Every commit scored for change-risk against this repo's own history, so 'elevated' means elevated here rather than on some global curve.
Needs review
94 commits sit in this repo's top risk tercile, which is 34% of the 280scored. The cut is drawn against this codebase's own history rather than a global curve, so a quiet repo still fills its top band, and here it starts at 4.1 out of 10. What pushes a commit up is size and spread together: a large change confined to one area scores below a smaller one scattered across a dozen files.
Commit categories over time, read off the subject line. Fixes carry the accent because that is the series this chart exists to show.
Began other-led, now leaning docs.
Ranked by change-risk, highest first. Priority is a tercile of this repo's own distribution, so a quiet repo still fills its top band.
| # | Commit | Author | When | Lines | Risk | Top driver |
|---|---|---|---|---|---|---|
| 1 | 208a5ae1Updated | Kenobi98 | 1y ago | +3.0M -1 | 100%Elevated | more lines added than baseline |
| 2 | 98fdddcaupdated af2 pred for example | Kenobi98 | 1y ago | +3.9K -1.6K | 99%Elevated | more lines added than baseline |
| 3 | 2d69c5b8Dataset and training code | Kenobi98 | 1y ago | +17.8K -0 | 99%Elevated | more lines added than baseline |
| 4 | bea6bc4eanalysis scripts | Kenobi98 | 1y ago | +1.9K -0 | 99%Elevated | more lines added than baseline |
| 5 | 87889077Updated | Kenobi98 | 1y ago | +1.6K -2 | 98%Elevated | more lines added than baseline |
| 6 | b6149924new model configs | Kenobi98 | 1y ago | +952 -0 | 98%Elevated | more lines added than baseline |
| 7 | b2c53464update license | Shruthi Viswanath | 4mo ago | +674 -0 | 98%Elevated | more lines added than baseline |
| 8 | beca748cscript to use disobind | Kenobi98 | 1y ago | +771 -0 | 98%Elevated | more lines added than baseline |
| 9 | 8e2ce621obtain and analyze preds for idppi | Kenobi98 | 1y ago | +605 -0 | 97%Elevated | more lines added than baseline |
| 10 | eb71ea3crun disobind on full protein | Kenobi98 | 1y ago | +520 -0 | 96%Elevated | more lines added than baseline |
| 11 | 586d27acget seq and cmap for PDB entry | Kenobi98 | 1y ago | +531 -0 | 96%Elevated | more lines added than baseline |
| 12 | 78fa21caadded support for using full AF2 structure | Kenobi98 | 1y ago | +500 -144 | 96%Elevated | more lines added than baseline |
| 13 | 847aea91Models/params/embedding | Kenobi98 | 1y ago | +744 -0 | 96%Elevated | more lines added than baseline |
| 14 | 2fb68250avg2d ignore pads model config | Kenobi98 | 1y ago | +360 -0 | 95%Elevated | more lines added than baseline |
| 15 | 37e0047av19 avg2d model configs | Kenobi98 | 1y ago | +360 -0 | 95%Elevated | more lines added than baseline |
| 16 | 7037dd02avg2d model configs | Kenobi98 | 1y ago | +360 -0 | 95%Elevated | more lines added than baseline |
| 17 | 26e749e0obtain PED entries | Kenobi98 | 1y ago | +386 -0 | 94%Elevated | more lines added than baseline |
| 18 | 88532e00bug fix: interaction_mask; some reorganization | Kenobi98 | 1y ago | +255 -220 | 93%Elevated | more lines added than baseline |
| 19 | 115be5c5creating slim, aa masks | Kenobi98 | 1y ago | +264 -12 | 93%Elevated | more lines added than baseline |
| 20 | 033ca94ftemp: evaluate ood/peds/misc/other methods | Kenobi98 | 1y ago | +270 -41 | 93%Elevated | more lines added than baseline |
| 21 | e643c906create idppi input for diso | Kenobi98 | 1y ago | +235 -0 | 93%Elevated | more lines added than baseline |
| 22 | 21c567e5no fragmenting for disobind input | Kenobi98 | 1y ago | +213 -0 | 92%Elevated | more lines added than baseline |
| 23 | 847557c2get stats for train/ood set | kenobi98 | 11mo ago | +198 -0 | 92%Elevated | more lines added than baseline |
| 24 | f5f5c193added support for different model params. clean up. | Kenobi98 | 1y ago | +198 -32 | 92%Elevated | more lines added than baseline |
| 25 | ff486da4Patched AF2 preds | Kenobi98 | 1y ago | +181 -19 | 92%Elevated | more lines added than baseline |
