Paper Citation Record · LEDGER

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators

As of 23 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 5 inbound Pith citation observations for arXiv:2602.22647.

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

pith.paper-citation-record.v1
2602.22647 v2

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T20:42:44.668233Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T20:27:57.569744Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-05T04:00:39.587320Z

Reference resolution

37 of 37 outbound references displayed

verified exact0
verified fuzzy0
unresolved36
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation bc5b190e-b8e7-436c-9b1c-bb6b34c5fd80 · outbound

This paper cites an unresolved cited work.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:39.211802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5914b857-63f6-4988-9362-4a18cf7b715f · outbound

This paper cites 2018.JAX: composable transformations of Python+NumPy programs.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators 2018.JAX: composable transformations of Python+NumPy programs

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:39.315595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bc7c4ff-520d-433e-83c7-f65bfb472673 · outbound

This paper cites Adams, and Emre Sargin.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Adams, and Emre Sargin

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:39.516267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e2644e2-bf44-4706-8c2e-b463fede8343 · outbound

This paper cites Fu, Stefano Ermon, Atri Rudra, and Christopher Ré.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Fu, Stefano Ermon, Atri Rudra, and Christopher Ré

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:39.725059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdc54eda-666b-4e78-8ce8-677cdee3f862 · outbound

This paper cites OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:40.053155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c858ea26-273f-402a-b46a-1ccac3d240c7 · outbound

This paper cites an unresolved cited work.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:40.220428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67109333-b2d8-45ea-82ac-bfd8d3ac9a40 · outbound

This paper cites Lindgren, Quan Geng, David Simcha, Felix Chern, and Sanjiv Kumar.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Lindgren, Quan Geng, David Simcha, Felix Chern, and Sanjiv Kumar

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:40.424662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2528011-db16-4030-9475-80f7a625b85b · outbound

This paper cites an unresolved cited work.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:40.641210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29e97188-57f7-4636-81a3-feda13ef8cb4 · outbound

This paper cites an unresolved cited work.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:40.843519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a3722f3-e874-4dbe-b2c8-ddf22a9ddf7f · outbound

This paper cites 2024.Flax: A neural network library and ecosystem for JAX.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators 2024.Flax: A neural network library and ecosystem for JAX

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:40.990738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 725ee176-52fe-492b-9dc5-7c42120d4366 · outbound

This paper cites an unresolved cited work.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:41.096660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69e37131-477c-42aa-82a3-7016f6e12bd4 · outbound

This paper cites an unresolved cited work.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Unresolved cited work

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:41.194057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 831e7cb9-0d91-40fd-8481-11c6638a2fdf · outbound

This paper cites Jouppi, Cliff Young, Nishant Patil, David A.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Jouppi, Cliff Young, Nishant Patil, David A

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:41.435141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 720de114-1376-4bb3-a635-eddef72737c5 · outbound

This paper cites an unresolved cited work.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:41.539211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e0606e2-6c9d-4cb2-8211-bf2cab7a0411 · outbound

This paper cites Gemma 3 Technical Report.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Gemma 3 Technical Report

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:41.661732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebc460a8-87ee-4063-aeb9-7132e8b816bc · outbound

This paper cites Bader, Aydın Buluç, Franz Franchetti, John R.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Bader, Aydın Buluç, Franz Franchetti, John R

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:41.748200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b04f637-935d-495b-8def-d54c7d462afc · outbound

This paper cites Automata-based constraints for language model decoding.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Automata-based constraints for language model decoding

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:41.830446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 704f64d2-a12c-4a9a-af32-ac48fb54a7a0 · outbound

This paper cites an unresolved cited work.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:41.985027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e9e8ead-58a9-4097-a793-9b25079a6492 · outbound

This paper cites an unresolved cited work.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:42.136699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f091c745-2c56-454a-883e-d2b3947bff0d · outbound

This paper cites an unresolved cited work.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:42.238178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0acb63dd-3b87-460b-9561-0f68ba8a2230 · outbound

This paper cites an unresolved cited work.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:42.343978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2593908b-17f0-4f2f-b53d-c1eadd72d94d · outbound

This paper cites Smith, and Yejin Choi.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Smith, and Yejin Choi

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:42.504717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 230ed146-f51b-4271-ad5e-70417386a0ac · outbound

