{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:5VX2VXBAF5XVFW7HTN4W5TZPW5","short_pith_number":"pith:5VX2VXBA","schema_version":"1.0","canonical_sha256":"ed6faadc202f6f52dbe79b796ecf2fb76b2f97af8a6bd083876fbcab5dfa9f0f","source":{"kind":"arxiv","id":"2111.12840","version":1},"attestation_state":"computed","paper":{"title":"Explaining machine-learned particle-flow reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","hep-ex","physics.ins-det"],"primary_cat":"physics.data-an","authors_text":"Daniel Diaz, Farouk Mokhtar, Javier Duarte, Jean-Roch Vlimant, Joosep Pata, Maurizio Pierini, Raghav Kansal","submitted_at":"2021-11-24T23:20:03Z","abstract_excerpt":"The particle-flow (PF) algorithm is used in general-purpose particle detectors to reconstruct a comprehensive particle-level view of the collision by combining information from different subdetectors. A graph neural network (GNN) model, known as the machine-learned particle-flow (MLPF) algorithm, has been developed to substitute the rule-based PF algorithm. However, understanding the model's decision making is not straightforward, especially given the complexity of the set-to-set prediction task, dynamic graph building, and message-passing steps. In this paper, we adapt the layerwise-relevance"},"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":"2111.12840","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.data-an","submitted_at":"2021-11-24T23:20:03Z","cross_cats_sorted":["cs.LG","hep-ex","physics.ins-det"],"title_canon_sha256":"65700cab3432bdd48a411ce0d82ec829527a8aad588771f71a5915761216eea0","abstract_canon_sha256":"c52ded513ef9e1300117caa8fde4c5152be270a7c559e4bbb0e9edcd538e58cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:34:59.091829Z","signature_b64":"v7QbjhW/Q5pQOAubt9PxHfD5cQ3cyKH6lgwOA5nR8kRL+VLoEO+4mzeTTMXZ4h7QOoxe0GSGAe2YoZa59WpjDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed6faadc202f6f52dbe79b796ecf2fb76b2f97af8a6bd083876fbcab5dfa9f0f","last_reissued_at":"2026-07-05T03:34:59.091407Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:34:59.091407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explaining machine-learned particle-flow reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","hep-ex","physics.ins-det"],"primary_cat":"physics.data-an","authors_text":"Daniel Diaz, Farouk Mokhtar, Javier Duarte, Jean-Roch Vlimant, Joosep Pata, Maurizio Pierini, Raghav Kansal","submitted_at":"2021-11-24T23:20:03Z","abstract_excerpt":"The particle-flow (PF) algorithm is used in general-purpose particle detectors to reconstruct a comprehensive particle-level view of the collision by combining information from different subdetectors. A graph neural network (GNN) model, known as the machine-learned particle-flow (MLPF) algorithm, has been developed to substitute the rule-based PF algorithm. However, understanding the model's decision making is not straightforward, especially given the complexity of the set-to-set prediction task, dynamic graph building, and message-passing steps. In this paper, we adapt the layerwise-relevance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.12840","kind":"arxiv","version":1},"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/2111.12840/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":"2111.12840","created_at":"2026-07-05T03:34:59.091466+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.12840v1","created_at":"2026-07-05T03:34:59.091466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.12840","created_at":"2026-07-05T03:34:59.091466+00:00"},{"alias_kind":"pith_short_12","alias_value":"5VX2VXBAF5XV","created_at":"2026-07-05T03:34:59.091466+00:00"},{"alias_kind":"pith_short_16","alias_value":"5VX2VXBAF5XVFW7H","created_at":"2026-07-05T03:34:59.091466+00:00"},{"alias_kind":"pith_short_8","alias_value":"5VX2VXBA","created_at":"2026-07-05T03:34:59.091466+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09881","citing_title":"Dissecting Jet-Tagger Through Mechanistic Interpretability","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5VX2VXBAF5XVFW7HTN4W5TZPW5","json":"https://pith.science/pith/5VX2VXBAF5XVFW7HTN4W5TZPW5.json","graph_json":"https://pith.science/api/pith-number/5VX2VXBAF5XVFW7HTN4W5TZPW5/graph.json","events_json":"https://pith.science/api/pith-number/5VX2VXBAF5XVFW7HTN4W5TZPW5/events.json","paper":"https://pith.science/paper/5VX2VXBA"},"agent_actions":{"view_html":"https://pith.science/pith/5VX2VXBAF5XVFW7HTN4W5TZPW5","download_json":"https://pith.science/pith/5VX2VXBAF5XVFW7HTN4W5TZPW5.json","view_paper":"https://pith.science/paper/5VX2VXBA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.12840&json=true","fetch_graph":"https://pith.science/api/pith-number/5VX2VXBAF5XVFW7HTN4W5TZPW5/graph.json","fetch_events":"https://pith.science/api/pith-number/5VX2VXBAF5XVFW7HTN4W5TZPW5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5VX2VXBAF5XVFW7HTN4W5TZPW5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5VX2VXBAF5XVFW7HTN4W5TZPW5/action/storage_attestation","attest_author":"https://pith.science/pith/5VX2VXBAF5XVFW7HTN4W5TZPW5/action/author_attestation","sign_citation":"https://pith.science/pith/5VX2VXBAF5XVFW7HTN4W5TZPW5/action/citation_signature","submit_replication":"https://pith.science/pith/5VX2VXBAF5XVFW7HTN4W5TZPW5/action/replication_record"}},"created_at":"2026-07-05T03:34:59.091466+00:00","updated_at":"2026-07-05T03:34:59.091466+00:00"}