287efb53bc13 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Unresolved cited work
Reference 20
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 40306aa9-bebf-4eae-8e2e-519aad42f735 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress The Pile: An 800GB Dataset of Diverse Text for Language Modeling
Reference 21
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9c8e9558-96f7-4224-bcc3-891730c359d0 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Whack-a-Chip: The Futility of Hardware-Centric Export Controls
Reference 22
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation f67d6553-8e6b-477e-980f-8d25a2885ec1 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Unresolved cited work
Reference 23
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation f26529a5-b2ca-482e-a11f-8d75abee9bda · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Algorithmic progress in language models
Reference 24
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation adb61e52-acf3-4b25-821c-85a2b597361d · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress A.; Jordan, M
Reference 25
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 1d516883-6327-49bf-8354-67bc3c2be3b7 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Dissecting the NVIDIA Volta GPU Architecture via Microbenchmarking
Reference 26
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f9862fbf-a608-4560-abd5-aee124f41df8 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Scaling Laws for Neural Language Models
Reference 27
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9492fdaa-5389-48e8-b9f3-835a2d5fcdb7 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Unresolved cited work
Reference 28
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation d8600f0b-278f-4627-b028-68e8864a0d94 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding
Reference 29
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c2ef684d-6aed-4153-a9b1-05746d924386 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress StarCoder: may the source be with you!
Reference 30
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 768f5be3-2034-4039-9b16-13a9100661c2 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Unresolved cited work
Reference 31
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation abb9305c-4496-42ac-86f5-b12a52b165e3 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Falcon2-11B Technical Report
Reference 32
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8996375b-b9c2-4c3b-9652-4f9536ffa44a · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMs
Reference 33
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6e329ae9-a48a-4c6d-89db-86892c0dad24 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Unresolved cited work
Reference 34
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation e858aad1-a38e-481d-a34c-38e1ef640f80 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Unresolved cited work
Reference 35
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 5c36b3f7-b7f7-412f-b09b-fc0a0e0f0f19 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation
Reference 36
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3e5cb9f7-94ef-4ebb-85ef-8570c84327b8 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Unresolved cited work
Reference 37
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 518e6558-fb9e-4735-953e-eb21706cefae · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Unresolved cited work
Reference 38
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation dc6c4e19-3f4a-496c-b39c-4756d18e5122 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Unresolved cited work
Reference 39
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation bd915aff-ab75-472c-b246-6d306af88591 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Unresolved cited work
Reference 40
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 00e9d135-f747-440c-a21e-a40b53c800b9 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Unresolved cited work
Reference 41
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 39902fdb-bf12-4f84-8441-d5f6cd11851f · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Unresolved cited work
Reference 42
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 57b3e739-ba9c-43c9-9a8d-aa2b95c86eb0 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision
Reference 43
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7fcd377b-5bc8-41da-a46d-ca21a4e17ceb · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Fast Transformer Decoding: One Write-Head is All You Need
Reference 44
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f866243a-d3c9-4edc-bb4f-b5bf0c43e3f9 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
Reference 45
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0cb61b15-ede0-426c-a4d3-c29235e50d2d · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress RoFormer: Enhanced Transformer with Rotary Position Embedding
Reference 46
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1955cc03-f4cb-490a-b9f5-eb56e1ed9d86 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress N.; Kaiser, .; and Polosukhin, I
Reference 47
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 0fb456bc-14f7-44b9-ac31-1d564e49f6e9 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Experts
Reference 48
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 715904ec-b9c8-4c1e-83f4-e678d5a32303 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Reference 49
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bb731f50-9a33-4cf7-b04a-207825dec488 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention
Reference 50
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b19912a7-ea17-4de6-a305-e598e089961e · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress Root Mean Square Layer Normalization
Reference 51
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8d973f5d-7d9d-4e73-b104-96fac88d3c27 · outbound
Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress A Survey of Large Language Models
Reference 52
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2169f9a8-dce1-4e9f-94b9-474b72f230a7 · inbound
Multi-Bitwidth Quantization for LLMs Using Additive Codebooks Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress
Reference 95
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.