Pith. sign in

LEDGER 24,235 ledger works 25,000 demand tokens 100 top demand shown

Every Pith citation is demand for coverage.

Access class x coverage tier. Not an importance ranking.

Measured lane counts only. Not a ranking of importance, prestige, or foundational status. Full text moves only behind a one-use legal fetch permit.

24,235 ledger works · 25,000 demand tokens · JSON

Coverage histogram

  • Metadata indexed 15,147
  • Abstract indexed 4,968
  • Citation stub 4,120

Access histogram

  • Metadata only 14,442
  • arXiv full text 6,163
  • Unclassified 3,596
  • Unresolved 34

Top demand

Ordered by distinct inbound Pith citations. Cap 100. Each row links to its citation hub when resolved.

  1. 3164 inbound citations Qwen3 Technical Report arXiv full text Abstract indexed 2025 arXiv:2505.09388 doi:10.1016/j.aiopen.2022.12

    Abstract indexed; Pith does not hold full text.
  2. 2509 inbound citations The Llama 3 Herd of Models arXiv full text Abstract indexed 2024 arXiv:2407.21783 doi:10.1016/s0749-0720(15

    Abstract indexed; Pith does not hold full text.
  3. 2498 inbound citations GPT-4 Technical Report arXiv full text Abstract indexed 2023 arXiv:2303.08774 doi:10.1002/tea.20265

    Abstract indexed; Pith does not hold full text.
  4. 2110 inbound citations Adam: A Method for Stochastic Optimization arXiv full text Abstract indexed 2014 arXiv:1412.6980 doi:10.1002/mrm.28086

    Abstract indexed; Pith does not hold full text.
  5. 2032 inbound citations Proximal Policy Optimization Algorithms arXiv full text Abstract indexed 2017 arXiv:1707.06347 doi:10.1016/j.artint.2010.12.005

    Abstract indexed; Pith does not hold full text.
  6. 1966 inbound citations DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models arXiv full text Abstract indexed 2024 arXiv:2402.03300 doi:10.1016/0004-3702(73)90011-8

    Abstract indexed; Pith does not hold full text.
  7. 1937 inbound citations DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning arXiv full text Abstract indexed 2025 arXiv:2501.12948 doi:10.1016/j.artmed.2024.103001

    Abstract indexed; Pith does not hold full text.
  8. 1493 inbound citations Training Verifiers to Solve Math Word Problems arXiv full text Abstract indexed 2021 arXiv:2110.14168 doi:10.1002/j.1545-

    Abstract indexed; Pith does not hold full text.
  9. 1339 inbound citations Evaluating Large Language Models Trained on Code arXiv full text Abstract indexed 2021 arXiv:2107.03374 doi:10.48550/arxiv.2107.03374

    Abstract indexed; Pith does not hold full text.
  10. 1326 inbound citations LLaMA: Open and Efficient Foundation Language Models arXiv full text Abstract indexed 2023 arXiv:2302.13971 doi:10.48550/arxiv.2302.13971

    Abstract indexed; Pith does not hold full text.
  11. 1316 inbound citations Qwen2.5-VL Technical Report arXiv full text Abstract indexed 2025 arXiv:2502.13923 doi:10.48550/arxiv.2502.13923

    Abstract indexed; Pith does not hold full text.
  12. 1251 inbound citations Decoupled Weight Decay Regularization arXiv full text Abstract indexed 2017 arXiv:1711.05101 doi:10.1137/1.9781611972825.47

    Abstract indexed; Pith does not hold full text.
  13. 1217 inbound citations Qwen3-VL Technical Report arXiv full text Abstract indexed 2025 arXiv:2511.21631 doi:10.1016/j.neunet.2025.107777

    Abstract indexed; Pith does not hold full text.
  14. 1157 inbound citations Qwen2.5 Technical Report arXiv full text Abstract indexed 2024 arXiv:2412.15115 doi:10.1145/3581783.3612503

