Files
ZacharyZhang-NY 77219c930b Add third-party benchmark suite frozen at 50,789 sources / 5,308 queries
Ground truth comes only from third-party annotations (MMLongBench-Doc
evidence_page_ids, VisRAG qrels, ScreenSpot-v2 bboxes, Video-MME QA,
LongMemEval answer_session_ids, CodeSearchNet func_path+func_name) and
from document structure; no model judgement is used anywhere.

- bench/corpus/manifest.jsonl: 28 sources with url, retrieved_at, sha256,
  annotation_source, license, files[]; verified by bench.manifest_check
- bench/sets/{pdf,image,ui_screenshot,video,code,conversation}.{jsonl} plus
  corpus indexes and a manifest that freezes every file's sha256
- 2,928 answerable + 2,380 unanswerable queries over 854 holders; every
  query carries scope {holder, scenario, as_of} for transactive routing
- bench/validate_sets.py fails on missing gold, holder mismatch between
  gold and query, gold observed after as_of, and manifest digest drift
2026-10-06 12:05:43 -04:00

960 lines
25 KiB
JSON

{
"corpus_manifest": "corpus/manifest.jsonl",
"corpus_manifest_sha256": "8fc1ed861c891d778853d41107630869f9eb267a669c5d1038e389de80114347",
"corpus_records": 50789,
"holders": 854,
"modalities": {
"code": {
"corpus_file": "corpus/code.jsonl",
"corpus_records": 21976,
"corpus_sha256": "0c7a0d220e1f87cd497acf376c0371790abbfdbdaf727916e13e766c934df5cc",
"holders": [
"20tab-twentytab-treeeditor",
"3DLIRIOUS-MeshLabXML",
"4degrees-riffle",
"5j9-wikitextparser",
"5monkeys-django-bananas",
"AartGoossens-goldencheetahlib",
"AkihikoITOH-capybara",
"Alignak-monitoring-contrib-alignak-backend-client",
"AnthonyMRios-pymetamap",
"Azure-Azure-MachineLearning-ClientLibrary-Python",
"Azure-azure-sdk-for-python",
"BD2KGenomics-toil-lib",
"BHSPitMonkey-vmflib",
"BlueDragonX-detach",
"CITGuru-PyInquirer",
"CLARIAH-iribaker",
"Chilipp-sphinx-nbexamples",
"ChrisBeaumont-soupy",
"CiscoDevNet-webexteamssdk",
"Clinical-Genomics-scout",
"ContinuumIO-pycosat",
"Crypto-toolbox-btfxwss",
"Danielhiversen-PyXiaomiGateway",
"Dirrot-python-cryptocoincharts-api",
"DiscordBotList-DBL-Python-Library",
"EpistasisLab-scikit-mdr",
"Erotemic-progiter",
"Erotemic-xdoctest",
"GGiecold-Density_Sampling",
"Gandi-pyramid_kvs",
"GeoffAtHome-lightwave",
"GreatFruitOmsk-tailhead",
"HaaLeo-pylint-file-header",
"HumanBrainProject-hbp-service-client",
"HydraChain-hydrachain",
"IEMLdev-ieml",
"IdentityPython-fedoidcmsg",
"JIC-CSB-jicbioimage.illustrate",
"Jasily-jasily-python",
"Jaymon-pyt",
"Jaza-s3-saver",
"JonathanRaiman-ciseau",
"JukeboxPipeline-jukedj",
"Julian-Ivoire",
"Julian-Virtue",
"Kroisse-FormEncode-Jinja2",
"L3viathan-sql-mojo-parser",
"LLNL-scraper",
"LionelAuroux-pyrser",
"LordSputnik-mutagen",
"Loudr-asana-hub",
"LudovicRousseau-PyKCS11",
"LuminosoInsight-luminoso-api-client-python",
"ManageIQ-manageiq-api-client-python",
"MartinHjelmare-leicacam",
"MaxStrange-AudioSegment",