This paper cites Synchromesh: Reliable code generation from pre-trained language models.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Synchromesh: Reliable code generation from pre-trained language models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:42.678596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29616544-2490-4612-9a12-a5e7ea4ec85c · outbound

This paper cites Recommender Systems with Generative Retrieval.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Recommender Systems with Generative Retrieval

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:42.844104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a83dd41f-215e-4a61-86dc-ebdba787cca5 · outbound

This paper cites an unresolved cited work.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Unresolved cited work

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:43.024242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ef08b99-004a-4332-9f8e-523ce0d6dd37 · outbound

This paper cites an unresolved cited work.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:43.219118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b61cd463-c645-4ea9-9478-d14f0d5f3f72 · outbound

This paper cites SOAR: Improved Indexing for Approximate Nearest Neighbor Search.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators SOAR: Improved Indexing for Approximate Nearest Neighbor Search

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:43.375846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7940073a-67da-4a0b-83c7-27cdc3a2cb1d · outbound

This paper cites Transformer Memory as a Differentiable Search Index.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Transformer Memory as a Differentiable Search Index

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:43.482084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e18d8979-cf8b-4d70-a356-d5cfdc9ae137 · outbound

This paper cites Gomez, Lukasz Kaiser, and Illia Polosukhin.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Gomez, Lukasz Kaiser, and Illia Polosukhin

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:43.640905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac00d3e5-6349-451c-aac4-9ec86a2cc9d9 · outbound

This paper cites an unresolved cited work.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:43.819222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca182872-3609-4f6f-b789-78b9777295b4 · outbound

This paper cites an unresolved cited work.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Unresolved cited work

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:43.994307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7849806-ecc5-4b6a-9d47-a8d6639e53b3 · outbound

This paper cites Efficient and Asymptotically Unbiased Constrained Decoding for Large Language Models.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Efficient and Asymptotically Unbiased Constrained Decoding for Large Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:44.117497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84db747b-c40b-41f5-8e03-1902279b709e · outbound

This paper cites an unresolved cited work.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:44.272778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a635377d-ee4b-4614-8763-781391683c5c · outbound

This paper cites an unresolved cited work.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:44.412116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 876dfa7c-61f6-4a87-8d3a-3db53cb24f3d · outbound

This paper cites OneRec-V2 Technical Report.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators OneRec-V2 Technical Report

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:44.513735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d19b1876-6be0-438e-a05a-3716b4877246 · outbound

This paper cites ""Implementation of Hardware-Accelerated Constrained Decoding algorithms.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators ""Implementation of Hardware-Accelerated Constrained Decoding algorithms

Reference 37

Resolution: malformed identifier; no resolver link, observed 2026-08-02T20:42:44.668233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6d2a398-7827-449a-9c8d-d3ca0b736dea · outbound

This paper cites FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness.

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-02T20:42:39.854459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 052de851-b058-4f09-89e7-f14359352609 · inbound

CapsID: Soft-Routed Variable-Length Semantic IDs for Generative Recommendation cites this paper.

CapsID: Soft-Routed Variable-Length Semantic IDs for Generative Recommendation Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-07-22T01:22:20.900011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f702e618-053d-4e16-b03f-1798ca96847d · inbound

LLMs Need Encoders for Semantic IDs Too cites this paper.

LLMs Need Encoders for Semantic IDs Too Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-07-22T01:22:20.900011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8b814ea0-49fd-44f6-aaa6-6f6947a1668f · inbound

UniPinRec: Unifying Generative Retrieval and Ranking at Pinterest Scale cites this paper.

UniPinRec: Unifying Generative Retrieval and Ranking at Pinterest Scale Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-07-22T01:22:20.900011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 23901eda-0c74-46c8-a28f-4d3ef4473dda · inbound

LatticeBridge: Rare-Event Sequential Inference for Faithful Structured Sequence Synthesis cites this paper.

LatticeBridge: Rare-Event Sequential Inference for Faithful Structured Sequence Synthesis Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-07-22T01:22:20.900011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9594d763-b246-403e-8708-24bb2bb772c8 · inbound

Beyond Fixed Depths and Widths: Optimizing Textual Decoding Tries in LLM-based Generative Recommendation cites this paper.

Beyond Fixed Depths and Widths: Optimizing Textual Decoding Tries in LLM-based Generative Recommendation Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-01T20:27:57.569744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.