{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6MTMXO4YWNDK5NBWHP3ADWOZMM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"76d076eb490d4521857cf72385dbded1e622d1ac258959b3f427fc0b0165fe4b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T13:53:21Z","title_canon_sha256":"f42a4726ccd35d5a41236fab1f7e364bfd92e6a6482b785cacdf2a92133627fc"},"schema_version":"1.0","source":{"id":"2505.17909","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17909","created_at":"2026-07-05T11:08:33Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17909v1","created_at":"2026-07-05T11:08:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17909","created_at":"2026-07-05T11:08:33Z"},{"alias_kind":"pith_short_12","alias_value":"6MTMXO4YWNDK","created_at":"2026-07-05T11:08:33Z"},{"alias_kind":"pith_short_16","alias_value":"6MTMXO4YWNDK5NBW","created_at":"2026-07-05T11:08:33Z"},{"alias_kind":"pith_short_8","alias_value":"6MTMXO4Y","created_at":"2026-07-05T11:08:33Z"}],"graph_snapshots":[{"event_id":"sha256:2543a1311d7a5abf46badf3d5a44645d95bc85d8ffef4f1cd57485c4f9446960","target":"graph","created_at":"2026-07-05T11:08:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.17909/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model ensembles have long been a cornerstone for improving generalization and robustness in deep learning. However, their effectiveness often comes at the cost of substantial computational overhead. To address this issue, state-of-the-art methods aim to replicate ensemble-class performance without requiring multiple independently trained networks. Unfortunately, these algorithms often still demand considerable compute at inference. In response to these limitations, we introduce $\\textbf{NeuroTrails}$, a sparse multi-head architecture with dynamically evolving topology. This unexplored model-ag","authors_text":"Boqian Wu, Bram Grooten, Chenxiang Zhang, Decebal Constantin Mocanu, Elena Mocanu, Farid Hasanov, Ghada Sokar, Lu Yin, Mykola Pechenizkiy, Qiao Xiao, Shiwei Liu, Zahra Atashgahi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T13:53:21Z","title":"NeuroTrails: Training with Dynamic Sparse Heads as the Key to Effective Ensembling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17909","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4e289746da77b24b2ca8adfddfa264943ad9dbeeadeea2ea588599962e4d5035","target":"record","created_at":"2026-07-05T11:08:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"76d076eb490d4521857cf72385dbded1e622d1ac258959b3f427fc0b0165fe4b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T13:53:21Z","title_canon_sha256":"f42a4726ccd35d5a41236fab1f7e364bfd92e6a6482b785cacdf2a92133627fc"},"schema_version":"1.0","source":{"id":"2505.17909","kind":"arxiv","version":1}},"canonical_sha256":"f326cbbb98b346aeb4363bf601d9d9631e61a013590b9a1be1db1d8f5d1beb62","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f326cbbb98b346aeb4363bf601d9d9631e61a013590b9a1be1db1d8f5d1beb62","first_computed_at":"2026-07-05T11:08:33.666962Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:33.666962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dIQ39ji94nPa4fttJtbkdd0YNwg8T7NpTom19twQsWQcvUq2Pq7JK1rs2EnJ8Y8f04odPDRcW9XLxegBZQtgDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:33.667533Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17909","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e289746da77b24b2ca8adfddfa264943ad9dbeeadeea2ea588599962e4d5035","sha256:2543a1311d7a5abf46badf3d5a44645d95bc85d8ffef4f1cd57485c4f9446960"],"state_sha256":"0a9b2fd8f9eadc6ac595b8bf77b3987b843fc314f066181dc7da3b7edcb69cf7"}