BlueGlass: A Framework for Composite AI Safety | Paper Citation Record

Observation c88b976d-03ed-4382-8076-217bd43b3a34 · outbound

This paper cites write newline.

BlueGlass: A Framework for Composite AI Safety write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:15.323916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 724930c3-b3fe-4b85-899b-4cc49bcdc7be · outbound

This paper cites Sanity Checks for Saliency Maps.

BlueGlass: A Framework for Composite AI Safety Sanity Checks for Saliency Maps

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:15.373932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6f99e68-2dc0-42e8-9c9d-f2aebe854de5 · outbound

This paper cites Understanding intermediate layers using linear classifier probes.

BlueGlass: A Framework for Composite AI Safety Understanding intermediate layers using linear classifier probes

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:15.466161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 409004ff-8edb-4db6-9268-463a36c4b7d1 · outbound

This paper cites Physics of Language Models: Part 3.1, Knowledge Storage and Extraction.

BlueGlass: A Framework for Composite AI Safety Physics of Language Models: Part 3.1, Knowledge Storage and Extraction

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:15.570127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bccc730e-1a91-4613-ade5-2b6a9024088e · outbound

This paper cites Apache parquet.

BlueGlass: A Framework for Composite AI Safety Apache parquet

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:46:28.248362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e97cc8f2-9068-49ee-ba09-53893093cb6f · outbound

This paper cites Apache arrow: A cross-language development platform for in-memory data.

BlueGlass: A Framework for Composite AI Safety Apache arrow: A cross-language development platform for in-memory data

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:46:28.138998Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1fba99e1-0585-455d-a137-20b30e57c618 · outbound

This paper cites Refusal in Language Models Is Mediated by a Single Direction.

BlueGlass: A Framework for Composite AI Safety Refusal in Language Models Is Mediated by a Single Direction

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:15.929100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0dbd63e7-ed16-4b54-a06c-59c0a0d00814 · outbound

This paper cites A Survey of Word Embeddings Evaluation Methods.

BlueGlass: A Framework for Composite AI Safety A Survey of Word Embeddings Evaluation Methods

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-08-06T17:46:24.514053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 342c7307-d71a-46a7-b46b-9edb473814ec · outbound

This paper cites Mechanistic Interpretability for AI Safety -- A Review.

BlueGlass: A Framework for Composite AI Safety Mechanistic Interpretability for AI Safety -- A Review

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:16.059377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3065a345-7af3-4c74-b4f5-3f4676bccafe · outbound

This paper cites an unresolved cited work.

BlueGlass: A Framework for Composite AI Safety Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-06T17:46:28.020173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation edab9dcc-3591-4ec2-bc6c-ddaa94c0264e · outbound

This paper cites an unresolved cited work.

BlueGlass: A Framework for Composite AI Safety Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:16.163889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9afa9af6-a364-4c41-95f9-278155481ddd · outbound

This paper cites E., Hume, T., Carter, S., Henighan, T., and Olah, C.

BlueGlass: A Framework for Composite AI Safety E., Hume, T., Carter, S., Henighan, T., and Olah, C

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:46:27.905857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e744d89e-f625-48bd-9a2d-944b37cf8872 · outbound

This paper cites BatchTopK Sparse Autoencoders.

BlueGlass: A Framework for Composite AI Safety BatchTopK Sparse Autoencoders

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:16.400548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10b64f59-8fbe-4986-b96d-8f7e92bc671d · outbound

This paper cites Learning Multi-Level Features with Matryoshka Sparse Autoencoders.

BlueGlass: A Framework for Composite AI Safety Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:16.512841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1da9890-ef98-414d-b7c6-8811a04724ea · outbound

This paper cites M., Favero, A., and Wyart, M.

BlueGlass: A Framework for Composite AI Safety M., Favero, A., and Wyart, M

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:16.611680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25553133-d791-41b7-ad7e-a8d99adab7ea · outbound

This paper cites On Evaluating Adversarial Robustness.

