Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-18T01:59:30.583027Z
Paper Citation Record · LEDGER
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators
As of 11 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 4 inbound Pith citation observations for arXiv:2511.03092.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-05-19T16:41:30.021302Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-05-19T16:42:39.697093Z
Reference resolution
30 of 30 outbound references displayed
- verified exact9
- verified fuzzy0
- unresolved0
- parse uncertain0
- malformed identifier1
- metadata mismatch20
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 99981bc5-d0a4-49de-a7c1-f551b1b376a8 · outbound
This paper cites SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills
Reference 1
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T02:00:39.372114Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation d52dde91-7d46-4ab9-9939-5fd516255bac · outbound
This paper cites GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints
Reference 2
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T02:00:39.419974Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 65fa7184-6bdb-4b0e-b740-c716fab62ecf · outbound
This paper cites LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding
Reference 3
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T02:00:39.367043Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 8059ce83-f165-464a-a6e8-afa35de30d8a · outbound
This paper cites Titans: Learning to Memorize at Test Time.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators Titans: Learning to Memorize at Test Time
Reference 4
- Resolution
- verified exact
- local_arxiv, observed 2026-05-18T02:00:39.426911Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 6f074476-8bfb-4f69-a980-94e902b0d96c · outbound
This paper cites Longformer: The Long-Document Transformer.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators Longformer: The Long-Document Transformer
Reference 5
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T02:00:39.362089Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation eaeb9162-6276-4cb3-83bc-47e6f87bd4d4 · outbound
This paper cites Generating Long Sequences with Sparse Transformers.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators Generating Long Sequences with Sparse Transformers
Reference 6
- Resolution
- verified exact
- local_arxiv, observed 2026-05-18T02:00:39.317879Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation be0f46fd-d8bc-4789-910d-e1efccc5c45f · outbound
This paper cites FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
Reference 7
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T02:00:39.344554Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 7ec75e2a-6e6f-4574-9ee9-7cb701263abb · outbound
This paper cites DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
Reference 8
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T02:00:39.357328Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 9e6914be-a189-47f1-abbe-1c3ef59c6370 · outbound
This paper cites Cartridges: Lightweight and general-purpose long context representations via self-study.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators Cartridges: Lightweight and general-purpose long context representations via self-study
Reference 9
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-18T02:00:39.432146Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 2ce07502-b386-4659-abfc-e70360970fe4 · outbound
This paper cites The Llama 3 Herd of Models.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators The Llama 3 Herd of Models
Reference 10
- Resolution
- verified exact
- local_arxiv, observed 2026-05-18T02:00:39.340093Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 4ad8e13b-fbb1-4987-90f5-f33cad7e6545 · outbound
This paper cites RULER: What's the Real Context Size of Your Long-Context Language Models?.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators RULER: What's the Real Context Size of Your Long-Context Language Models?
Reference 11
- Resolution
- verified exact
- local_arxiv, observed 2026-05-18T02:00:39.322244Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 368adab0-7116-4192-880e-f38329d7758e · outbound
This paper cites Kimi K2: Open Agentic Intelligence.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators Kimi K2: Open Agentic Intelligence
Reference 12
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T02:00:39.313481Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 17671d48-a744-4796-a3d8-e32581783177 · outbound
This paper cites Reformer: The Efficient Transformer.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators Reformer: The Efficient Transformer
Reference 13
- Resolution
- verified exact
- local_arxiv, observed 2026-05-18T02:00:39.348262Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation f76bc791-9b01-41e9-a8b3-5726bb1c4118 · outbound
This paper cites Efficient Memory Management for Large Language Model Serving with PagedAttention.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators Efficient Memory Management for Large Language Model Serving with PagedAttention
Reference 14
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T02:00:39.352517Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 433183e5-5817-468f-a0d6-d6e3d241614c · outbound
This paper cites SnapKV: LLM Knows What You are Looking for Before Generation.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators SnapKV: LLM Knows What You are Looking for Before Generation
Reference 15
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T02:00:39.335562Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation cf40428b-2d64-406e-8887-ca66295ecf4c · outbound
This paper cites Choquette.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators Choquette
Reference 16
- Resolution
- malformed identifier
- doi_truncated, observed 2026-05-18T02:00:38.288794Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 4c354e2d-1044-45a5-9da8-613e0b707664 · outbound