"MeirKriheli-django-bidi-utils",
"MeirKriheli-python-bidi",
"Microsoft-botbuilder-python",
"MinchinWeb-minchin.text",
"MisterY-price-database",
"MitchellChu-torndsession",
"MomsFriendlyRobotCompany-fake_rpi",
"MuhammedHasan-sklearn_utils",
"Music-Moo-music2storage",
"MycroftAI-padaos",
"NLeSC-pycoeman",
"NarrativeScience-lsi",
"NateFerrero-oauth2lib",
"Nekmo-amazon-dash",
"Nekroze-greencard",
"Nic30-hwt",
"Numergy-yoda",
"ONSdigital-sdc-cryptography",
"OldhamMade-exemelopy",
"OpenKMIP-PyKMIP",
"OpenMath-py-openmath",
"Overdrivr-pytelemetry",
"Patreon-multiget-cache-py",
"PierreRaybaut-PyQtdoc",
"Pirionfr-pyLinky",
"PolicyStat-docx2html",
"Polyconseil-devpi-metawheel",
"PyCQA-pylint",
"PyFilesystem-s3fs",
"PyProphet-pyprophet",
"PythonSanSebastian-docstamp",
"Qiskit-qiskit-terra",
"RRZE-HPC-kerncraft",
"RazerM-yourls-python",
"SeabornGames-Logger",
"SectorLabs-django-postgres-extra",
"SiLab-Bonn-pixel_clusterizer",
"SketchingDev-Doodle-Dashboard",
"Skyscanner-pages",
"SmBe19-praw-OAuth2Util",
"SmartDeveloperHub-sdh-curator-py",
"SmokinCaterpillar-pypet",
"StackSentinel-stacksentinel-python",
"StaticCube-python-synology",
"TDG-Platform-cloud-harness",
"Terrance-SkPy",
"Tivix-django-rest-auth",
"Toblerity-rtree",
"ToucanToco-toucan-data-sdk",
"Trim21-sdu_bkjws",
"Tsjerk-Insane",
"UCBerkeleySETI-blimpy",
"UDST-pandana",
"URXtech-cmph-cffi",
"Valuehorizon-valuehorizon-forex",
"VingtCinq-python-resize-image",
"VorskiImagineering-C3PO",
"WGBH-wagtail-streamfieldtools",
"WhoopInc-pytsdb",
"WoLpH-mt940",
"Yaco-Sistemas-django-transmeta",
"Yelp-py_zipkin",
"Yubico-python-u2flib-host",
"ZELLMECHANIK-DRESDEN-fcswrite",
"Zsailer-pyasr",
"a-tal-nagaram",
"abau171-highfive",
"accraze-pymtranslate",
"adafruit-Adafruit_Python_PureIO",
"addok-addok",
"admiralobvious-flask-mysqldb",
"agabrown-PyGaia",
"agile-geoscience-striplog",
"aholkner-bacon",
"albertodonato-prometheus-aioexporter",
"alexprengere-currencyconverter",
"alexseitsinger-find_best_string",
"alghafli-fileslice",
"algofairness-BlackBoxAuditing",
"alimuldal-PyFNND",
"allanlei-django-argparse-command",
"alpacahq-alpaca-trade-api-python",
"ambitioninc-python-logentries-api",
"amcat-progressmonitor",
"amelchio-eternalegypt",
"amorison-loam",
"amyth-django-instapush",
"analytehealth-django-analytics",
"andrefsp-pyflot",
"andreikop-python-ws-discovery",
"anentropic-dirtyebay",
"ankitmathur3193-song-cli",
"ansible-ansible-lint",
"antevens-listen",
"apache-airflow",
"appier-h5sparse",
"appknox-google-chartwrapper",
"arlyon-hyperion",
"arve0-microscopestitching",
"asciimoo-searx",
"ashleysommer-sanic-cors",
"assemblerflow-flowcraft",
"astrofrog-numtraits",
"astrorafael-twisted-mqtt",
"athre0z-wasm",
"atlassistant-pychatl",
"attm2x-m2x-python",
"audiencepi-SimilarWeb-Python",
"ausaki-python-validator",
"authomatic-authomatic",
"avelino-bottle-auth",
"awentzonline-keras-vgg-buddy",
"bakwc-PySyncObj",
"benhoff-microphone",
"bennylope-django-taggit-labels",
"bheinzerling-descriptors",
"bicv-LogGabor",
"bigdatacesga-kvstore",
"bindlock-vklancer",
"bipsandbytes-django-api",
"bitlabstudio-django-dashboard-app",
"bitlabstudio-django-hero-slider",
"bivab-smbus-cffi",
"bjodah-pycvodes",
"bjoernricks-python-quilt",
"bkg-greenwich",
"bkosciow-python_iot-1",
"blockstack-packages-keychain-manager-py",
"blockstack-zone-file-py",
"bloomreach-s4cmd",
"bluedisk-hangul-toolkit",
"bmaeser-pyque",
"bolt-project-bolt",
"boto-s3transfer",
"boundary-pulse-api-cli",
"brandon-rhodes-python-jplephem",
"bruth-cypher",
"bsmithyman-problemo",
"bucknerns-concordance",
"bunchesofdonald-photohash",
"buzzfeed-phonon",
"c-soft-satel_integra",
"caktus-rapidsms-twilio",
"calston-tensor",
"capitalone-giraffez",
"cartoonist-pystream-protobuf",
"cassinyio-SwarmSpawner",
"ccubed-Shosetsu",
"celiao-tmdbsimple",
"cgarciae-dicto",
"chairco-pyRscript",
"chaoss-grimoirelab-kingarthur",
"chaoss-grimoirelab-perceval",
"chaoss-grimoirelab-perceval-mozilla",
"chrisjrn-registrasion",
"chrisnorman7-wxgoodies",
"chrisrink10-basilisp",
"chuck1-codemach",
"cloud9ers-gurumate",
"clouserw-tower",
"cmcginty-PyWeather",
"cnu-scrapy-random-useragent",
"codeghar-brokerlso",
"codeinthehole-django-async-messages",
"codelv-enaml-web",
"coleifer-irc",
"collab-project-django-admin-footer",
"connectordb-connectordb-python",
"coops-r53",
"crankycoder-hydra",
"cthoyt-ols-client",
"cyberdelia-metrology",
"d0ugal-home",
"dagster-io-dagster",
"datacamp-pythonwhat",
"dave-shawley-ietfparse",
"davidmiller-urlhelp",
"dbcli-cli_helpers",
"deepmipt-DeepPavlov",
"dessibelle-sorl-thumbnail-serializer-field",
"dialoguemd-multi-method",
"disqus-python-phabricator",
"django-inplaceedit-django-inplaceedit",
"djangobot-djangobot",
"dogoncouch-lightcli",
"domainaware-parsedmarc",
"dopefishh-pympi",
"dossier-dossier.store",
"draios-python-sdc-client",
"dreidev-Suggestions",
"drestebon-papageorge",
"drewsonne-pyum",
"drhagen-parsita",
"dropseed-combine",
"dry-python-dependencies",
"dsoprea-pytzPure",
"dwavesystems-minorminer",
"dwhswenson-autorelease",
"eagleflo-adjutant",
"eclarke-melt",
"ecometrica-grandfatherson",
"edavis-django-override-settings",
"edoburu-django-debugtools",
"edoburu-django-tag-parser",
"edx-ecommerce-worker",
"edx-web-fragments",
"eecs-autograder-autograder-sandbox",
"egh-ledger-autosync",
"eisber-sarplus",
"ekmmetering-ekmmeters",
"ekzhu-datasketch",
"ellisonleao-vl",
"elliterate-capybara.py",
"ellmetha-neojsonrpc",
"elyase-masstable",
"eng-tools-geofound",
"erichiggins-gaek",
"ethereum-py_ecc",
"etsinko-pymonoprice",
"eyeseast-python-frontmatter",
"farzadghanei-statsd-metrics",
"fastmonkeys-stellar",
"fatihsucu-pyzomato",
"feifangit-dj-api-auth",
"ferrix-dj-mongohq-url",
"filepreviews-filepreviews-python",
"flit-elapsedtimer",
"fm4d-PyMarkovTextGenerator",
"frascoweb-easywebassets",
"frispete-keyrings.cryptfile",
"fukuball-fuku-ml",
"funilrys-PyFunceble",
"garyelephant-pygrok",
"gawel-panoramisk",
"gears-gears",
"genialis-genesis-pyapi",
"geopython-OWSLib",
"getgauge-gauge-python",
"getsentry-sentry-hipchat-ac",
"ghcollin-multitables",
"gholt-swiftly",
"giffels-CloudStackAIO",
"globality-corp-flake8-logging-format",
"glottobank-python-newick",
"gmr-tornado-elasticsearch",
"gnosis-gnosis-py",
"google-brotli",
"google-gin-config",
"google-pybadges",
"gooofy-py-nltools",
"grampajoe-happy",
"graphql-python-graphene-sqlalchemy",
"greenbender-pynntp",
"griffithlab-civicpy",
"gtaylor-python-route53",
"gtzampanakis-aml",
"gunyarakun-python-shogi",
"gvalkov-tornado-http-auth",
"h2non-pook",
"h2oai-h2o-3",
"hamelsmu-ktext",
"hdima-erlport",
"hipikat-adjspecies",
"hiposfer-o2g",
"hirmeos-entity-fishing-client-python",
"hivetech-dna",
"horazont-aiosasl",
"howie6879-ruia",
"hustlzp-Flask-Boost",
"hydrosquall-tiingo-python",
"ianare-django-memcache-admin",
"iandees-pyosm",
"ibm-watson-iot-iot-python",
"idlesign-django-etc",
"idlesign-django-sitetree",
"idlesign-django-yaturbo",
"impulsare-config",
"incuna-django-pgcrypto-fields",
"incuna-django-user-management",
"incuna-django-wkhtmltopdf",
"ingolemo-python-lenses",
"instagrambot-instabot",
"intel-analytics-BigDL",
"inveniosoftware-counter-robots",
"inveniosoftware-invenio-migrator",
"inveniosoftware-invenio-records-ui",
"ioam-parambokeh",
"ionelmc-python-tblib",
"iotaledger-iota.lib.py",
"iotile-typedargs",
"isambard-uob-budeff",
"its-rigs-Trolly",
"jab-bidict",
"jaraco-jaraco.classes",
"jaraco-jaraco.itertools",
"jaraco-jaraco.util",
"jaraco-svg.charts",
"jaraco-wolframalpha",
"jazzband-django-ddp",
"jdrumgoole-pymongo_formatter",
"jerith-txfake",
"jfialkoff-pyphaxio",
"jgorset-django-kronos",
"jic-dtool-dtool-azure",
"jic-dtool-dtool-s3",
"jjangsangy-py-translate",
"joeblackwaslike-pricing",
"jonashaag-django-addanother",
"jonfaustman-django-frontend",
"joopert-nad_receiver",
"josiahcarlson-rom",
"jp74-django-model-publisher",
"jrfonseca-xdot.py",
"jrxFive-python-nomad",
"jshiv-turntable",
"jtambasco-opticalmaterialspy",
"jterrace-pyssim",
"juga0-dhcpcanon",
"jupyter-widgets-jupyterlab-sidecar",
"justanr-flask-allows",
"justbilt-untp",
"kadrlica-pymodeler",
"kamalshadi-Localization",
"karimbahgat-PyCRS",
"katerina7479-pypdflite",
"keflavich-plfit",
"kejbaly2-comdev",
"kenneth-reitz-dynamo",
"kennethreitz-flask-common",
"kennethreitz-twitter-scraper",
"kgiusti-pyngus",
"kmmbvnr-django-any",
"kolypto-py-smsframework",
"ktdreyer-rhcalendar",
"kurtbrose-sampro",
"kxepal-viivakoodi",
"labstreaminglayer-liblsl-Python",
"lambdalisue-django-codemirror-widget",
"laplacesdemon-django-youtube",
"larsyencken-proj",
"lcharleux-argiope",
"ldesousa-hex-utils",
"leVirve-dcard-spider",
"lensacom-sparkit-learn",
"leovp-steamfiles",
"lepture-flask-oauthlib",
"librosa-librosa",
"lincolnloop-goodconf",
"linjackson78-jstyleson",
"linuxwhatelse-mapper",
"litl-leeroy",
"littlemo-mohand",
"liubola-sangreal-db",
"lkreidberg-batman",
"llimllib-pub",
"lmjohns3-theanets",
"loanzen-probe-py",
"lord63-five.py",
"lsst-sqre-ltd-conveyor",
"lucaslamounier-USGSDownload",
"lvh-txampext",
"makearl-tornado-profile",
"makeev-django-boolean-switch",
"makinacorpus-django-templatetag-handlebars",
"manrajgrover-py-spinners",
"maralla-bmd",
"marcoagner-Flask-QRcode",
"marians-py-daterangestr",
"marrabld-planarradpy",
"marrow-package",
"marrow-web.db",
"marshmallow-code-marshmallow-sqlalchemy",
"matrix-org-python-canonicaljson",
"matthewdeanmartin-find_known_secrets",
"maxcountryman-flask-uploads",
"may-day-wsgicors",
"mblayman-httpony",
"mcs07-MolVS",
"mdgoldberg-sportsref",
"memsql-memsql-python",
"mental32-spotify.py",
"merrychap-shellen",
"mesos-magellan-pyrallelsa",
"mezuro-kalibro_client_py",
"mfcovington-django-project-home-templatetags",
"mikewaters-command-session",
"mjtamlyn-django-cbvpatterns",
"mk-fg-python-onedrive",
"mohabusama-pyguacamole",
"mohan3d-PyOpenload",
"mopidy-mopidy-spotify",
"mordred-descriptor-mordred",
"moreati-ppeg",
"mozilla-iot-webthing-python",
"mozilla-services-sign-xpi-lib",
"mpenning-polymer",
"mrsarm-mongotail",
"mrtazz-notifo.py",
"mseclab-PyJFuzz",
"mshroyer-pointfree",
"mwarkentin-django-watchman",
"mwhooker-jsonselect",
"myint-autoflake",
"napalm-automation-napalm-yang",
"nathforge-validatesns",
"nats-io-asyncio-nats",
"ncolony-ncolony",
"ndokter-dsmr_parser",
"ndrlslz-ternya",
"neherlab-treetime",
"neithere-argh",
"nens-qgispluginreleaser",
"neogenix-jsonklog",
"nesdis-djongo",
"netom-satispy",
"neurodata-ndio",
"neurosynth-neurosynth",
"nicferrier-pyproxyfs",
"nicfit-nicfit.py",
"nickw444-flask-ldap3-login",
"nicolas-van-mailflash",
"nigma-django-twilio-sms",
"ninjaaron-libaaron",
"nixmc-chatter",
"nkgilley-python-ecobee-api",
"not-na-peng3d",
"nprapps-copydoc",
"nsqio-pynsq",
"nvdv-vprof",
"oceanprotocol-oceandb-elasticsearch-driver",
"ojarva-python-sshpubkeys",
"ojengwa-accounting",
"omaciel-pytest-fauxfactory",
"open-mmlab-mmcv",
"opencast-pyCA",
"openergy-oplus",
"openmicroscopy-yaclifw",
"openvenues-pypostal",
"orangain-scrapy-s3pipeline",
"oriontvv-pyaspeller",
"oscarbranson-latools",
"ossobv-exactonline",
"pasztorpisti-kwonly-args",
"pelotoncycle-cycle_detector",
"penguinmenac3-opendatalake",
"pgjones-hypercorn",
"phfaist-pylatexenc",
"philipsoutham-py-mysql2pgsql",
"phoikoi-sisy",
"piface-pifacecommon",
"pltrdy-rouge",
"pmacosta-peng",
"pmbarrett314-curses-menu",
"power-system-simulation-toolbox-psst",
"praekelt-django-analytics",
"praekeltfoundation-seed-control-interface",
"precond-django-customary",
"proofit404-service-factory",
"psd-tools-packbits",
"pyblish-pyblish-maya",
"pyca-pyopenssl",
"pydanny-cookiecutter-django",
"pydron-anycall",
"pyrocat101-moo",
"python-performance",
"python-useful-helpers-advanced-descriptors",
