Paper Citation Record · LEDGER

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe

As of 11 August 2026, this Paper Citation Record lists 65 of 65 outbound references and 2 inbound Pith citation observations for arXiv:2412.19396.

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

pith.paper-citation-record.v1
2412.19396 v1

Coverage vector

measured 65 of 65 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T00:45:36.072796Z

measured 67 of 67 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:33:54.880840Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-12T06:31:24.706841Z

Reference resolution

65 of 65 outbound references displayed

verified exact3
verified fuzzy49
unresolved12
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 73a48c5f-5d88-4ccf-8d49-4b7204c7fffe · outbound

This paper cites Principal compo- nent analysis.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Principal compo- nent analysis

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.839768Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 930b6a8d-30f9-46fc-abed-c980215c43b9 · outbound

This paper cites Learning user interaction models for predicting web search result preferences.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Learning user interaction models for predicting web search result preferences

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.830495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 505cf66b-75ec-4ff0-9ba5-2e5a9976b835 · outbound

This paper cites A first-order algorithm for the a-optimal experimental design problem: a mathe- matical programming approach.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe A first-order algorithm for the a-optimal experimental design problem: a mathe- matical programming approach

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.821746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 946624a0-79a0-4e96-83a5-7760dff213b0 · outbound

This paper cites Best arm identification in multi-armed ban- dits.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Best arm identification in multi-armed ban- dits

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.811310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation eba99011-a564-4f1b-8118-efc839964e14 · outbound

This paper cites Fixed-budget best-arm iden- tification in structured bandits.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Fixed-budget best-arm iden- tification in structured bandits

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.801691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 518c7b9b-46f6-4128-a748-2c4ca279c30b · outbound

This paper cites Two-point step size gradient methods.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Two-point step size gradient methods

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T00:45:35.888835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 242af294-ce23-4769-8b92-bcf3a2761bce · outbound

This paper cites Convex Op- timization.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Convex Op- timization

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.787695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation dd716cd0-d739-42d2-8e5a-a4b51bcaaf46 · outbound

This paper cites Rank analysis of incomplete block designs: I.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Rank analysis of incomplete block designs: I

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.779321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 55068812-9180-4dbe-9901-fd1d64eff91a · outbound

This paper cites Pure exploration in multi-armed bandits problems.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Pure exploration in multi-armed bandits problems

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.771043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 453f6f5d-cbc5-4d96-a03a-fd10d120fdb0 · outbound

This paper cites Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T00:45:35.901723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b93440a-468d-44c5-8166-ecf173d41ca1 · outbound

This paper cites Bge m3-embedding: Multi- lingual, multi-functionality, multi-granularity text em- beddings through self-knowledge distillation, 2024.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Bge m3-embedding: Multi- lingual, multi-functionality, multi-granularity text em- beddings through self-knowledge distillation, 2024

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.762019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation b4a2617b-30a4-45ac-877f-3102566abb44 · outbound

This paper cites Active Preference Optimization for Sample Efficient RLHF.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Active Preference Optimization for Sample Efficient RLHF

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T00:45:35.909262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73b7c139-d7c9-40f5-92c9-4dab7ec5908b · outbound

This paper cites CVXPY: A Python-embedded modeling language for convex opti- mization.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe CVXPY: A Python-embedded modeling language for convex opti- mization

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.753350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 3efbfe66-296e-47ea-8d1a-f3cd32f3de94 · outbound

This paper cites Conditional gradi- ent algorithms with open loop step size rules.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Conditional gradi- ent algorithms with open loop step size rules

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.744562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 896a7941-36f1-4bc1-9846-4cd874d7fe21 · outbound

This paper cites A density-based algorithm for discov- ering clusters in large spatial databases with noise.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe A density-based algorithm for discov- ering clusters in large spatial databases with noise

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.735126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 2d5d74a0-768c-4498-b597-ddbf5bf53581 · outbound

This paper cites Elsevier, 2013.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Elsevier, 2013

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.726375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation a6e6bf70-f454-47e5-9693-42513eb6a3e8 · outbound

This paper cites An algorithm for quadratic programming.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe An algorithm for quadratic programming

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.717847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 6bc78a44-46ee-4350-a2fb-79d7a598df04 · outbound

This paper cites Enlargement methods for comput- ing the inverse matrix.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Enlargement methods for comput- ing the inverse matrix

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.708804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 4d8c5305-11ed-4043-bbda-77be463f6f77 · outbound

This paper cites Solving the optimal experiment design problem with mixed-integer convex methods.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Solving the optimal experiment design problem with mixed-integer convex methods

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T00:45:35.931597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40039037-f07d-4763-89e9-aee4a989c958 · outbound

This paper cites Cascading linear submodular bandits: Accounting for position bias and diversity in online learning to rank.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Cascading linear submodular bandits: Accounting for position bias and diversity in online learning to rank

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.701093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 58265661-b81e-4c07-bc48-77ddc47b4e8d · outbound

This paper cites Fidelity, soundness, and efficiency of interleaved comparison methods.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Fidelity, soundness, and efficiency of interleaved comparison methods