BlueGlass: A Framework for Composite AI Safety On Evaluating Adversarial Robustness

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:16.651922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3a84728-238a-4f7d-b9c9-74df179a3200 · outbound

This paper cites DLST 4: Phase Transitions in Neural Networks.

BlueGlass: A Framework for Composite AI Safety DLST 4: Phase Transitions in Neural Networks

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:46:27.781480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7a4ad18b-71c6-4173-9af5-1a34a864385e · outbound

This paper cites MMDetection: Open MMLab Detection Toolbox and Benchmark.

BlueGlass: A Framework for Composite AI Safety MMDetection: Open MMLab Detection Toolbox and Benchmark

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:16.912919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9ae5232-9ace-4ab1-b128-8b8795276059 · outbound

This paper cites Generative Region-Language Pretraining for Open-Ended Object Detection.

BlueGlass: A Framework for Composite AI Safety Generative Region-Language Pretraining for Open-Ended Object Detection

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:46:27.673550Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6487b47b-7b5f-46e4-97ad-2bf01af2e79e · outbound

This paper cites Sparse Autoencoders Find Highly Interpretable Features in Language Models.

BlueGlass: A Framework for Composite AI Safety Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:17.149232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22291758-2325-43be-9687-36d8a4a06dc4 · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

BlueGlass: A Framework for Composite AI Safety BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:17.237274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f6126c4-260a-4f21-b87e-b92da4ded3e1 · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

BlueGlass: A Framework for Composite AI Safety An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:17.392533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45d1f631-5cf5-46aa-bc47-32db5aa3e311 · outbound

This paper cites Transcoders Find Interpretable LLM Feature Circuits.

BlueGlass: A Framework for Composite AI Safety Transcoders Find Interpretable LLM Feature Circuits

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:17.561067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e7baaaa-8f6f-4733-b251-c52a42f4c79c · outbound

This paper cites Garçon , December 2021.

BlueGlass: A Framework for Composite AI Safety Garçon , December 2021

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:46:27.499860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a89a8554-ad1e-4b76-9e14-76dea3809264 · outbound

This paper cites NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals.

BlueGlass: A Framework for Composite AI Safety NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:17.810429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3604c46-0f88-49d6-91a3-b8aa86a0b994 · outbound

This paper cites Scaling and evaluating sparse autoencoders.

BlueGlass: A Framework for Composite AI Safety Scaling and evaluating sparse autoencoders

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:17.955168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b41e325c-0cb0-4e68-9f84-d300db121f70 · outbound

This paper cites Detecting Strategic Deception Using Linear Probes.

BlueGlass: A Framework for Composite AI Safety Detecting Strategic Deception Using Linear Probes

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:18.135459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9861cd60-4169-4728-bd33-757c017c30c0 · outbound

This paper cites VALERIE22 -- A photorealistic, richly metadata annotated dataset of urban environments.

BlueGlass: A Framework for Composite AI Safety VALERIE22 -- A photorealistic, richly metadata annotated dataset of urban environments

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-08-06T17:46:24.175232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ab7b6516-8cad-4b23-85ae-e04ac0f1cbe8 · outbound

This paper cites Safety by Measurement: A Systematic Literature Review of AI Safety Evaluation Methods.

BlueGlass: A Framework for Composite AI Safety Safety by Measurement: A Systematic Literature Review of AI Safety Evaluation Methods

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:18.445211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3254e4a8-ed4d-46f4-a1e4-25c0826b1c07 · outbound

This paper cites LVIS: A Dataset for Large Vocabulary Instance Segmentation.

BlueGlass: A Framework for Composite AI Safety LVIS: A Dataset for Large Vocabulary Instance Segmentation

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:18.556765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c110fa2f-ff69-41fb-a658-47720fa33ba2 · outbound

This paper cites How to use and interpret activation patching.

BlueGlass: A Framework for Composite AI Safety How to use and interpret activation patching

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:18.640840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4eaa86aa-c39d-49fc-9911-1f448e9bde96 · outbound

This paper cites FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods.

