Paper Citation Record · LEDGER

Implicit Inversion turns CLIP into a Decoder

As of 9 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 1 inbound Pith citation observation for arXiv:2505.23161.

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

pith.paper-citation-record.v1
2505.23161 v2

Coverage vector

measured 40 of 40 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:58:10.698924Z

measured 41 of 41 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-17T05:59:14.478279Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-17T06:01:34.637502Z

Reference resolution

40 of 40 outbound references displayed

verified exact0
verified fuzzy18
unresolved21
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 876088c6-7e5b-41f8-8739-0174a1bfc2e7 · outbound

This paper cites Improving image generation with better captions.Computer Science.

Implicit Inversion turns CLIP into a Decoder Improving image generation with better captions.Computer Science

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T12:58:07.384279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ccd19de-977b-4eb4-810d-959586a79573 · outbound

This paper cites Large scale gan training for high fidelity natural image synthesis.

Implicit Inversion turns CLIP into a Decoder Large scale gan training for high fidelity natural image synthesis

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:58:14.474171Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 87f781c1-351d-4049-85f7-e9a7f42ad304 · outbound

This paper cites Muse: Text-to-image generation via masked generative transformers.

Implicit Inversion turns CLIP into a Decoder Muse: Text-to-image generation via masked generative transformers

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T12:58:07.536052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e4f1577-1828-4b29-92fd-05ca4b5f50a0 · outbound

This paper cites Decoupled Kullback-Leibler Divergence Loss.

Implicit Inversion turns CLIP into a Decoder Decoupled Kullback-Leibler Divergence Loss

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T12:58:07.599829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7abad66-fc79-4a3c-b181-3cf3525f6915 · outbound

This paper cites Scaling rectified flow transformers for high-resolution image synthesis.

Implicit Inversion turns CLIP into a Decoder Scaling rectified flow transformers for high-resolution image synthesis

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:58:14.302657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation fa680c2a-7b2c-42db-9fa8-07e296413172 · outbound

This paper cites Direct Ascent Synthesis: Revealing Hidden Generative Capabilities in Discriminative Models.

Implicit Inversion turns CLIP into a Decoder Direct Ascent Synthesis: Revealing Hidden Generative Capabilities in Discriminative Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T12:58:07.753995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5073ed89-995d-485a-94f9-3b91c4e266c4 · outbound

This paper cites an unresolved cited work.

Implicit Inversion turns CLIP into a Decoder Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:58:14.148363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6dcba974-834a-4b23-b31f-e4efed793c96 · outbound

This paper cites Clipag: Towards generator-free text-to-image generation, 2023.

Implicit Inversion turns CLIP into a Decoder Clipag: Towards generator-free text-to-image generation, 2023

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:58:13.979757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6d690dea-e80b-4f6e-9b39-8a9b0256d9e0 · outbound

This paper cites Text-to-image generation via energy-based clip, 2024.

Implicit Inversion turns CLIP into a Decoder Text-to-image generation via energy-based clip, 2024

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:58:13.748850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d0497f4d-25c0-43f4-b7fd-ae9417124f82 · outbound

This paper cites Do perceptually aligned gradients imply robustness? In ICML, 2023.

Implicit Inversion turns CLIP into a Decoder Do perceptually aligned gradients imply robustness? In ICML, 2023

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:58:13.544683Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2516449c-a1b7-489b-adfd-4d8491f0bbf7 · outbound

This paper cites CLIPScore: A Reference-free Evaluation Metric for Image Captioning.

Implicit Inversion turns CLIP into a Decoder CLIPScore: A Reference-free Evaluation Metric for Image Captioning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T12:58:08.091170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4c2a3aa-bc88-4629-a2bc-d2ce68928a45 · outbound

This paper cites Gans trained by a two time-scale update rule converge to a local nash equilibrium.

Implicit Inversion turns CLIP into a Decoder Gans trained by a two time-scale update rule converge to a local nash equilibrium

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T12:58:08.180237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13840c18-16f4-4a51-8995-bd82eac1f610 · outbound

This paper cites Measuring forgetting of memorized training examples.

Implicit Inversion turns CLIP into a Decoder Measuring forgetting of memorized training examples

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:58:13.323699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c3d23fb3-01eb-448e-870b-4c552bd8a99b · outbound

This paper cites What do we learn from inverting clip models? InNeurips Safe Generative AI Workshop 2024.