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.693085Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 53628f8a-55d0-46c2-8da6-242d6ae83d4d · outbound

This paper cites On- line evaluation for information retrieval.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe On- line evaluation for information retrieval

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.685233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation db83ee6a-2423-4227-b040-5ed8893f223d · outbound

This paper cites Revisiting frank-wolfe: Projection-free sparse convex optimization.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Revisiting frank-wolfe: Projection-free sparse convex optimization

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.676563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 885bae25-db46-4367-8cd3-36e84751bed5 · outbound

This paper cites Is pes- simism provably efficient for offline rl? In Interna- tional Conference on Machine Learning, pages 5084–.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Is pes- simism provably efficient for offline rl? In Interna- tional Conference on Machine Learning, pages 5084–

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.667230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation b77ac3fd-0a00-4d17-acf3-b3352b88eeda · outbound

This paper cites Beyond Reward: Offline Preference-guided Policy Optimization.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Beyond Reward: Offline Preference-guided Policy Optimization

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T00:45:35.949355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a84b77a-833b-4536-8e6a-3b17e1b965f2 · outbound

This paper cites Rank correlation methods.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Rank correlation methods

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.658085Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation b0321da2-070e-4837-bbef-b6d75704ba14 · outbound

This paper cites Frank-wolfe with subsampling oracle.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Frank-wolfe with subsampling oracle

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.648716Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 75f78b15-1355-4537-b17d-bd3ecead8dc0 · outbound

This paper cites Rounding of polytopes in the real number model of computation.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Rounding of polytopes in the real number model of computation

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.639459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation a95202aa-7b24-47f2-bd62-7c4f724bf185 · outbound

This paper cites Data-driven rank breaking for efficient rank aggregation.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Data-driven rank breaking for efficient rank aggregation

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.630624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation c228a665-3c0c-4161-be11-17d7c8226ccb · outbound

This paper cites Sequential minimax search for a max- imum.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Sequential minimax search for a max- imum

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.621105Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation c8c58908-8490-4ebe-b6cd-f3ddc1ca5a6c · outbound

This paper cites The equivalence of two extremum problems.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe The equivalence of two extremum problems

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.612166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 81d7585d-2499-49d0-b9ce-dc41842cd85f · outbound

This paper cites Cascading bandits: Learning to rank in the cascade model.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Cascading bandits: Learning to rank in the cascade model

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.603867Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d7256de0-abf7-4d62-a53d-ae2f66a2204c · outbound

This paper cites Multiple-play bandits in the position-based model.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Multiple-play bandits in the position-based model

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.594973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 0f594595-3ccb-47fa-b77f-3bb9416bb218 · outbound

This paper cites Bandit Algo- rithms.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Bandit Algo- rithms

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.586252Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 0005eb18-6d47-425f-9e3a-8c77aa53033d · outbound

This paper cites Contextual combinatorial cascading bandits.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Contextual combinatorial cascading bandits

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.578251Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 35f8f7c1-8e37-4012-94bf-f12d5cfd6414 · outbound

This paper cites Individual Choice Behavior: A Theoretical Analysis.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Individual Choice Behavior: A Theoretical Analysis

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.569569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 5aba3326-f61b-435e-bedb-ce745c656172 · outbound

This paper cites Introduction to Information Retrieval.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Introduction to Information Retrieval

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.560738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 6305a891-33ef-45e0-ac8b-b36061d7c992 · outbound

This paper cites UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-11T00:45:35.987938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 629ce119-4754-4d82-91a5-90639aa00243 · outbound

This paper cites Sample Efficient Preference Alignment in LLMs via Active Exploration.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Sample Efficient Preference Alignment in LLMs via Active Exploration

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-11T00:45:35.991585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation daaef99a-2146-452a-9261-2c47fc04d65b · outbound

This paper cites Optimal design for human feed- back.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Optimal design for human feed- back

Reference 40

Resolution: verified exact; raw_fallback, observed 2026-08-11T00:45:36.257795Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation dbe72c99-cf2e-4cbb-b308-0cf7d3b4a84e · outbound

This paper cites Learning from comparisons and choices.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Learning from comparisons and choices

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.551469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation db94ce64-9903-4d6f-ad11-3d5cd5db18d2 · outbound

This paper cites Introductory Lectures on Convex Opti- mization: A Basic Course.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Introductory Lectures on Convex Opti- mization: A Basic Course

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.541349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 22d89ca2-4e61-4eed-a4a5-0e9e029d52b9 · outbound

This paper cites Training lan- guage models to follow instructions with human feed- back.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Training lan- guage models to follow instructions with human feed- back

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.532595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 8013951a-7260-4d49-a43e-a7e756199bb2 · outbound

This paper cites Fast and robust rank aggregation against model misspecification.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Fast and robust rank aggregation against model misspecification

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.523272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation ba98eb98-a162-47a8-8bab-5931f97520b2 · outbound

This paper cites The analysis of permutations.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe The analysis of permutations

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.513734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation f1e55345-883c-446e-baf1-ffe34d2f3407 · outbound