    Abstract indexed; Pith does not hold full text.
  15. 1134 inbound citations Lipiecki, K Metadata only Metadata indexed 2019 doi:10.1016/j

    Metadata indexed; abstract and full text not held.
  16. 1130 inbound citations An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale arXiv full text Abstract indexed 2020 arXiv:2010.11929 doi:10.1175/jcli-d-22-0357.1

    Abstract indexed; Pith does not hold full text.
  17. 1105 inbound citations Llama 2: Open Foundation and Fine-Tuned Chat Models arXiv full text Abstract indexed 2023 arXiv:2307.09288 doi:10.24963/ijcai.2025/706

    Abstract indexed; Pith does not hold full text.
  18. 1065 inbound citations GPT-4o System Card arXiv full text Abstract indexed 2024 arXiv:2410.21276 doi:10.1177/15248380231178756

    Abstract indexed; Pith does not hold full text.
  19. 1057 inbound citations Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities arXiv full text Abstract indexed 2025 arXiv:2507.06261 doi:10.48550/arxiv.2503.19

    Abstract indexed; Pith does not hold full text.
  20. 1005 inbound citations DeepSeek-V3 Technical Report arXiv full text Abstract indexed 2024 arXiv:2412.19437 doi:10.1016/j.neucom.2023.127063.url:https://www.sciencedirect

    Abstract indexed; Pith does not hold full text.
  21. 962 inbound citations Gemini: A Family of Highly Capable Multimodal Models arXiv full text Abstract indexed 2023 arXiv:2312.11805 doi:10.1038/nrn2888

    Abstract indexed; Pith does not hold full text.
  22. 888 inbound citations Scaling Laws for Neural Language Models arXiv full text Abstract indexed 2020 arXiv:2001.08361 doi:10.1145/3616855.3635845

    Abstract indexed; Pith does not hold full text.
  23. 870 inbound citations DINOv2: Learning Robust Visual Features without Supervision arXiv full text Abstract indexed 2023 arXiv:2304.07193 doi:10.48550/arxiv.2304.07193

    Abstract indexed; Pith does not hold full text.
  24. 829 inbound citations Wan: Open and Advanced Large-Scale Video Generative Models arXiv full text Abstract indexed 2025 arXiv:2503.20314 doi:10.1109/19.492748

    Abstract indexed; Pith does not hold full text.
  25. 819 inbound citations , keywords = arXiv full text Metadata indexed 2011 arXiv:2966.2011 doi:10.1111/j.1365-2966.2011

    Metadata indexed; abstract and full text not held.
  26. 808 inbound citations MNRAS , author = arXiv full text Metadata indexed 2012 arXiv:2966.2012 doi:10.1111/j.1365-2966.2012

    Metadata indexed; abstract and full text not held.
  27. 806 inbound citations MNRAS , author = arXiv full text Metadata indexed 2010 arXiv:2966.2010 doi:10.1111/j.1365-2966.2010

    Metadata indexed; abstract and full text not held.
  28. 797 inbound citations Flow Matching for Generative Modeling arXiv full text Abstract indexed 2022 arXiv:2210.02747 doi:10.1038/s41467-024-47656-z

    Abstract indexed; Pith does not hold full text.
  29. 788 inbound citations 2009, title Clustering of luminous red galaxies - III arXiv full text Metadata indexed 2009 arXiv:2966.2009 doi:10.1111/j.1365-2966.2009

    Metadata indexed; abstract and full text not held.
  30. 768 inbound citations Auto-Encoding Variational Bayes arXiv full text Abstract indexed 2013 arXiv:1312.6114 doi:10.2139/ssrn.4269703

    Abstract indexed; Pith does not hold full text.
  31. 745 inbound citations Distilling the Knowledge in a Neural Network arXiv full text Abstract indexed 2015 arXiv:1503.02531 doi:10.1109/cvpr52733.2024.01515

    Abstract indexed; Pith does not hold full text.
  32. 719 inbound citations $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control arXiv full text Abstract indexed 2024 arXiv:2410.24164 doi:10.48550/arxiv.2410.24164

