{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:J3XD7Z4KFJ3SUE5PDDLZYXEQOG","short_pith_number":"pith:J3XD7Z4K","schema_version":"1.0","canonical_sha256":"4eee3fe78a2a772a13af18d79c5c9071abedac89ca5f1f6002c129e0e87006d1","source":{"kind":"arxiv","id":"2605.19122","version":1},"attestation_state":"computed","paper":{"title":"Dual-Channel Tensor Neural Networks: Finite-Sample Theory and Conformal Structure Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Elynn Chen, Jian Pei, Jiayu Li, Zheshi Zheng","submitted_at":"2026-05-18T21:16:37Z","abstract_excerpt":"Tensor-valued data arise naturally in neuroimaging, genomics, climate science, and spatiotemporal networks, where multilinear dependencies across modes carry information that is destroyed under vectorization. Existing approaches either impose a single low-rank structure, which can miss localized signal, or treat the tensor as a long vector, which discards its multiway geometry. We propose a *Dual-Channel Tensor Neural Network* (DC-TNN) that decomposes each tensor input into a low-rank core and a sparse refinement, and processes the two components through coupled neural channels. The framework "},"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":"2605.19122","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-18T21:16:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d4659873aace4b43f41dbd114ba1eb94b2cdc4853856e66270d163e9d13b1e22","abstract_canon_sha256":"f81ad0da186e97ff12a82cf44da8b563e38c7d46bd41f9b28b787105d1b58964"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:05:28.246938Z","signature_b64":"2H1VO/x+tn6UFo41N9AeYdCp+roOxD2xUNB2tzeSLRWJDuJVUecu7mbL9aTQmNuEC39omNGlebV2olROTrhiAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4eee3fe78a2a772a13af18d79c5c9071abedac89ca5f1f6002c129e0e87006d1","last_reissued_at":"2026-05-20T01:05:28.246361Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:05:28.246361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual-Channel Tensor Neural Networks: Finite-Sample Theory and Conformal Structure Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Elynn Chen, Jian Pei, Jiayu Li, Zheshi Zheng","submitted_at":"2026-05-18T21:16:37Z","abstract_excerpt":"Tensor-valued data arise naturally in neuroimaging, genomics, climate science, and spatiotemporal networks, where multilinear dependencies across modes carry information that is destroyed under vectorization. Existing approaches either impose a single low-rank structure, which can miss localized signal, or treat the tensor as a long vector, which discards its multiway geometry. We propose a *Dual-Channel Tensor Neural Network* (DC-TNN) that decomposes each tensor input into a low-rank core and a sparse refinement, and processes the two components through coupled neural channels. The framework "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19122","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/2605.19122/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":"2605.19122","created_at":"2026-05-20T01:05:28.246463+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.19122v1","created_at":"2026-05-20T01:05:28.246463+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19122","created_at":"2026-05-20T01:05:28.246463+00:00"},{"alias_kind":"pith_short_12","alias_value":"J3XD7Z4KFJ3S","created_at":"2026-05-20T01:05:28.246463+00:00"},{"alias_kind":"pith_short_16","alias_value":"J3XD7Z4KFJ3SUE5P","created_at":"2026-05-20T01:05:28.246463+00:00"},{"alias_kind":"pith_short_8","alias_value":"J3XD7Z4K","created_at":"2026-05-20T01:05:28.246463+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/J3XD7Z4KFJ3SUE5PDDLZYXEQOG","json":"https://pith.science/pith/J3XD7Z4KFJ3SUE5PDDLZYXEQOG.json","graph_json":"https://pith.science/api/pith-number/J3XD7Z4KFJ3SUE5PDDLZYXEQOG/graph.json","events_json":"https://pith.science/api/pith-number/J3XD7Z4KFJ3SUE5PDDLZYXEQOG/events.json","paper":"https://pith.science/paper/J3XD7Z4K"},"agent_actions":{"view_html":"https://pith.science/pith/J3XD7Z4KFJ3SUE5PDDLZYXEQOG","download_json":"https://pith.science/pith/J3XD7Z4KFJ3SUE5PDDLZYXEQOG.json","view_paper":"https://pith.science/paper/J3XD7Z4K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.19122&json=true","fetch_graph":"https://pith.science/api/pith-number/J3XD7Z4KFJ3SUE5PDDLZYXEQOG/graph.json","fetch_events":"https://pith.science/api/pith-number/J3XD7Z4KFJ3SUE5PDDLZYXEQOG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J3XD7Z4KFJ3SUE5PDDLZYXEQOG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J3XD7Z4KFJ3SUE5PDDLZYXEQOG/action/storage_attestation","attest_author":"https://pith.science/pith/J3XD7Z4KFJ3SUE5PDDLZYXEQOG/action/author_attestation","sign_citation":"https://pith.science/pith/J3XD7Z4KFJ3SUE5PDDLZYXEQOG/action/citation_signature","submit_replication":"https://pith.science/pith/J3XD7Z4KFJ3SUE5PDDLZYXEQOG/action/replication_record"}},"created_at":"2026-05-20T01:05:28.246463+00:00","updated_at":"2026-05-20T01:05:28.246463+00:00"}