91
edits
Computable Graphs: Difference between revisions
no edit summary
(Add myself) |
No edit summary |
||
| Line 21: | Line 21: | ||
* [[Simularium]] - https://simularium.allencell.org/ | * [[Simularium]] - https://simularium.allencell.org/ | ||
* [[Vivarium Collective]] - https://vivarium-collective.github.io/ | * [[Vivarium Collective]] - https://vivarium-collective.github.io/ | ||
=== First breakout group session === | |||
* anchoring on [[Synthesis center for cell biology]] | |||
* challenge: students wrapping their heads around the model; get really excited once they do | |||
* Dafna: very much like the old issue-based argument maps! | |||
* Belinda: what is scope of the project in terms of users? | |||
** Matt: hoping this accessible all the way to high school students also! | |||
* AI2 has platform for running simulations, make it easy to run and share with others | |||
* Dafna: are there pain points on the input side? (seems painful!) | |||
* Dafna: how similar are the things that people pull out from the same paper? | |||
** Matt: for our field, pretty similar, esp. for well-written papers | |||
** Belinda: compare what each person is highlighting and extract summary that is representative of all the annotations | |||
* Dafna: how useful are these (bits of) knowledge graphs for others? | |||
** Works well within lab; better than unstructured text, motivating to try to create micropublications to summarize outcome 10-week rotation | |||
* Dafna: "compiling" discourse graph to manuscript seems much easier, esp. if have consistent structure and human-in-the-loop | |||
** Similar to brainstorming discussion/ethics statements for a paper given abstract (via GPT-3 | |||
* Belinda: how much variation in paper structure within your field? | |||
** some variations by journal | |||
** some authors (think more highly of themselves), more declarative/general, less clear distinction between claims and evidence | |||
* Aakanksha: | |||
** hypothes.is experiment | |||
** need infra changes | |||
*** help make the case for these changes | |||
**** maybe how much $$ each person would pay for this!!) | |||
**** demonstration of value | |||
**** brainstorming what research projects would be part of this | |||
** | |||
emerging themes/problems: | |||
* idea around changing the reading process somehow (with high hopes for somehting like semantic scholar PD reader that has beginning annotations tuned to what matt is trying to extract, maybe also on the abstract level) --> these could also feed back / forward to other users | |||
** can probably start from this: Scim: Intelligent Faceted Highlights for Interactive, Multi-Pass Skimming of Scientific Papers <nowiki>https://arxiv.org/pdf/2205.04561.pdf</nowiki> | |||
** cross connections to what [[ | |||
* idea of compiling from discourse graph to manuscript seems feasible? | |||
** Belinda could mock something up in OpenAI playground really quickly for a few papers | |||
*** need examples or access to repo | |||
** Could also integrate into Matt's lab via GPT-3 extension | |||
* question: understanding different levels of value of having a knowledge graph for someone else who didn't create it | |||
** --> Joel can add links to ongoing lit review on this question - not resolved yet | |||
* theme/idea: "compiling" from discourse to knowledge graphs (entities as nodes, relations that are | |||
** Aakanksha: often see ontologies in isolation | |||
*** Aakanksha: can look into NLP around adding context to knowledge graphs | |||
** Michael: interesting to think about the user experience on this - how do they interact? | |||
** Grounding abstractions: https://www.susielu.com/data-viz/abstractions | |||
== Next Steps == | == Next Steps == | ||