    Abstract indexed; Pith does not hold full text.
  33. 672 inbound citations Mistral 7B arXiv full text Abstract indexed 2023 arXiv:2310.06825 doi:10.48550/arxiv.2310.06825

    Abstract indexed; Pith does not hold full text.
  34. 665 inbound citations Planck 2018 results. VI. Cosmological parameters arXiv full text Abstract indexed 2018 arXiv:1807.06209 doi:10.1007/jhep11(2024)108

    Abstract indexed; Pith does not hold full text.
  35. 627 inbound citations LoRA: Low-Rank Adaptation of Large Language Models arXiv full text Abstract indexed 2021 arXiv:2106.09685 doi:10.4088/pcc.v03n0609

    Abstract indexed; Pith does not hold full text.
  36. 607 inbound citations OpenVLA: An Open-Source Vision-Language-Action Model arXiv full text Abstract indexed 2024 arXiv:2406.09246 doi:10.18653/v1/2022.naacl-main.68

    Abstract indexed; Pith does not hold full text.
  37. 606 inbound citations Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge arXiv full text Abstract indexed 2018 arXiv:1803.05457 doi:10.1162/tacl_a_00448.https://aclanthology.org/2022.tacl-1.5

    Abstract indexed; Pith does not hold full text.
  38. 605 inbound citations DAPO: An Open-Source LLM Reinforcement Learning System at Scale arXiv full text Abstract indexed 2025 arXiv:2503.14476 doi:10.48550/arxiv.2503.14476

    Abstract indexed; Pith does not hold full text.
  39. 604 inbound citations ReAct: Synergizing Reasoning and Acting in Language Models arXiv full text Abstract indexed 2022 arXiv:2210.03629 doi:10.48550/arxiv.2210.03629

    Abstract indexed; Pith does not hold full text.
  40. 604 inbound citations Denoising Diffusion Implicit Models arXiv full text Abstract indexed 2020 arXiv:2010.02502 doi:10.48550/arxiv.2010.02502

    Abstract indexed; Pith does not hold full text.
  41. 601 inbound citations , keywords = arXiv full text Metadata indexed 2006 arXiv:2966.2006 doi:10.1111/j.1365-2966.2006

    Metadata indexed; abstract and full text not held.
  42. 596 inbound citations DINOv3 arXiv full text Abstract indexed 2025 arXiv:2508.10104 doi:10.1055/a-2487-1252

    Abstract indexed; Pith does not hold full text.
  43. 588 inbound citations BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding arXiv full text Abstract indexed 2018 arXiv:1810.04805 doi:10.1111/jofi.12885

    Abstract indexed; Pith does not hold full text.
  44. 583 inbound citations Program Synthesis with Large Language Models arXiv full text Abstract indexed 2021 arXiv:2108.07732 doi:10.1007/s11390-025-5518-5

    Abstract indexed; Pith does not hold full text.
  45. 579 inbound citations and Vecchio, A arXiv full text Metadata indexed 2008 arXiv:2966.2008 doi:10.1111/j.1365-2966.2008.12689.x

    Metadata indexed; abstract and full text not held.
  46. 578 inbound citations Qwen Technical Report arXiv full text Abstract indexed 2023 arXiv:2309.16609 doi:10.48550/arxiv.2309.16609

    Abstract indexed; Pith does not hold full text.
  47. 571 inbound citations Gemma 3 Technical Report arXiv full text Abstract indexed 2025 arXiv:2503.19786 doi:10.1007/978-3-540-48085-3_36

    Abstract indexed; Pith does not hold full text.
  48. 567 inbound citations 2005, title The three-point function in large-scale structure: redshift distortions and galaxy bias , , 361, 824, 10.1111/j.1365-2966.2005.09234.x arXiv full text Metadata indexed 2005 arXiv:2966.2005 doi:10.1111/j.1365-2966.2005

    Metadata indexed; abstract and full text not held.
  49. 560 inbound citations , keywords = arXiv full text Metadata indexed 2007 arXiv:2966.2007 doi:10.1111/j.1365-2966.2007