This paper cites gpt-oss-120b & gpt-oss-20b Model Card.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators gpt-oss-120b & gpt-oss-20b Model Card
Reference 17
- Resolution
- verified exact
- local_arxiv, observed 2026-05-18T02:00:39.303801Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 6b7ab900-8ee3-4313-bfcd-d1420eb90ad0 · outbound
This paper cites doi: 10.1109/HCS61935.2024.10664717.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators doi: 10.1109/HCS61935.2024.10664717
Reference 18
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-18T02:00:38.284771Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 1a225cb9-ab8e-4e76-b080-baf954915d29 · outbound
This paper cites Tacos: Topology-aware collective algorithm synthesizer for distributed machine learning.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators Tacos: Topology-aware collective algorithm synthesizer for distributed machine learning
Reference 19
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-18T02:00:38.293875Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation e09c8e9c-8d95-48f7-ae73-7bea46641f32 · outbound
This paper cites Gemma 2: Improving Open Language Models at a Practical Size.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators Gemma 2: Improving Open Language Models at a Practical Size
Reference 20
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T02:00:39.330829Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 670d5b0e-c687-4816-846f-635f0eb31712 · outbound
This paper cites Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference
Reference 21
- Resolution
- verified exact
- local_arxiv, observed 2026-05-18T02:00:39.384869Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 0a7c5652-c170-428a-b664-b3fd6c392469 · outbound
This paper cites Attention Is All You Need.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators Attention Is All You Need
Reference 22
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T02:00:39.414791Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 04bf6933-e0ac-46ce-b63b-f50462c50b30 · outbound
This paper cites LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference
Reference 23
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T02:00:39.392292Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation d937a816-845c-44f6-91b9-81f4d3b09708 · outbound
This paper cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Reference 24
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T02:00:39.403509Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 42a42cee-404a-4b8d-8863-7a5cea8b9f22 · outbound
This paper cites Qwen3 Technical Report.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators Qwen3 Technical Report
Reference 25
- Resolution
- verified exact
- local_arxiv, observed 2026-05-18T02:00:39.326713Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 340b09c5-e6e5-4fd1-9917-a726acd440ff · outbound
This paper cites Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention
Reference 26
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T02:00:39.378002Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation eedf346a-1ea6-457e-9850-f9559659ba58 · outbound
This paper cites Spargeattn: Accurate sparse attention accelerating any model inference.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators Spargeattn: Accurate sparse attention accelerating any model inference
Reference 27
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-18T02:00:39.410021Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 0b58d72a-6099-4f09-991f-47c904079b56 · outbound
This paper cites $\infty$Bench: Extending Long Context Evaluation Beyond 100K Tokens.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators $\infty$Bench: Extending Long Context Evaluation Beyond 100K Tokens
Reference 28
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-18T02:00:39.299754Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 460379ee-66f2-47ce-81a0-e9e4a38deb76 · outbound
This paper cites H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models
Reference 29
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T02:00:39.309134Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation a713be5b-4cec-48fd-b760-e990a3df4b86 · outbound
This paper cites SGLang: Efficient Execution of Structured Language Model Programs.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators SGLang: Efficient Execution of Structured Language Model Programs
Reference 30
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T02:00:39.397829Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Pith citing papers
Observation e829cb08-ae8e-4dbd-b782-834e68d6103a · inbound
KV Cache Offloading for Context-Intensive Tasks cites this paper.
KV Cache Offloading for Context-Intensive Tasks SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators
Reference 25
- Resolution
- verified exact
- local_arxiv, observed 2026-05-11T08:06:01.095894Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 93f452a5-a4c8-499b-95c8-86e6ac9d5f5f · inbound
KV Cache Offloading for Context-Intensive Tasks cites this paper.
KV Cache Offloading for Context-Intensive Tasks SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators
Reference 25
- Resolution
- verified exact
- local_arxiv, observed 2026-05-11T04:20:56.323193Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 4c854c8c-7cdc-44e2-b359-5affd33eaa5c · inbound
KV Cache Offloading for Context-Intensive Tasks cites this paper.
KV Cache Offloading for Context-Intensive Tasks SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators
Reference 25
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T07:37:29.371449Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation fc5f6aa2-7d31-433c-a715-078373a41401 · inbound
KV Cache Offloading for Context-Intensive Tasks cites this paper.
KV Cache Offloading for Context-Intensive Tasks SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators
Reference 25
- Resolution
- verified exact
- local_arxiv, observed 2026-05-19T16:42:39.698754Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.