{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:A5W6JTTUOUBDX6N7N3MQKTJZDL","short_pith_number":"pith:A5W6JTTU","schema_version":"1.0","canonical_sha256":"076de4ce7475023bf9bf6ed9054d391af174538adbcb949aaa4cd95e47f912a6","source":{"kind":"arxiv","id":"2312.03434","version":2},"attestation_state":"computed","paper":{"title":"Quark-versus-gluon tagging in CMS Open Data with CWoLa and TopicFlow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"hep-ph","authors_text":"Ayodele Ore, John Gargalionis, Matthew J. Dolan","submitted_at":"2023-12-06T11:28:54Z","abstract_excerpt":"We use the CMS Open Data to examine the performance of weakly-supervised learning for tagging quark and gluon jets at the LHC. We target $Z$+jet and dijet events as respective quark- and gluon-enriched mixtures and derive samples both from data taken in 2011 at 7 TeV, and from Monte Carlo. CWoLa and TopicFlow models are trained on real data and compared to fully-supervised classifiers trained on simulation. In order to obtain estimates for the discrimination power in real data, we consider three different estimates of the quark/gluon mixture fractions in the data. Compared to when the models a"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2312.03434","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"hep-ph","submitted_at":"2023-12-06T11:28:54Z","cross_cats_sorted":[],"title_canon_sha256":"3848a646a136c6c04e6192247df15bfe164021f961231e3095c1efbd4519a241","abstract_canon_sha256":"e6af4917d5489a1102cab540457f13336fcd2d72c7ad999378f5072cefd3f31c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:44.814640Z","signature_b64":"6kbl7oObjiHRg7X8o5eNmxOp8BPzyDJupj6TsNRLzah4dCgSCt2vLm28yqwQ72iIwuNq94MQWYMfuReP6nniAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"076de4ce7475023bf9bf6ed9054d391af174538adbcb949aaa4cd95e47f912a6","last_reissued_at":"2026-07-05T11:49:44.814118Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:44.814118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quark-versus-gluon tagging in CMS Open Data with CWoLa and TopicFlow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"hep-ph","authors_text":"Ayodele Ore, John Gargalionis, Matthew J. Dolan","submitted_at":"2023-12-06T11:28:54Z","abstract_excerpt":"We use the CMS Open Data to examine the performance of weakly-supervised learning for tagging quark and gluon jets at the LHC. We target $Z$+jet and dijet events as respective quark- and gluon-enriched mixtures and derive samples both from data taken in 2011 at 7 TeV, and from Monte Carlo. CWoLa and TopicFlow models are trained on real data and compared to fully-supervised classifiers trained on simulation. In order to obtain estimates for the discrimination power in real data, we consider three different estimates of the quark/gluon mixture fractions in the data. Compared to when the models a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03434","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2312.03434/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2312.03434","created_at":"2026-07-05T11:49:44.814174+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.03434v2","created_at":"2026-07-05T11:49:44.814174+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03434","created_at":"2026-07-05T11:49:44.814174+00:00"},{"alias_kind":"pith_short_12","alias_value":"A5W6JTTUOUBD","created_at":"2026-07-05T11:49:44.814174+00:00"},{"alias_kind":"pith_short_16","alias_value":"A5W6JTTUOUBDX6N7","created_at":"2026-07-05T11:49:44.814174+00:00"},{"alias_kind":"pith_short_8","alias_value":"A5W6JTTU","created_at":"2026-07-05T11:49:44.814174+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A5W6JTTUOUBDX6N7N3MQKTJZDL","json":"https://pith.science/pith/A5W6JTTUOUBDX6N7N3MQKTJZDL.json","graph_json":"https://pith.science/api/pith-number/A5W6JTTUOUBDX6N7N3MQKTJZDL/graph.json","events_json":"https://pith.science/api/pith-number/A5W6JTTUOUBDX6N7N3MQKTJZDL/events.json","paper":"https://pith.science/paper/A5W6JTTU"},"agent_actions":{"view_html":"https://pith.science/pith/A5W6JTTUOUBDX6N7N3MQKTJZDL","download_json":"https://pith.science/pith/A5W6JTTUOUBDX6N7N3MQKTJZDL.json","view_paper":"https://pith.science/paper/A5W6JTTU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.03434&json=true","fetch_graph":"https://pith.science/api/pith-number/A5W6JTTUOUBDX6N7N3MQKTJZDL/graph.json","fetch_events":"https://pith.science/api/pith-number/A5W6JTTUOUBDX6N7N3MQKTJZDL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A5W6JTTUOUBDX6N7N3MQKTJZDL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A5W6JTTUOUBDX6N7N3MQKTJZDL/action/storage_attestation","attest_author":"https://pith.science/pith/A5W6JTTUOUBDX6N7N3MQKTJZDL/action/author_attestation","sign_citation":"https://pith.science/pith/A5W6JTTUOUBDX6N7N3MQKTJZDL/action/citation_signature","submit_replication":"https://pith.science/pith/A5W6JTTUOUBDX6N7N3MQKTJZDL/action/replication_record"}},"created_at":"2026-07-05T11:49:44.814174+00:00","updated_at":"2026-07-05T11:49:44.814174+00:00"}