    Metadata indexed; abstract and full text not held.
  50. 557 inbound citations OpenAI GPT-5 System Card arXiv full text Abstract indexed 2025 arXiv:2601.03267 doi:10.48550/arxiv.2601.03267

    Abstract indexed; Pith does not hold full text.
  51. 547 inbound citations Constitutional AI: Harmlessness from AI Feedback arXiv full text Abstract indexed 2022 arXiv:2212.08073 doi:10.48550/arxiv.2212.08073

    Abstract indexed; Pith does not hold full text.
  52. 545 inbound citations Chen, Intrinsic Axion Statistical Topological In- sulator, Physical Review Letters134, 10.1103/Phys- RevLett.134.226601 (2025) Metadata only Metadata indexed 2025 doi:10.1103/phys-

    Metadata indexed; abstract and full text not held.
  53. 544 inbound citations Measuring Massive Multitask Language Understanding arXiv full text Abstract indexed 2020 arXiv:2009.03300 doi:10.48550/arxiv.2009.03300

    Abstract indexed; Pith does not hold full text.
  54. 539 inbound citations R., Millman , K arXiv full text Metadata indexed 2020 arXiv:articles/7759461 doi:10.1038/s41586-020-2649-2

    Metadata indexed; abstract and full text not held.
  55. 538 inbound citations Score-Based Generative Modeling through Stochastic Differential Equations arXiv full text Abstract indexed 2020 arXiv:2011.13456 doi:10.1088/1748-9326/aae98d

    Abstract indexed; Pith does not hold full text.
  56. 513 inbound citations Mamba: Linear-Time Sequence Modeling with Selective State Spaces arXiv full text Abstract indexed 2023 arXiv:2312.00752 doi:10.48550/arxiv.2312.00752

    Abstract indexed; Pith does not hold full text.
  57. 509 inbound citations doi:10.1111/j.1365-2966.2004.07942.x , journal= arXiv full text Metadata indexed 2004 arXiv:2966.2004 doi:10.1111/j.1365-2966.2004

    Metadata indexed; abstract and full text not held.
  58. 491 inbound citations OpenAI o1 System Card arXiv full text Abstract indexed 2024 arXiv:2412.16720 doi:10.48550/arxiv.2412.16720

    Abstract indexed; Pith does not hold full text.
  59. 483 inbound citations Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback arXiv full text Abstract indexed 2022 arXiv:2204.05862 doi:10.1016/j.respol.2005.01.014

    Abstract indexed; Pith does not hold full text.
  60. 481 inbound citations Computing in Science and Engineering , keywords = Metadata only Metadata indexed 2007 doi:10.1109/mcse.2007.55

    Metadata indexed; abstract and full text not held.
  61. 478 inbound citations Universal and Transferable Adversarial Attacks on Aligned Language Models arXiv full text Abstract indexed 2023 arXiv:2307.15043 doi:10.48550/arxiv.2307.15043

    Abstract indexed; Pith does not hold full text.
  62. 468 inbound citations Measuring Mathematical Problem Solving With the MATH Dataset arXiv full text Abstract indexed 2021 arXiv:2103.03874 doi:10.48550/arxiv.2103.03874

    Abstract indexed; Pith does not hold full text.
  63. 463 inbound citations doi:10.1046/j.1365-8711.2003.06504.x , keywords = arXiv full text Metadata indexed 2003 arXiv:8711.2003 doi:10.1046/j.1365-8711.2003

    Metadata indexed; abstract and full text not held.
  64. 463 inbound citations SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python Metadata only Metadata indexed 2020 doi:10.1038/s41592-019-0686-2

    Metadata indexed; abstract and full text not held.
  65. 462 inbound citations $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization arXiv full text Abstract indexed 2025 arXiv:2504.16054 doi:10.1609/aaai.v40i28.39562