| 26 | 8e844ab2added vote based analysis | Kenobi98 | 1y ago | +162 -106 | 90%Elevated | more lines added than baseline |
| 27 | a8527046obtain predictions from aiupred and deepdisobind | Kenobi98 | 1y ago | +175 -0 | 90%Elevated | more lines added than baseline |
| 28 | 2895857bobtain af2/3 inputs too | Kenobi98 | 1y ago | +163 -34 | 90%Elevated | more lines added than baseline |
| 29 | bb0dce98added support for using different model params | Kenobi98 | 1y ago | +163 -36 | 90%Elevated | more lines added than baseline |
| 30 | bdbeb594other methods on p1 only | Kenobi98 | 1y ago | +141 -138 | 89%Elevated | more lines added than baseline |
| 31 | d48d5c64PEDS dataset pipeline complete | Kenobi98 | 1y ago | +138 -57 | 89%Elevated | more lines added than baseline |
| 32 | c02d4aa5update | Kenobi98 | 1y ago | +115 -46 | 89%Elevated | more lines added than baseline |
| 33 | 6be6768fprepare input for aiupred and deepdisobind | Kenobi98 | 1y ago | +133 -0 | 88%Elevated | more lines added than baseline |
| 34 | f6b56328not using max_num_chains | Kenobi98 | 1y ago | +127 -127 | 88%Elevated | more lines added than baseline |
| 35 | de6a97dfaded support for fasta input; added example | kenobi98 | 1mo ago | +158 -13 | 87%Elevated | more lines added than baseline |
| 36 | b785ffe3chimera script for case study | Kenobi98 | 1y ago | +130 -0 | 87%Elevated | more lines added than baseline |
| 37 | 54ff873cusing updated model | Kenobi98 | 1y ago | +116 -124 | 87%Elevated | more lines added than baseline |
| 38 | e2f252c5save samplewise f1 for misc dataset | Kenobi98 | 1y ago | +111 -293 | 87%Elevated | more lines added than baseline |
| 39 | 8c5371dballow AF2 pred of any length - testing | Kenobi98 | 1y ago | +159 -170 | 87%Elevated | more lines added than baseline |
| 40 | 26376270added morfchibi preds | Kenobi98 | 1y ago | +73 -11 | 86%Elevated | more lines added than baseline |
| 41 | fa66ebfachanged slims to lips | Kenobi98 | 1y ago | +55 -64 | 85%Elevated | more lines added than baseline |
| 42 | 00708ccfadded masks for slims, aa types | Kenobi98 | 1y ago | +64 -32 | 85%Elevated | more lines added than baseline |
| 43 | be7d1cbdadded cg preds for other methods | kenobi98 | 11mo ago | +54 -24 | 84%Elevated | more lines added than baseline |
| 44 | 1e866d0cminor changes | Kenobi98 | 1y ago | +46 -32 | 84%Elevated | more lines added than baseline |
| 45 | c6998fb2Updated case sp analysis | Kenobi98 | 1y ago | +52 -34 | 84%Elevated | more lines added than baseline |
| 46 | 3ba54c3awrite benchmark details to json file | Kenobi98 | 1y ago | +55 -3 | 84%Elevated | more lines added than baseline |
| 47 | f2043933analysis readme | Kenobi98 | 1y ago | +51 -0 | 84%Elevated | more lines added than baseline |
| 48 | 7bdf676ebug fix in get_morfchibi_predictions() | Kenobi98 | 1y ago | +46 -36 | 83%Elevated | more lines added than baseline |
| 49 | 685e5970update | Kenobi98 | 1y ago | +41 -15 | 83%Elevated | more lines added than baseline |
| 50 | 6ccedd88Update README.md | Shruthi Viswanath | 1y ago | +39 -34 | 83%Elevated | more lines added than baseline |
Two views of the same model: where the cuts fall, and what commit shape lands you above them.
Every scored commit, binned on the raw 0 to 10 score rather than the percentile. Percentile ranks are uniform by construction, so that axis has no shape to draw. The dashed lines are the tercile cuts behind each row's priority pill.
The 200 most recent commits, on their own recency sample rather than the feed above: that defaults to risk-sorted, so reusing it would plot only the top tercile and call it the spread. Big and scattered is what the model penalises. Click a dot to open it.
isblab/disobind has 283 commits in its history from 5 contributors, the first of them Sep 28, 2024. In the last 90 days 1 file was touched, 1 times in total, most often run_disobind.py. Every commit is scored for change risk from its size, spread and the history of the files it touches.