BlueGlass: A Framework for Composite AI Safety FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-08-06T17:46:23.959712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e996239e-be49-4477-ae13-bd1613d439b5 · outbound

This paper cites A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks.

BlueGlass: A Framework for Composite AI Safety A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-08-06T17:46:23.701365Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d0be80d8-2336-43d6-ab5f-4d1182d0b754 · outbound

This paper cites Ultralytics YOLO , January 2023.

BlueGlass: A Framework for Composite AI Safety Ultralytics YOLO , January 2023

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:46:27.342062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0afec4d0-01ee-444b-bdd3-993b6fcbf964 · outbound

This paper cites Are Sparse Autoencoders Useful? A Case Study in Sparse Probing.

BlueGlass: A Framework for Composite AI Safety Are Sparse Autoencoders Useful? A Case Study in Sparse Probing

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:18.929519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acd04884-4e1a-4a82-ac33-d96a34da1479 · outbound

This paper cites The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale.

BlueGlass: A Framework for Composite AI Safety The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:46:27.189594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 080aa468-8507-4b6b-ba6c-8d6d68a747ef · outbound

This paper cites NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models.

BlueGlass: A Framework for Composite AI Safety NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:19.125111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec3abb6f-c646-4fa8-8b54-1d0af3e8622f · outbound

This paper cites Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects.

BlueGlass: A Framework for Composite AI Safety Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:19.212667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 476a2bf4-6d87-48bb-b1f7-ca4b68b8c97c · outbound

This paper cites Open World Object Detection: A Survey.

BlueGlass: A Framework for Composite AI Safety Open World Object Detection: A Survey

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-08-06T17:46:23.411252Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9ce1f919-f93d-413d-b860-570ddff36ca1 · outbound

This paper cites Microsoft COCO: Common Objects in Context.

BlueGlass: A Framework for Composite AI Safety Microsoft COCO: Common Objects in Context

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:19.415317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e21b1cfe-bf83-45d4-89d7-eb5f4d6cc0f4 · outbound

This paper cites Sparse Crosscoders for Cross-Layer Features and Model Diffing.

BlueGlass: A Framework for Composite AI Safety Sparse Crosscoders for Cross-Layer Features and Model Diffing

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:46:26.978315Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0c4d431f-f983-4e24-a2a2-08cd898794bb · outbound

This paper cites an unresolved cited work.

BlueGlass: A Framework for Composite AI Safety Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-08-06T17:46:26.836469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d8ae6d68-e42b-4faf-98c6-c5f460355fc5 · outbound

This paper cites Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection.

BlueGlass: A Framework for Composite AI Safety Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:19.640739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80c6e2a7-9ab3-4949-9148-078c97e4bee3 · outbound

This paper cites Data Attribution: A Data-Centric Approach for Trustworthy AI Development.

BlueGlass: A Framework for Composite AI Safety Data Attribution: A Data-Centric Approach for Trustworthy AI Development

Reference 44

Resolution: verified exact; doi, observed 2026-08-06T17:46:22.687260Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 59e4ae61-2b3e-4697-9c56-a0f73d90f512 · outbound

This paper cites A Survey on Vision-Language-Action Models for Embodied AI.

BlueGlass: A Framework for Composite AI Safety A Survey on Vision-Language-Action Models for Embodied AI

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:19.838147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97c99df3-41c9-419b-a568-d9fde04a3301 · outbound

This paper cites k-Sparse Autoencoders.

BlueGlass: A Framework for Composite AI Safety k-Sparse Autoencoders

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:19.924890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5955998a-17cd-465f-b711-6f1740694cd4 · outbound

This paper cites Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models.

BlueGlass: A Framework for Composite AI Safety Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:20.011978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3bdf3bf-2306-4363-8e0f-10bb4bcc79f5 · outbound

This paper cites Deep Double Descent: Where Bigger Models and More Data Hurt.

BlueGlass: A Framework for Composite AI Safety Deep Double Descent: Where Bigger Models and More Data Hurt

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:20.073892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7293ed22-f9c4-481d-bd3d-47f0abe7e658 · outbound

This paper cites Interpretability will not reliably find deceptive ai.