    Abstract indexed; Pith does not hold full text.
  66. 457 inbound citations Self-Consistency Improves Chain of Thought Reasoning in Language Models arXiv full text Abstract indexed 2022 arXiv:2203.11171 doi:10.1101/2025.04.03.646459

    Abstract indexed; Pith does not hold full text.
  67. 451 inbound citations Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context arXiv full text Abstract indexed 2024 arXiv:2403.05530 doi:10.48550/arxiv.2403.05530

    Abstract indexed; Pith does not hold full text.
  68. 451 inbound citations Very Deep Convolutional Networks for Large-Scale Image Recognition arXiv full text Abstract indexed 2014 arXiv:1409.1556 doi:10.48550/arxiv.1409.1556

    Abstract indexed; Pith does not hold full text.
  69. 446 inbound citations and Prestwich, A arXiv full text Metadata indexed 2001 arXiv:8711.2001 doi:10.1046/j.1365-8711.2001

    Metadata indexed; abstract and full text not held.
  70. 445 inbound citations gpt-oss-120b & gpt-oss-20b Model Card arXiv full text Abstract indexed 2025 arXiv:2508.10925 doi:10.3115/1073083.1073135

    Abstract indexed; Pith does not hold full text.
  71. 436 inbound citations Attention Is All You Need arXiv full text Abstract indexed 2017 arXiv:1706.03762 doi:10.1186/s13550-021-00830-6

    Abstract indexed; Pith does not hold full text.
  72. 431 inbound citations LLaVA-OneVision: Easy Visual Task Transfer arXiv full text Abstract indexed 2024 arXiv:2408.03326 doi:10.48550/arxiv.2408.03326

    Abstract indexed; Pith does not hold full text.
  73. 420 inbound citations Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow arXiv full text Abstract indexed 2022 arXiv:2209.03003 doi:10.48550/arxiv.2209.03003

    Abstract indexed; Pith does not hold full text.
  74. 414 inbound citations Language Models are Few-Shot Learners arXiv full text Abstract indexed 2020 arXiv:2005.14165 doi:10.1145/1926385.1926423

    Abstract indexed; Pith does not hold full text.
  75. 413 inbound citations Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets arXiv full text Abstract indexed 2023 arXiv:2311.15127 doi:10.48550/arxiv.2311.15127

    Abstract indexed; Pith does not hold full text.
  76. 401 inbound citations GR00T N1: An Open Foundation Model for Generalist Humanoid Robots arXiv full text Abstract indexed 2025 arXiv:2503.14734 doi:10.48550/arxiv.2503.14734

    Abstract indexed; Pith does not hold full text.
  77. 400 inbound citations Retrieval-Augmented Generation for Large Language Models: A Survey arXiv full text Abstract indexed 2023 arXiv:2312.10997 doi:10.1186/1476-072x-8-72

    Abstract indexed; Pith does not hold full text.
  78. 392 inbound citations Hierarchical Text-Conditional Image Generation with CLIP Latents arXiv full text Abstract indexed 2022 arXiv:2204.06125 doi:10.48550/arxiv.2204.06125

    Abstract indexed; Pith does not hold full text.
  79. 391 inbound citations SWE-bench: Can Language Models Resolve Real-World GitHub Issues? arXiv full text Abstract indexed 2023 arXiv:2310.06770 doi:10.1145/512927.512945

    Abstract indexed; Pith does not hold full text.
  80. 387 inbound citations Voyager: An Open-Ended Embodied Agent with Large Language Models arXiv full text Abstract indexed 2023 arXiv:2305.16291 doi:10.18653/v1/2023.emnlp-main.118

    Abstract indexed; Pith does not hold full text.
  81. 379 inbound citations SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis arXiv full text Abstract indexed 2023 arXiv:2307.01952 doi:10.48500/arxiv.2307.01952

    Abstract indexed; Pith does not hold full text.
  82. 362 inbound citations Chain-of-Thought Prompting Elicits Reasoning in Large Language Models arXiv full text Abstract indexed 2022 arXiv:2201.11903 doi:10.48550/arxiv.2201.11903