Implicit Inversion turns CLIP into a Decoder What do we learn from inverting clip models? InNeurips Safe Generative AI Workshop 2024

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:58:13.094119Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e0d917ef-9d7f-4070-9461-88ecdba5dc9c · outbound

This paper cites Glow: Generative flow with invertible 1x1 convolutions.Advances in neural information processing systems, 31, 2018.

Implicit Inversion turns CLIP into a Decoder Glow: Generative flow with invertible 1x1 convolutions.Advances in neural information processing systems, 31, 2018

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T12:58:08.418361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80d5b421-c28d-4f49-9ab9-c955977759cc · outbound

This paper cites Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning.

Implicit Inversion turns CLIP into a Decoder Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:58:12.865703Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b3942c63-d086-4914-b67a-413c8562847e · outbound

This paper cites Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning.Advances in Neural Information Processing Systems, 35:17612–17625, 2022.

Implicit Inversion turns CLIP into a Decoder Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning.Advances in Neural Information Processing Systems, 35:17612–17625, 2022

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:58:12.657206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 94efc4ae-f9c3-48d2-a6f5-7e3d3836b215 · outbound

This paper cites Microsoft coco: Common objects in context.

Implicit Inversion turns CLIP into a Decoder Microsoft coco: Common objects in context

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T12:58:08.650663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fc2ac30-57e2-4ee3-ad91-175642a52bd8 · outbound

This paper cites Finer: Flexible spectral-bias tuning in implicit neural representation by variable-periodic activation functions.

Implicit Inversion turns CLIP into a Decoder Finer: Flexible spectral-bias tuning in implicit neural representation by variable-periodic activation functions

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:58:12.493719Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 94c8ee32-118e-4608-85db-fdee2e362338 · outbound

This paper cites Towards deep learning models resistant to adversarial attacks.

Implicit Inversion turns CLIP into a Decoder Towards deep learning models resistant to adversarial attacks

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T12:58:08.801151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9495bd32-66da-4db3-bdac-662c182667e2 · outbound

This paper cites Latent space translation via semantic alignment.Advances in Neural Information Processing Systems, 36:55394–55414, 2023.

Implicit Inversion turns CLIP into a Decoder Latent space translation via semantic alignment.Advances in Neural Information Processing Systems, 36:55394–55414, 2023

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:58:12.367338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 54e14a5d-3ea6-41fa-bb51-f654049a0600 · outbound

This paper cites Shedding more light on robust classifiers under the lens of energy-based models.

Implicit Inversion turns CLIP into a Decoder Shedding more light on robust classifiers under the lens of energy-based models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:58:12.177703Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1028b1d7-8134-40ff-88b2-5fd97489b81f · outbound

This paper cites Cross the gap: Exposing the intra-modal misalignment in clip via modality inversion.ICLR 2025, 2025.

Implicit Inversion turns CLIP into a Decoder Cross the gap: Exposing the intra-modal misalignment in clip via modality inversion.ICLR 2025, 2025

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:58:12.059971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c822e84d-b629-4995-ac6a-c165400da176 · outbound

This paper cites Glide: Towards photorealistic image generation and editing with text-guided diffusion models.

Implicit Inversion turns CLIP into a Decoder Glide: Towards photorealistic image generation and editing with text-guided diffusion models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T12:58:09.178917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2cce845-cdf2-4285-9e9b-6be9df94ccbf · outbound

This paper cites Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks.

Implicit Inversion turns CLIP into a Decoder Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T12:58:09.271643Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5744712-07d3-468d-99b8-3411affa1703 · outbound

This paper cites Learning transferable visual models from natural language supervision.

Implicit Inversion turns CLIP into a Decoder Learning transferable visual models from natural language supervision

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T12:58:09.369056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99f73d79-d4a2-4391-b902-aa42af6f0e98 · outbound

This paper cites Hierarchical Text-Conditional Image Generation with CLIP Latents.

Implicit Inversion turns CLIP into a Decoder Hierarchical Text-Conditional Image Generation with CLIP Latents

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T12:58:09.470285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1dd0d8a-bd69-4a8e-9550-a6e0a8457613 · outbound

This paper cites High-resolution image synthesis with latent diffusion models.

Implicit Inversion turns CLIP into a Decoder High-resolution image synthesis with latent diffusion models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T12:58:09.564242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dd5078f-dd69-4e45-9cce-6bf79e986fe5 · outbound

This paper cites Photorealistic text-to- image diffusion models with deep language understanding.Advances in neural information processing systems, 35:36479–36494, 2022.

Implicit Inversion turns CLIP into a Decoder Photorealistic text-to- image diffusion models with deep language understanding.Advances in neural information processing systems, 35:36479–36494, 2022

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T12:58:09.683431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af9da4ff-c882-42d1-a722-dcb0e99b053c · outbound

This paper cites Improved techniques for training gans.Advances in neural information processing systems, 29, 2016.

Implicit Inversion turns CLIP into a Decoder Improved techniques for training gans.Advances in neural information processing systems, 29, 2016

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T12:58:09.783758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc7de873-566a-4d58-8e97-804badb2b851 · outbound

This paper cites Stylegan-t: Unlocking the power of gans for fast large-scale text-to-image synthesis.

Implicit Inversion turns CLIP into a Decoder Stylegan-t: Unlocking the power of gans for fast large-scale text-to-image synthesis

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T12:58:09.878673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a997127-283b-43bd-b5bf-99fbcc66f79c · outbound

This paper cites Laion-5b: An open large-scale dataset for training next generation image-text models.Advances in neural information processing systems, 2022.

Implicit Inversion turns CLIP into a Decoder Laion-5b: An open large-scale dataset for training next generation image-text models.Advances in neural information processing systems, 2022

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:58:11.819929Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e94bf74b-3908-4632-8d71-444093796e30 · outbound

This paper cites Implicit neural representations with periodic activation functions.Advances in neural information processing systems, 33:7462–7473, 2020.

Implicit Inversion turns CLIP into a Decoder Implicit neural representations with periodic activation functions.Advances in neural information processing systems, 33:7462–7473, 2020

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T12:58:10.059412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c5756a4-e802-43fc-b432-a90f6c889392 · outbound

This paper cites Srinivasan, Ben Mildenhall, Sara Fridovich-Keil, Nithin Raghavan, Utkarsh Singhal, Ravi Ramamoorthi, Jonathan T.

Implicit Inversion turns CLIP into a Decoder Srinivasan, Ben Mildenhall, Sara Fridovich-Keil, Nithin Raghavan, Utkarsh Singhal, Ravi Ramamoorthi, Jonathan T

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T12:58:10.163326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f48e25c-3207-4b9f-b9aa-1cd18994deae · outbound

This paper cites Galip: Generative adversarial clips for text-to-image synthesis, 2023.

Implicit Inversion turns CLIP into a Decoder Galip: Generative adversarial clips for text-to-image synthesis, 2023

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:58:11.672437Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 35f7d5a6-a6e8-4309-92db-1fe2c72e733f · outbound

This paper cites Manifold alignment using procrustes analysis.

Implicit Inversion turns CLIP into a Decoder Manifold alignment using procrustes analysis

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:58:11.503880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation fc31449a-d54d-4159-8edc-c13736f48fc1 · outbound

This paper cites CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP.

Implicit Inversion turns CLIP into a Decoder CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T12:58:10.360905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6d1836a-fabf-499a-a508-062e0b693a9d · outbound

This paper cites Adversarial weight perturbation helps robust generalization.

Implicit Inversion turns CLIP into a Decoder Adversarial weight perturbation helps robust generalization

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:58:11.343399Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e19d0072-ac9d-40fb-87f6-6d1c31345b8b · outbound

This paper cites Xing, Laurent El Ghaoui, and Michael I.

Implicit Inversion turns CLIP into a Decoder Xing, Laurent El Ghaoui, and Michael I

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:58:11.181507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 990fc5c1-5a31-490c-9891-7eb92e7df2e5 · outbound

This paper cites Connect, collapse, corrupt: Learning cross-modal tasks with uni-modal data.ICLR 2024, 2024.

Implicit Inversion turns CLIP into a Decoder Connect, collapse, corrupt: Learning cross-modal tasks with uni-modal data.ICLR 2024, 2024

Reference 40

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T12:58:10.976536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Pith citing papers

Observation 03541f61-cfda-4171-8baf-abe75c8eaa76 · inbound

TRANSPORTER: Transferring Visual Semantics from VLM Manifolds cites this paper.

TRANSPORTER: Transferring Visual Semantics from VLM Manifolds Implicit Inversion turns CLIP into a Decoder

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-17T06:01:34.645135Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.