context
Part 17
ctx:discord/blah/papers/part-17No external document is attached to this context. (Many contexts are pure organisational labels.)
Facts in this context
Grouped by subject. Each subject links to its full article.
Ajaxdavis21 factsex:ajaxdavis
| challengesOthersWith | 34 Percent Benchmark |
| commitsToExamine | Huggingface Paper 2403 03234 |
| expressedEnthusiasm | fuck yeah |
| hasNotYetViewed | Huggingface Paper 2403 03234 |
| identifiesAsBenchmarkToBeat | 34% |
| intendsToDownload | Ancient Dna Samples |
| pingedUser | Discord User 1211062099137265723 |
| postedAt | 2026-04-23 19:03 |
| postedAt | 2026-04-26 20:46 |
| postedAt | 2026-04-26 06:26 |
| postedAt | 2026-04-27 03:11 |
| postedAt | 2026-04-23 19:02 |
| postedAt | 2026-04-26 06:29 |
| postedAt | 2026-04-26 20:47 |
| postedSequentiallyAfter | Lisamegawatts |
| postedUrl | Prbench Paper |
| postedUrl | Akshay Pachaar Tweet |
| quotedTextFrom | Prbench Paper |
| reportsPositiveProgressOn | Toiletpaper Project |
| sharedAttachment | Screencast From 2026 04 27 06 45 23 Webm |
| showsInterestIn | Ancient Dna Samples |
Lisamegawatts14 factsex:lisamegawatts
| frequentlySharesArxivPapers | true |
| postedAt | 2026-04-23 15:42 |
| postedAt | 2026-04-19 10:01 |
| postedAt | 2026-04-20 22:09 |
| postedAt | 2026-05-01 00:57 |
| postedAt | 2026-05-01 22:30 |
| postedAt | 2026-05-02 05:23 |
| postedUrl | Arxiv Paper 2308 07134v2 |
| postedUrl | Huggingface Paper 2403 03234 |
| postedUrl | Nyx Foundation Tweet |
| postedUrl | Cliffordnet Paper |
| postedUrl | Megawatts Notion Concepts |
| postedUrl | Arxiv Paper 2512 24601 |
| sharesTweets | Nyx Foundation Tweet |
Prbench11 factsex:prbench
| buildsOn | Agentified Evaluation Paradigm |
| comprises | Expert Curated Tasks |
| comprisesNum | 30 |
| covers | 11 Subfields of Physics |
| designs | Multi Agent Evaluation Pipeline |
| evaluatesEndToEndReproductionOf | Computational Results From Published Physics Papers |
| introducedIn | Prbench Paper |
| isBenchmarkFor | AI Agents |
| sourcedFromNum | >20 |
| spans | Subfields of Physics |
| spansNum | 11 |
AI Agents5 factsex:ai-agents
| achieveModeratePerformanceIn | Instruction Following |
| achieveModeratePerformanceIn | Methodology Understanding |
| failConsistentlyOn | Data Reproduction Accuracy |
| haveEndToEndCallbackRate | 0 |
| haveLowOverallScores | true |
Foxhop5 factsex:foxhop
| postedAt | 2026-04-20 11:00 |
| postedAt | 2026-04-30 21:36 |
| postedUrl | Lumbda Com |
| sharedAttachment | Andrea Whitepaper Pdf |
| sharesWhitepapers | Andrea Whitepaper Pdf |
Prbench Evaluation2 factsex:prbench-evaluation
| revealsGapBetween | Accurate Execution |
| revealsGapBetween | Scientific Comprehension |
Best Performing System1 factex:best-performing-system
| reachesScore | 0.34 |
Chat Log1 factex:chat-log
| referencesExternalPapers | >5 |
Chat Participants1 factex:chat-participants
| discussAiInPhysics | true |
Cliffordnet Paper1 factex:cliffordnet-paper
| hasTitle | CliffordNet: All You Need is Geometric Algebra |
Current Agents1 factex:current-agents
| oftenFail | Prbench Tasks |
Expert Curated Tasks1 factex:expert-curated-tasks
| sourcedFrom | School of Physics Peking University |
Huggingface Paper 2403 032341 factex:huggingface-paper-2403-03234
| concerns | Ancient Dna Samples |
Multi Agent Evaluation Pipeline1 factex:multi-agent-evaluation-pipeline
| conductsExecutionsIn | Sandboxed Environment |
Prbench Paper1 factex:prbench-paper
| authoredBy | Peking University Physicists |
School of Physics Peking University1 factex:school-of-physics-peking-university
| hostsNumResearchGroups | >20 |
Screencast From 2026 04 27 06 45 23 Webm1 factex:screencast-from-2026-04-27-06-45-23-webm
| likelyDemonstrates | Toiletpaper Project |
This Chat Log1 factex:this-chat-log
| isReply | true |
Toiletpaper Project1 factex:toiletpaper-project
| underDevelopmentBy | Ajaxdavis |