Spaces:
Sleeping
Sleeping
Commit History
-
fallback legacy
Ruzzel Mendoza18f4339 -
fix
Ruzzel Mendoza28a415d
-
Fix transform_consistency default + expose agreement counts
Ruzzel MendozaReporting bug (from review of the production washed-out response): compute_transform_consistency returned the neutral (1.0, None) default even when there were NO agreeing block pairs, so every unrelated row showed a misleadingly perfect consistency of 1.0 next to a raw/calibrated score of 0. That is the root of the reported page of constants: raw_similarity 0 + calibrated_confidence 0 + transform_consistency 1.0 + content_blocks_used 5. Fix (reporting-only; zero score impact): - compute_transform_consistency([]) now returns (0.0, None). Only a non-empty set of agreements that is entirely geometrically uninformative (e.g. center-center) keeps the neutral (1.0, None); the MIN_CONSENSUS_BLOCKS cap continues to guard against single coincidental matches. - Algebra unchanged: with no block agreements the block contribution is already 0, so the consistency multiplier (0 or 1) does not change the score. Expose agreement counts on every match object and the compare payload: - transfor…6f114bb
-
API: wire new scoring fields through /plagiarism responses - db/web/best_match and every other_matches entry now carry raw_similarity, raw_similarity_legacy, calibrated_confidence, transform_consistency, content_blocks_used, low_content_warning alongside the unchanged similarity field - best_match picked by calibrated_confidence (monotonic in raw score; tie-break semantics unchanged) - top-level low_content_warning on both endpoints (upload-side flag for /check/web, either-image flag for /compare) - hashes payload blocks now include entropy tags (additive) - drop debug print of the full artwork payload - verified end-to-end with a stubbed-services smoke test: /compare and /check/web return the documented field set
Ruzzel Mendoza2dac237
-
removed pyinstrument
Ruzzel Mendozaef4e0ab -
add parallelization to generating hash from serp
Ruzzel Mendoza0c2a3e0
-
Show Multiple Matches for Plagiarized Artworks
Ruzzel MendozaModify the plagiarism detection query/algorithm to return an array of the top 3-5 matches instead of just the top 1. The API should return the image URLs and similarity percentages for each match. The frontend team will then need to map through this data to display a grid or carousel of the detected similarities.1a39441
-
change url to return the id of the artwork
Ruzzel Mendoza030a111 -
rename route name for compare_two_artsworks
Ruzzel Mendoza9beeff1 -
add route for comparing two images
Ruzzel Mendoza5315099 -
integrate database scan to upload plagiarism api
Ruzzel Mendozabfdc38e -
add the hashes to plagiarism upload response
Ruzzel Mendozaa0fc0ed -
add success response to plagiarism upload
Ruzzel Mendozaac976fc -
change plagiarism upload to return only the best match
Ruzzel Mendoza828f661 -
add asset url to db best match
Ruzzel Mendoza017dad9 -
Changed PlagiarismWebResult type structure to db scan
Ruzzel Mendozaf2dc9bb -
plagiarism check route name
Ruzzel Mendoza65909f2 -
plagiarism check route name
Ruzzel Mendoza662d7e0 -
database similarity check
Ruzzel Mendoza17c6fb0
-
rework plagiarism algo to grid based hashing
Ruzzel Mendoza1998795
-
add original and unaltered phash to the return structure of web plagiarism search result
Ruzzel Mendozae3bcf7c -
rework return structure of web plagiarism search result
Ruzzel Mendoza64c549c
-
Change Plagiarism Check from a websocket into a normal API POST request
Ruzzel Mendozab35f641
-
Clean Deployment for Hugging Face
Ruzzel Mendoza887791e