"pytorch-vision",
"quantopian-pgcontents",
"quantum5-pyfortune",
"rackerlabs-timid",
"rainwoodman-bigfile",
"ralphbean-bugwarrior",
"raviparekh-webapp-error-handler",
"rbarrois-aionotify",
"reflect-reflect-python",
"regardscitoyens-cpc-api",
"regebro-pyroma",
"reingart-gui2py",
"respondcreate-django-versatileimagefield",
"ribalba-markdown.highlight",
"ricobl-django-importer",
"riffm-mint",
"rochacon-punch",
"rochapps-django-secure-input",
"rocky-pycolumnize",
"rocky-python3-trepan",
"rodluger-pysyzygy",
"rollbar-pyrollbar",
"rsennrich-Bleualign",
"rupertford-melody",
"rwl-godot",
"sagemath-sage-package",
"salsita-flask-raml",
"savoirfairelinux-num2words",
"saxix-sample-data-utils",
"sbneto-s3conf",
"scheibler-khard",
"schul-cloud-resources-api-v1",
"scrapinghub-dateparser",
"seebass-django-tooling",
"seiferma-deterministic_encryption_utils",
"seporaitis-mysqlparse",
"sergedomk-fiql_parser",
"sergei-maertens-django-systemjs",
"shanbay-sea",
"shaunduncan-giphypop",
"shopkick-flawless",
"siddhantgoel-tornado-sqlalchemy",
"sigmaris-python-gssapi",
"simion-pip-upgrader",
"singularityhub-sregistry-cli",
"six8-polydatum",
"skioo-django-datatrans-gateway",
"skorokithakis-django-loginas",
"slacy-minimongo",
"sloria-aiohttp_utils",
"snare-scruffy",
"snjoetw-py-synology",
"snowplow-snowplow-python-analytics-sdk",
"soimort-you-get",
"solvebio-solvebio-python",
"sontek-pyramid_webassets",
"sophilabs-django-qurl-templatetag",
"sourcesimian-pyTelegramBotAPI",
"sp4ke-howto",
"spotify-pyschema",
"srevenant-onetimejwt",
"ssherar-hook",
"stevelittlefish-littlefish",
"stovorov-IteratorDecorator",
"streamlink-streamlink",
"sublee-zeronimo",
"sundarnagarajan-cffi_utils",
"sunshowers-ntfs",
"susam-ice",
"sveetch-crispy-forms-foundation",
"swarmer-fridge",
"synw-gencharts",
"takluyver-entrypoints",
"tallero-trovotutto",
"tarmstrong-git2json",
"techdragon-python-check-pypi-name",
"tek-amino",
"tek-ribosome",
"tell-k-goolabs",
"tensorflow-probability",
"theduke-django-baseline",
"thombashi-sqliteschema",
"thusoy-pwm",
"tigrawap-pybabel-hbs",
"timheap-django-enumchoicefield",
"tjkessler-PyGenetics",
"tmontaigu-pylas",
"tnkteja-myhelp",
"tomMoral-loky",
"tomasbasham-dominos",
"tomatohater-django-unfriendly",
"tomekwojcik-ForgeryPy",
"tonyseek-flask-navigation",
"trapeze-fancy_tag",
"trec-kba-streamcorpus-pipeline",
"treycucco-pyebnf",
"trp07-messages",
"twaddington-django-gravatar",
"twz915-excel",
"ubyssey-dispatch",
"ui-django-thumbnails",
"umich-brcf-bioinf-Jacquard",
"un33k-django-toolware",
"unistra-django-rest-framework-custom-exceptions",
"uogbuji-amara3-xml",
"uploadcare-pyuploadcare",
"urda-nistbeacon",
"urinieto-msaf",
"uucidl-uu.xunitgen",
"uw-it-aca-uw-restclients-canvas",
"uw-it-aca-uw-restclients-gws",
"vaexio-vaex",
"vahtras-findifftool",
"valentinalexeev-pwaqi",
"valsaven-md5hash",
"varikin-Tigre",
"versae-ipython-cypher",
"victor-o-silva-db_file_storage",