BlueGlass: A Framework for Composite AI Safety Interpretability will not reliably find deceptive ai

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:46:26.697795Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 07e4e179-8f27-4798-98d8-746186b6ce4c · outbound

This paper cites and Bloom, J.

BlueGlass: A Framework for Composite AI Safety and Bloom, J

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:46:26.515842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f20aa03e-5b6c-4a2e-aa14-417471083741 · outbound

This paper cites Understanding Neural Networks via Feature Visualization: A survey.

BlueGlass: A Framework for Composite AI Safety Understanding Neural Networks via Feature Visualization: A survey

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-08-06T17:46:23.176853Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation fd6289ab-5d40-43e8-b39c-7c132a9b7ffe · outbound

This paper cites In-context Learning and Induction Heads.

BlueGlass: A Framework for Composite AI Safety In-context Learning and Induction Heads

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:46:26.284943Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 43551005-0b9f-4ef7-a88f-6dbacf340caa · outbound

This paper cites GPT-4o System Card.

BlueGlass: A Framework for Composite AI Safety GPT-4o System Card

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:20.489299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ba300c2-cc56-4d1b-95c0-612a9bf8be97 · outbound

This paper cites Mamba-360: Survey of State Space Models as Transformer Alternative for Long Sequence Modelling: Methods, Applications, and Challenges.

BlueGlass: A Framework for Composite AI Safety Mamba-360: Survey of State Space Models as Transformer Alternative for Long Sequence Modelling: Methods, Applications, and Challenges

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:20.549128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ebb9618-cde8-44d3-bfe6-58c6473c59c9 · outbound

This paper cites Introducing Gemini 2.0: our new AI model for the agentic era , December 2024.

BlueGlass: A Framework for Composite AI Safety Introducing Gemini 2.0: our new AI model for the agentic era , December 2024

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:46:26.078534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9951d616-7bf0-416a-a1ca-f0d7631b94d6 · outbound

This paper cites On Evaluating the Durability of Safeguards for Open-Weight LLMs.

BlueGlass: A Framework for Composite AI Safety On Evaluating the Durability of Safeguards for Open-Weight LLMs

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:20.678400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2491fe7e-716e-48d5-ac1a-8d339f982919 · outbound

This paper cites Language Models are Unsupervised Multitask Learners , 2019.

BlueGlass: A Framework for Composite AI Safety Language Models are Unsupervised Multitask Learners , 2019

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:46:25.933137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b6a4309e-db90-4475-a23b-568dc5649260 · outbound

This paper cites Learning Transferable Visual Models From Natural Language Supervision.

BlueGlass: A Framework for Composite AI Safety Learning Transferable Visual Models From Natural Language Supervision

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:20.831314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfffdb04-f8d6-4c92-b3d4-626fa75efab4 · outbound

This paper cites Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.

BlueGlass: A Framework for Composite AI Safety Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:20.913958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 313eb60f-c70a-4a58-bcee-97b520ee1469 · outbound

This paper cites A Phase Transition in Diffusion Models Reveals the Hierarchical Nature of Data.

BlueGlass: A Framework for Composite AI Safety A Phase Transition in Diffusion Models Reveals the Hierarchical Nature of Data

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:20.970397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8aef35c-367d-42d3-b983-eabc606ef55c · outbound

This paper cites b1ade series of models , 2024.

BlueGlass: A Framework for Composite AI Safety b1ade series of models , 2024

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:46:25.768780Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 857dab4a-4f74-4e98-97d2-0855672292b1 · outbound

This paper cites The 'strong' feature hypothesis could be wrong.

BlueGlass: A Framework for Composite AI Safety The 'strong' feature hypothesis could be wrong

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:46:25.591968Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2faf6f59-3585-4f9e-a665-1375f64d4dca · outbound

This paper cites Negative Results for SAEs On Downstream Tasks and Deprioritising SAE Research (GDM Mech Interp Team Progress Update \#2).

