{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JFHUPYUXWREBYCE5ZQEJN7YKRP","short_pith_number":"pith:JFHUPYUX","schema_version":"1.0","canonical_sha256":"494f47e297b4481c089dcc0896ff0a8bf329efcc1385012a52ad50999de1a43c","source":{"kind":"arxiv","id":"2412.00129","version":2},"attestation_state":"computed","paper":{"title":"Scaling Particle Collision Data Analysis","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["hep-ex","physics.data-an"],"primary_cat":"cs.LG","authors_text":"Bruce Liu, Chen Zhou, Dahao Liang, Hengkui Wu, Liujiang Liu, Manqi Ruan, Panpan Chi, Qihao Wang, Shuyang Hu, Xinglong Jia, Yingsi Xin, Yongfeng Zhu, Yuexin Wang","submitted_at":"2024-11-28T13:32:56Z","abstract_excerpt":"For decades, researchers have developed task-specific models to address scientific challenges across diverse disciplines. Recently, large language models (LLMs) have shown enormous capabilities in handling general tasks; however, these models encounter difficulties in addressing real-world scientific problems, particularly in domains involving large-scale numerical data analysis, such as experimental high energy physics. This limitation is primarily due to BPE tokenization's inefficacy with numerical data. In this paper, we propose a task-agnostic architecture, BBT-Neutron, which employs a bin"},"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":"2412.00129","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-28T13:32:56Z","cross_cats_sorted":["hep-ex","physics.data-an"],"title_canon_sha256":"a54aa1d516225d4ef83483ccbf24878656bf9d6d4da492bb87e6d7eae6423a37","abstract_canon_sha256":"c50c86def79168f5a6246e435e19dd97562e0f0282e52947044b357bd294479d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:55.318375Z","signature_b64":"pq3KDqUDAlKSZhRLw1AMS9kBjUnAT2tuiTQLYq0Z5a+0MntdbwC33+lI+sM42EEVLur3ZkoqY20UXIQo+OHpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"494f47e297b4481c089dcc0896ff0a8bf329efcc1385012a52ad50999de1a43c","last_reissued_at":"2026-07-05T09:46:55.317859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:55.317859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Particle Collision Data Analysis","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["hep-ex","physics.data-an"],"primary_cat":"cs.LG","authors_text":"Bruce Liu, Chen Zhou, Dahao Liang, Hengkui Wu, Liujiang Liu, Manqi Ruan, Panpan Chi, Qihao Wang, Shuyang Hu, Xinglong Jia, Yingsi Xin, Yongfeng Zhu, Yuexin Wang","submitted_at":"2024-11-28T13:32:56Z","abstract_excerpt":"For decades, researchers have developed task-specific models to address scientific challenges across diverse disciplines. Recently, large language models (LLMs) have shown enormous capabilities in handling general tasks; however, these models encounter difficulties in addressing real-world scientific problems, particularly in domains involving large-scale numerical data analysis, such as experimental high energy physics. This limitation is primarily due to BPE tokenization's inefficacy with numerical data. In this paper, we propose a task-agnostic architecture, BBT-Neutron, which employs a bin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00129","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/2412.00129/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":"2412.00129","created_at":"2026-07-05T09:46:55.317926+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00129v2","created_at":"2026-07-05T09:46:55.317926+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00129","created_at":"2026-07-05T09:46:55.317926+00:00"},{"alias_kind":"pith_short_12","alias_value":"JFHUPYUXWREB","created_at":"2026-07-05T09:46:55.317926+00:00"},{"alias_kind":"pith_short_16","alias_value":"JFHUPYUXWREBYCE5","created_at":"2026-07-05T09:46:55.317926+00:00"},{"alias_kind":"pith_short_8","alias_value":"JFHUPYUX","created_at":"2026-07-05T09:46:55.317926+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.18169","citing_title":"PiERN: Token-Level Routing for Integrating High-Precision Computation and Reasoning","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JFHUPYUXWREBYCE5ZQEJN7YKRP","json":"https://pith.science/pith/JFHUPYUXWREBYCE5ZQEJN7YKRP.json","graph_json":"https://pith.science/api/pith-number/JFHUPYUXWREBYCE5ZQEJN7YKRP/graph.json","events_json":"https://pith.science/api/pith-number/JFHUPYUXWREBYCE5ZQEJN7YKRP/events.json","paper":"https://pith.science/paper/JFHUPYUX"},"agent_actions":{"view_html":"https://pith.science/pith/JFHUPYUXWREBYCE5ZQEJN7YKRP","download_json":"https://pith.science/pith/JFHUPYUXWREBYCE5ZQEJN7YKRP.json","view_paper":"https://pith.science/paper/JFHUPYUX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00129&json=true","fetch_graph":"https://pith.science/api/pith-number/JFHUPYUXWREBYCE5ZQEJN7YKRP/graph.json","fetch_events":"https://pith.science/api/pith-number/JFHUPYUXWREBYCE5ZQEJN7YKRP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JFHUPYUXWREBYCE5ZQEJN7YKRP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JFHUPYUXWREBYCE5ZQEJN7YKRP/action/storage_attestation","attest_author":"https://pith.science/pith/JFHUPYUXWREBYCE5ZQEJN7YKRP/action/author_attestation","sign_citation":"https://pith.science/pith/JFHUPYUXWREBYCE5ZQEJN7YKRP/action/citation_signature","submit_replication":"https://pith.science/pith/JFHUPYUXWREBYCE5ZQEJN7YKRP/action/replication_record"}},"created_at":"2026-07-05T09:46:55.317926+00:00","updated_at":"2026-07-05T09:46:55.317926+00:00"}