This paper cites An introduction to grids, graphs, and networks.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe An introduction to grids, graphs, and networks

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.504296Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation b744c86b-d170-4cbb-a89b-c276b9940195 · outbound

This paper cites Optimal Design of Experiments.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Optimal Design of Experiments

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.495480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 3a33d967-b7f3-4f51-b3d1-e8936b6bbef5 · outbound

This paper cites Learning diverse rankings with multi-armed bandits.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Learning diverse rankings with multi-armed bandits

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.486650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 3a91af31-d1ec-4f5e-8266-73876c6eb0d1 · outbound

This paper cites Di- rect preference optimization: Your language model is secretly a reward model.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Di- rect preference optimization: Your language model is secretly a reward model

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.477419Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 23f54b48-01a5-4875-a344-503d550d5ac9 · outbound

This paper cites Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-11T00:45:36.029134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10f40224-b8a0-45b0-b975-7f726413eceb · outbound

This paper cites Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-11T00:45:36.032487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9e2cdee-d4a7-4423-a6b1-ddd1378e5cb0 · outbound

This paper cites Embedding-Aligned Language Models.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Embedding-Aligned Language Models

Reference 52

Resolution: verified exact; local_arxiv, observed 2026-08-11T00:45:36.132016Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 34a7ec85-c897-437b-8ca4-083a0534283a · outbound

This paper cites Judgment under uncertainty: Heuristics and biases.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Judgment under uncertainty: Heuristics and biases

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.467848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 4c291af1-e943-46da-bc9a-a2109ad1261d · outbound

This paper cites Inverting modified matrices.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Inverting modified matrices

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.458538Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation b87e07d4-3892-4a15-8bde-c8022158949d · outbound

This paper cites Provably Efficient Offline Reinforcement Learning with Trajectory-Wise Reward.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Provably Efficient Offline Reinforcement Learning with Trajectory-Wise Reward

Reference 55

Resolution: verified exact; local_arxiv, observed 2026-08-11T00:45:36.118267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation f533508f-d760-4962-bf9e-f85264d302e9 · outbound

This paper cites Minimax optimal fixed- budget best arm identification in linear bandits.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Minimax optimal fixed- budget best arm identification in linear bandits

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.449241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 3e4d5ad2-c588-4d51-b592-88b113e50751 · outbound

This paper cites When is realizability sufficient for off- policy reinforcement learning? In International Con- ference on Machine Learning , pages 40637–40668.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe When is realizability sufficient for off- policy reinforcement learning? In International Con- ference on Machine Learning , pages 40637–40668

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.440991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation c7597923-dc27-4358-8e31-ba70322dc6f7 · outbound

This paper cites Analysis of the frank–wolfe method for convex composite optimiza- tion involving a logarithmically-homogeneous barrier.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Analysis of the frank–wolfe method for convex composite optimiza- tion involving a logarithmically-homogeneous barrier

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.432037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 46ab2f0c-9e43-4587-8c00-7ad648c2f25c · outbound

This paper cites Principled Reinforcement Learning with Human Feedback from Pairwise or $K$-wise Comparisons.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Principled Reinforcement Learning with Human Feedback from Pairwise or $K$-wise Comparisons

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-11T00:45:36.054778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77556b48-5f7d-4d2f-8e33-327a942b51a0 · outbound

This paper cites Cascading bandits for large-scale recommendation problems.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Cascading bandits for large-scale recommendation problems

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.423698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 74bcd6d3-60db-4ad6-bfd5-2653dbf767d8 · outbound

This paper cites None of these works focus on ranking problems.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe None of these works focus on ranking problems

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.414579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d88e2feb-cc1a-4ee4-a7a5-71b5025ff525 · outbound

This paper cites an unresolved cited work.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Unresolved cited work

Reference 62

Resolution: unresolved; raw_fallback, observed 2026-08-11T00:45:36.405534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 760e450b-aa44-45b0-8caf-129e035a4a91 · outbound

This paper cites f (tu) = f (u) − θ log t, for all u ∈ int(K) and t >0 for some θ ≥ 1,.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe f (tu) = f (u) − θ log t, for all u ∈ int(K) and t >0 for some θ ≥ 1,

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:45:36.396582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation f64f5873-fd28-43ca-9ae7-51804e038a6b · outbound

This paper cites an unresolved cited work.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe Unresolved cited work

Reference 64

Resolution: unresolved; raw_fallback, observed 2026-08-11T00:45:36.387401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 138dc4f5-a130-4bff-aeed-8b2d6fce9908 · outbound

This paper cites descent lemma.

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe descent lemma

Reference 65

Resolution: malformed identifier; raw_fallback, observed 2026-08-11T00:45:36.378115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Pith citing papers

Observation 64413cef-0d91-4807-9ca8-f8e52ee96539 · inbound

FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain cites this paper.

FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:54.880840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dc6952f-33d2-4a0c-8a49-5617d87ef2a4 · inbound

MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization cites this paper.

MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe

Reference 60

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:31:24.712722Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.