BlueGlass: A Framework for Composite AI Safety Negative Results for SAEs On Downstream Tasks and Deprioritising SAE Research (GDM Mech Interp Team Progress Update \#2)

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:46:25.367268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8a3da632-3e0b-442b-85e2-2ef2c99e7e16 · outbound

This paper cites PaliGemma 2: A Family of Versatile VLMs for Transfer.

BlueGlass: A Framework for Composite AI Safety PaliGemma 2: A Family of Versatile VLMs for Transfer

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:21.301935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2f6727a-56a5-41a2-a1e0-0e65ba8efac6 · outbound

This paper cites Attribution Patching Outperforms Automated Circuit Discovery.

BlueGlass: A Framework for Composite AI Safety Attribution Patching Outperforms Automated Circuit Discovery

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:21.376357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f581f6a-f19e-4337-bba0-09f90abf4149 · outbound

This paper cites Gemini Robotics: Bringing AI into the Physical World.

BlueGlass: A Framework for Composite AI Safety Gemini Robotics: Bringing AI into the Physical World

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:21.455155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 374a1aba-2c34-48d2-95ef-6ba1a555a2d8 · outbound

This paper cites L., McDougall, C., MacDiarmid, M., Freeman, C.

BlueGlass: A Framework for Composite AI Safety L., McDougall, C., MacDiarmid, M., Freeman, C

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:46:25.168007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0ed0daa9-1d69-47ee-b766-db511d0f2bec · outbound

This paper cites Deep Learning and the Information Bottleneck Principle.

BlueGlass: A Framework for Composite AI Safety Deep Learning and the Information Bottleneck Principle

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:21.620113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ffc898e-b009-4868-9660-4c6490e37a57 · outbound

This paper cites HuggingFace's Transformers: State-of-the-art Natural Language Processing.

BlueGlass: A Framework for Composite AI Safety HuggingFace's Transformers: State-of-the-art Natural Language Processing

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:21.699195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffd8580b-fa19-40ae-9f32-7c3ce4f756fe · outbound

This paper cites Detectron2.

BlueGlass: A Framework for Composite AI Safety Detectron2

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:46:24.955158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c56b6820-0adb-4373-9b3d-0f16f9b40ddc · outbound

This paper cites Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks.

BlueGlass: A Framework for Composite AI Safety Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:46:24.714013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 86ec7568-ca42-4508-b65a-5b75bd54ac0f · outbound

This paper cites Diffusion models: A comprehensive survey of methods and applications, 2024.

BlueGlass: A Framework for Composite AI Safety Diffusion models: A comprehensive survey of methods and applications, 2024

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:21.911308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11e7ef1a-1583-4170-9e1c-6f1df756af55 · outbound

This paper cites BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning.

BlueGlass: A Framework for Composite AI Safety BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:21.976517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c011ffda-9750-4188-9c2a-c87a58e49476 · outbound

This paper cites DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection.

BlueGlass: A Framework for Composite AI Safety DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:22.074193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3db49778-a5be-4ef0-a1c8-f7351c95ef90 · outbound

This paper cites Vision-Language Models for Vision Tasks: A Survey.

BlueGlass: A Framework for Composite AI Safety Vision-Language Models for Vision Tasks: A Survey

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:22.192112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bc78453-d434-4a79-9b95-1fc9f3fee28c · outbound

This paper cites Vision Language Models in Autonomous Driving: A Survey and Outlook.

BlueGlass: A Framework for Composite AI Safety Vision Language Models in Autonomous Driving: A Survey and Outlook

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:22.263759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6084b07b-a3bc-4de6-91d2-ce5533769d9d · outbound

This paper cites Object Detection in 20 Years: A Survey.

BlueGlass: A Framework for Composite AI Safety Object Detection in 20 Years: A Survey

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:22.364436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 306e0605-2734-4201-9e22-f5f69268bb97 · outbound

This paper cites Grokking phase transitions in learning local rules with gradient descent.

BlueGlass: A Framework for Composite AI Safety Grokking phase transitions in learning local rules with gradient descent

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:22.465170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers