{ "access": { "embargo": { "active": false, "reason": null }, "files": "public", "record": "public", "status": "open" }, "created": "2025-09-17T09:00:20.906711+00:00", "custom_fields": { "meeting:meeting": { "acronym": "FASTML25", "dates": "1-5 September 2025", "place": "Zurich, Switzerland" } }, "deletion_status": { "is_deleted": false, "status": "P" }, "file_key": "files/sbyss-as968__FM_Collide2V_EMoreno.pdf", "files": { "count": 1, "enabled": true, "entries": { "FM_Collide2V_EMoreno.pdf": { "access": { "hidden": false }, "checksum": "md5:065104c42f4d0548a0bba4edfad9707d", "ext": "pdf", "id": "649ed99d-12e7-4a59-b076-852787877bc5", "key": "FM_Collide2V_EMoreno.pdf", "metadata": { "height": 1080, "width": 1920 }, "mimetype": "application/pdf", "size": 10308960 } }, "order": [], "total_bytes": 10308960 }, "id": "sbyss-as968", "is_draft": false, "is_published": true, "links": { "access": "https://repository.cern/api/records/sbyss-as968/access", "access_grants": "https://repository.cern/api/records/sbyss-as968/access/grants", "access_groups": "https://repository.cern/api/records/sbyss-as968/access/groups", "access_links": "https://repository.cern/api/records/sbyss-as968/access/links", "access_request": "https://repository.cern/api/records/sbyss-as968/access/request", "access_users": "https://repository.cern/api/records/sbyss-as968/access/users", "archive": "https://repository.cern/api/records/sbyss-as968/files-archive", "archive_media": "https://repository.cern/api/records/sbyss-as968/media-files-archive", "communities": "https://repository.cern/api/records/sbyss-as968/communities", "communities-suggestions": "https://repository.cern/api/records/sbyss-as968/communities-suggestions", "doi": "https://doi.org/10.17181/sbyss-as968", "draft": "https://repository.cern/api/records/sbyss-as968/draft", "file_modification": "https://repository.cern/api/records/sbyss-as968/file-modification", "files": "https://repository.cern/api/records/sbyss-as968/files", "latest": "https://repository.cern/api/records/sbyss-as968/versions/latest", "latest_html": "https://repository.cern/records/sbyss-as968/latest", "media_files": "https://repository.cern/api/records/sbyss-as968/media-files", "parent": "https://repository.cern/api/records/7swp7-c5139", "parent_doi": "https://doi.org/10.17181/7swp7-c5139", "parent_doi_html": "https://repository.cern/doi/10.17181/7swp7-c5139", "parent_html": "https://repository.cern/records/7swp7-c5139", "preview_html": "https://repository.cern/records/sbyss-as968?preview=1", "quota_increase": "https://repository.cern/api/records/sbyss-as968/quota-increase", "request_deletion": "https://repository.cern/api/records/sbyss-as968/request-deletion", "requests": "https://repository.cern/api/records/sbyss-as968/requests", "reserve_doi": "https://repository.cern/api/records/sbyss-as968/draft/pids/doi", "self": "https://repository.cern/api/records/sbyss-as968", "self_doi": "https://doi.org/10.17181/sbyss-as968", "self_doi_html": "https://repository.cern/doi/10.17181/sbyss-as968", "self_html": "https://repository.cern/records/sbyss-as968", "self_iiif_manifest": "https://repository.cern/api/iiif/record:sbyss-as968/manifest", "self_iiif_sequence": "https://repository.cern/api/iiif/record:sbyss-as968/sequence/default", "thumbnails": { "10": "https://repository.cern/api/iiif/record:sbyss-as968:FM_Collide2V_EMoreno.pdf/full/%5E10,/0/default.jpg", "100": "https://repository.cern/api/iiif/record:sbyss-as968:FM_Collide2V_EMoreno.pdf/full/%5E100,/0/default.jpg", "1200": "https://repository.cern/api/iiif/record:sbyss-as968:FM_Collide2V_EMoreno.pdf/full/%5E1200,/0/default.jpg", "250": "https://repository.cern/api/iiif/record:sbyss-as968:FM_Collide2V_EMoreno.pdf/full/%5E250,/0/default.jpg", "50": "https://repository.cern/api/iiif/record:sbyss-as968:FM_Collide2V_EMoreno.pdf/full/%5E50,/0/default.jpg", "750": "https://repository.cern/api/iiif/record:sbyss-as968:FM_Collide2V_EMoreno.pdf/full/%5E750,/0/default.jpg" }, "versions": "https://repository.cern/api/records/sbyss-as968/versions" }, "media_files": { "count": 0, "enabled": false, "entries": {}, "order": [], "total_bytes": 0 }, "metadata": { "creators": [ { "affiliations": [ { "name": "Massachusetts Inst. of Technology (US)" } ], "person_or_org": { "family_name": "Moreno", "given_name": "Eric Anton", "identifiers": [ { "identifier": "0000-0001-5666-3637", "scheme": "orcid" } ], "name": "Moreno, Eric Anton", "type": "personal" } } ], "description": "
\n