"vint21h-nagios-check-supervisord",
"vint21h-nagios-notification-google-calendar",
"vkorn-pyvizio",
"voidfiles-lark",
"voidpp-vcp",
"vpelletier-python-libaio",
"wagtail-django-modelcluster",
"wangwenpei-fantasy",
"wdecoster-nanogui",
"wildfish-argparsetree",
"williamFalcon-test-tube",
"williballenthin-ida-settings",
"willkg-markus",
"willthames-ansible-review",
"wimglenn-wimpy",
"wreckage-django-happenings",
"wzpan-MusicBoxApi",
"xmartlabs-benderthon",
"xmikos-soapy_power",
"xtuml-pyxtuml",
"xvzf-asyncserial-py",
"yandex-yandex-tank",
"yashaka-selene",
"ybrs-single-beat",
"yeonghoey-yhy",
"yougov-motivation",
"yougov-openpack",
"youtux-pypebbleapi",
"zartstrom-snaptime",
"ze-phyr-us-django-libretto",
"zenodo-zenodo-accessrequests",
"zinic-pynsive",
"zloidemon-aiohttp_jrpc",
"zomux-deepy",
"zorg-zorg-network-camera",
"zqfang-GSEApy",
"zsennenga-module-discovery-utils"
],
"queries": 2474,
"queries_answerable": 1237,
"queries_file": "code.jsonl",
"queries_sha256": "ea7e248386350f95132a398f3710f6ce5f09424ca614fd88c618207f667a553e",
"queries_unanswerable": 1237,
"sources": [
"code-search-net/code_search_net"
]
},
"conversation": {
"corpus_file": "corpus/conversation.jsonl",
"corpus_records": 7188,
"corpus_sha256": "9cc8263c6a6d54ddc86ff1936ca57ddfd03e58d4b6dc0013cd0c47100e95a92f",
"holders": [
"00ca467f",
"01493427",
"06878be2",
"06db6396",
"06f04340",
"07b6f563",
"0862e8bf",
"08e075c7",
"08f4fc43",
"09d032c9",
"0a34ad58",
"0a995998",
"0ddfec37_abs",
"0e5e2d1a",
"0edc2aef",
"10e09553",
"118b2229",
"15745da0_abs",
"157a136e",
"16c90bf4",
"1903aded",
"195a1a1b",
"19b5f2b3_abs",
"1a1907b4",
"1c0ddc50",
"1d4e3b97",
"1da05512",
"1de5cff2",
"2133c1b5",
"21436231",
"2311e44b",
"2698e78f",
"28dc39ac",
"29f2956b",
"2a1811e2",
"2bf43736",
"311778f1",
"32260d93",
"352ab8bd",
"35a27287",
"37d43f65",
"37f165cf",
"38146c39",
"3ba21379",
"3d86fd0a",
"4100d0a0",
"41275add",
"45dc21b6",
"46a3abf7",
"488d3006",
"4c36ccef",
"4dfccbf7",
"505af2f5",
"50635ada",
"51a45a95",
"51c32626",
"54026fce",
"561fabcd",
"577d4d32",
"57f827a0",
"58470ed2",
"5a4f22c0",
"5d3d2817",
"60472f9c",
"6071bd76",
"6456829e_abs",
"65240037",
"66f24dbb",
"6a1eabeb",
"6aeb4375_abs",
"6b168ec8",
"6b7dfb22",
"6d550036",
"6e984302",
"70b3e69b",
"71a3fd6b",
"726462e0",
"7401057b",
"75499fd8",
"75832dbd",
"75f70248",
"77eafa52",
"7a8d0b71",
"830ce83f",
"8464fc84",
"853b0a1d",
"86b68151",
"87f22b4a",
"89527b6b",
"89941a94",
"8a137a7f",
"8a2466db",
"8b9d4367",
"8e91e7d9",
"8ebdbe50",
"95228167",
"95bcc1c8",
"982b5123",
"9bbe84a2",
"a08a253f",
"a2f3aa27",
"a3045048",
"a40e080f",
"a4996e51",
"a82c026e",
"a89d7624",
"af8d2e46",
"afdc33df",
"b0479f84",
"b3c15d39",
"b46e15ee",
"b6019101",
"b759caee",
"b86304ba",
"bc149d6b",
"c6853660",
"c7cf7dfd",
"c8090214_abs",
"cc06de0d",
"cc539528",
"cf22b7bf",
"d596882b",
"d905b33f",
"db467c8c",
"e3fc4d6e",
"e4e14d04",
"e5ba910e_abs",
"e61a7584",
"e8a79c70",