    Abstract indexed; Pith does not hold full text.
  83. 353 inbound citations Qwen-Image Technical Report arXiv full text Abstract indexed 2025 arXiv:2508.02324 doi:10.48550/arxiv.2508.02324

    Abstract indexed; Pith does not hold full text.
  84. 348 inbound citations MemGPT: Towards LLMs as Operating Systems arXiv full text Abstract indexed 2023 arXiv:2310.08560 doi:10.48550/arxiv.2310.08560

    Abstract indexed; Pith does not hold full text.
  85. 344 inbound citations DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models arXiv full text Abstract indexed 2025 arXiv:2512.02556 doi:10.18653/v1/d18-1512

    Abstract indexed; Pith does not hold full text.
  86. 344 inbound citations Qwen2.5-Coder Technical Report arXiv full text Abstract indexed 2024 arXiv:2409.12186 doi:10.48550/arxiv.2409.12186

    Abstract indexed; Pith does not hold full text.
  87. 338 inbound citations Mixtral of Experts arXiv full text Abstract indexed 2024 arXiv:2401.04088 doi:10.48550/arxiv.2401.04088

    Abstract indexed; Pith does not hold full text.
  88. 336 inbound citations CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer arXiv full text Abstract indexed 2024 arXiv:2408.06072 doi:10.48550/arxiv.2408.06072

    Abstract indexed; Pith does not hold full text.
  89. 335 inbound citations UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction arXiv full text Abstract indexed 2018 arXiv:1802.03426 doi:10.1037/adb0001138

    Abstract indexed; Pith does not hold full text.
  90. 335 inbound citations A Survey of Large Language Models arXiv full text Abstract indexed 2023 arXiv:2303.18223 doi:10.18653/v1/d16-1080

    Abstract indexed; Pith does not hold full text.
  91. 334 inbound citations Language Models (Mostly) Know What They Know arXiv full text Abstract indexed 2022 arXiv:2207.05221 doi:10.1145/3618260.3649777

    Abstract indexed; Pith does not hold full text.
  92. 332 inbound citations Longformer: The Long-Document Transformer arXiv full text Abstract indexed 2020 arXiv:2004.05150 doi:10.48550/arxiv.2004.05150

    Abstract indexed; Pith does not hold full text.
  93. 332 inbound citations AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation arXiv full text Abstract indexed 2023 arXiv:2308.08155 doi:10.48550/arxiv.2308.08155

    Abstract indexed; Pith does not hold full text.
  94. 323 inbound citations F., Percival , W arXiv full text Metadata indexed 2002 arXiv:8711.2002 doi:10.1046/j.1365-8711.2002.04944.x

    Metadata indexed; abstract and full text not held.
  95. 323 inbound citations Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters arXiv full text Abstract indexed 2024 arXiv:2408.03314 doi:10.18653/v1/2025.acl-long.1486

    Abstract indexed; Pith does not hold full text.
  96. 320 inbound citations Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism arXiv full text Abstract indexed 2019 arXiv:1909.08053 doi:10.48550/arxiv.1909.08053

    Abstract indexed; Pith does not hold full text.
  97. 318 inbound citations A Quantum Approximate Optimization Algorithm arXiv full text Abstract indexed 2014 arXiv:1411.4028 doi:10.48550/arxiv.1411.4028

    Abstract indexed; Pith does not hold full text.
  98. 315 inbound citations Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer arXiv full text Abstract indexed 2017 arXiv:1701.06538 doi:10.48550/arxiv.1701.06538

    Abstract indexed; Pith does not hold full text.
  99. 314 inbound citations Code Llama: Open Foundation Models for Code arXiv full text Abstract indexed 2023 arXiv:2308.12950 doi:10.48550/arxiv.2308.12950

    Abstract indexed; Pith does not hold full text.
  100. 310 inbound citations SAM 3: Segment Anything with Concepts arXiv full text Abstract indexed 2025 arXiv:2511.16719 doi:10.48550/arxiv.2511.16719

    Abstract indexed; Pith does not hold full text.