Modern foundation models (FMs) have pushed the frontiers of language, vision, and multi-model tasks by training ever-larger neural networks (NN) on unprecedented volumes of data. The use of FM models has yet to be established in collider physics, which both lack a comparably sized, general-purpose dataset on which to pre-train universal event representations, and a clear demonstrable need. Real-time event identification presents a possible need due to a requirement for fast event classification and selection of all possible collisions at the LHC. As a result, we construct a dual-view LHC collision dataset (COLLIDE-2V), a 50TB public dataset comprising ~750 million proton-proton events generated with MadGraph + Pythia + Delphes under High-Luminosity LHC conditions (<μ> = 200). Spanning everything from minimum-bias and γ+jets to top, Higgs, di-boson, multi-boson, exotic long-lived signatures and dark showers, the sample covers 50+ distinct processes and >99% of the CMS Run-3 trigger menu in a single coherent format. To allow for effective real-time event interpretation each event is provided twice, as Parquet files which retain physics-critical content:

\n\n\n\n\n\n

As a proof-of-concept, COLLIDE-2V supports a wide spectrum of research applications ranging from few-shot transfer learning, fine-tuning, pileup mitigation, detector-level generative modelling, cross-experiment benchmarking, to fast simulation surrogates and real-time trigger inference, and entirely novel anomaly-detection - thereby accelerating the shift from handcrafted topology cuts to data-driven decision making throughout the HL-LHC program.

\n
", "funding": [ { "funder": { "id": "014bj2y47", "name": "Schmidt Family Foundation" } } ], "identifiers": [], "publication_date": "2025-09-03", "publisher": "Next Generation Triggers, CERN", "references": [ { "reference": "https://indico.cern.ch/event/1496673/contributions/6637964/" } ], "related_identifiers": [], "resource_type": { "id": "presentation", "title": { "cs": "Prezentace", "de": "Präsentation", "en": "Presentation", "sv": "Presentation" } }, "rights": [ { "description": { "en": "The Creative Commons Attribution license allows re-distribution and re-use of a licensed work on the condition that the creator is appropriately credited." }, "icon": "cc-by-icon", "id": "cc-by-4.0", "props": { "scheme": "spdx", "url": "https://creativecommons.org/licenses/by/4.0/legalcode" }, "title": { "en": "Creative Commons Attribution 4.0 International" } } ], "title": "COLLIDE-2V - 750 Million Dual-View LHC Event Dataset for Low-Latency ML" }, "parent": { "access": { "owned_by": { "user": "39013" }, "settings": { "accept_conditions_text": null, "allow_guest_requests": false, "allow_user_requests": false, "secret_link_expiration": 0 } }, "communities": { "default": "da007c73-b7a0-4672-8f99-11faf13bab28", "entries": [ { "access": { "member_policy": "closed", "members_visibility": "public", "record_submission_policy": "open", "review_policy": "closed", "visibility": "public" }, "children": { "allow": false }, "created": "2025-06-18T07:31:01.048123+00:00", "deletion_status": { "is_deleted": false, "status": "P" }, "id": "da007c73-b7a0-4672-8f99-11faf13bab28", "links": {}, "metadata": { "funding": [ { "funder": { "id": "014bj2y47", "name": "Schmidt Family Foundation" } } ], "title": "Next Generation Triggers", "website": "https://nextgentriggers.web.cern.ch/" }, "revision_id": 12, "slug": "nextgentriggers", "updated": "2025-09-29T09:50:50.476550+00:00" } ], "ids": [ "da007c73-b7a0-4672-8f99-11faf13bab28" ] }, "id": "7swp7-c5139", "pids": { "doi": { "client": "datacite", "identifier": "10.17181/7swp7-c5139", "provider": "datacite" } } }, "pids": { "doi": { "client": "datacite", "identifier": "10.17181/sbyss-as968", "provider": "datacite" }, "oai": { "identifier": "oai:oai:repository.cern::sbyss-as968", "provider": "oai" } }, "revision_id": 7, "source_file_key": "FM_Collide2V_EMoreno.pdf", "source_file_url": "https://repository.cern/api/records/sbyss-as968/files/FM_Collide2V_EMoreno.pdf/content", "stats": { "all_versions": { "data_volume": 1061822880.0, "downloads": 103, "unique_downloads": 87, "unique_views": 120, "views": 122 }, "this_version": { "data_volume": 1061822880.0, "downloads": 103, "unique_downloads": 87, "unique_views": 120, "views": 122 } }, "status": "published", "updated": "2025-10-30T13:33:24.364675+00:00", "versions": { "index": 1, "is_latest": true } }