"ed4ddc30",
"eeda8a6d",
"f0e564bc",
"gpt4_0b2f1d21",
"gpt4_1d80365e",
"gpt4_2312f94c",
"gpt4_2f56ae70",
"gpt4_2f8be40d",
"gpt4_468eb064",
"gpt4_4ef30696",
"gpt4_5501fe77",
"gpt4_5dcc0aab",
"gpt4_6dc9b45b",
"gpt4_78cf46a3",
"gpt4_7ddcf75f",
"gpt4_85da3956",
"gpt4_93159ced_abs",
"gpt4_a2d1d1f6",
"gpt4_b5700ca9",
"gpt4_d6585ce9",
"gpt4_e414231e"
],
"queries": 300,
"queries_answerable": 150,
"queries_file": "conversation.jsonl",
"queries_sha256": "dc106d90e7749bee8be01b1fab3b645a5459d7527ef40e7fbf983677d5898d11",
"queries_unanswerable": 150,
"sources": [
"xiaowu0162/longmemeval-cleaned"
]
},
"image": {
"corpus_file": "corpus/image.jsonl",
"corpus_records": 20643,
"corpus_sha256": "4c34a3fbeddbe050431a5e8881d3a2ea56adf6af3448912e700a6f5e919eb76d",
"holders": [
"arxivqa",
"chartqa",
"infovqa",
"mp-docvqa",
"plotqa",
"slidevqa"
],
"queries": 480,
"queries_answerable": 240,
"queries_file": "image.jsonl",
"queries_sha256": "1c74488375c7ec9f3182964d51a5e506273bfd5cf3d126725c3cc431a8333128",
"queries_unanswerable": 240,
"sources": [
"openbmb/VisRAG-Ret-Test-ArxivQA",
"openbmb/VisRAG-Ret-Test-ChartQA",
"openbmb/VisRAG-Ret-Test-InfoVQA",
"openbmb/VisRAG-Ret-Test-MP-DocVQA",
"openbmb/VisRAG-Ret-Test-PlotQA",
"openbmb/VisRAG-Ret-Test-SlideVQA"
]
},
"pdf": {
"corpus_file": "corpus/pdf.jsonl",
"corpus_records": 123,
"corpus_sha256": "68f20f0b5b203b73aa08adbb4e61a512d5c9d55f60d10ea229bbdfc3322cf713",
"holders": [
"Academic-paper",
"Administration-Industry-file",
"Brochure",
"Financial-report",
"Guidebook",
"Research-report-Introduction",
"Tutorial-Workshop"
],
"queries": 984,
"queries_answerable": 766,
"queries_file": "pdf.jsonl",
"queries_sha256": "0cec488e660bf1bfa7ccfc72dbae8b7e3005f0b6a0255028e502296d4ecd4536",
"queries_unanswerable": 218,
"sources": [
"yubo2333/MMLongBench-Doc"
]
},
"ui_screenshot": {
"corpus_file": "corpus/ui_screenshot.jsonl",
"corpus_records": 730,
"corpus_sha256": "5bb110728ba5726f918139743612fcb0ca1a5e91cca2d396aaf4d3b022336570",
"holders": [
"android",
"forum",
"gitlab",
"ios",
"macos",
"shop",
"tool",
"windows"
],
"queries": 640,
"queries_answerable": 320,
"queries_file": "ui_screenshot.jsonl",
"queries_sha256": "2269dd623e67cd851fb3f6b24a4556a8462a37db98e12ad79577c5830167c7c5",
"queries_unanswerable": 320,
"sources": [
"OS-Copilot/ScreenSpot-v2"
]
},
"video": {
"corpus_file": "corpus/video.jsonl",
"corpus_records": 129,
"corpus_sha256": "6965a1e0541922fcb5f7bf943f6e67681bf3a2681bd1f196968621e870dc61c2",
"holders": [
"Artistic-Performance",
"Film-Television",
"Knowledge",
"Life-Record",
"Multilingual",
"Sports-Competition"
],
"queries": 430,
"queries_answerable": 215,
"queries_file": "video.jsonl",
"queries_sha256": "4973231d9f16d214b14923d79a34b85c3d2b423624dea752b1ee91ba09ff778c",
"queries_unanswerable": 215,
"sources": [
"lmms-eval/Video-MME"
]
}
},
"queries": 5308,
"queries_answerable": 2928,
"queries_unanswerable": 2380
}