{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OHPRM7LHU4LXUHSTYZJSLOAIJB","short_pith_number":"pith:OHPRM7LH","schema_version":"1.0","canonical_sha256":"71df167d67a7177a1e53c65325b80848400adc3ee863c17b7b0035ee66081187","source":{"kind":"arxiv","id":"2606.00130","version":1},"attestation_state":"computed","paper":{"title":"Automatically Differentiable Nonlinear Tensor Networks (ADNTNs) for Exponential Compression of Deep Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andrzej Cichocki, Michal Wietczak","submitted_at":"2026-05-28T19:43:10Z","abstract_excerpt":"We study Automatically Differentiable Nonlinear Tensor Networks (ADNTNs), a family of structured weight generators whose compact core tensors are trained end-to-end by reverse-mode automatic differentiation (AD). The approach can be viewed as a natural extension of low-rank adaptation and tensor factorisation: instead of using one low-rank matrix update, an ADNTN builds a large weight tensor through a hierarchy of small cores, nonlinear activations, and optional lateral mixing tensors. The paper focuses on three architectures: Tree Tensor Networks (TTNs), augmented TTNs (aTTNs) with boundary d"},"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":"2606.00130","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T19:43:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3db0a1403a89e81f859034af8c9e4e6c51516169300b5657ed27e54c1af69c88","abstract_canon_sha256":"04f20d4b5adccb6df8ecf4e811cbe362e797ae325a9de7cd32e97df7f803d2e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:19.171832Z","signature_b64":"q09VJa15gjCc4V0pHPDUoVz38oH/i2Q2j9oqcMl5wtK8AlC0OdchfL6H4rzBoqMxvqREDSsPGVFn0W4KSo+TAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71df167d67a7177a1e53c65325b80848400adc3ee863c17b7b0035ee66081187","last_reissued_at":"2026-06-02T01:03:19.171434Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:19.171434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatically Differentiable Nonlinear Tensor Networks (ADNTNs) for Exponential Compression of Deep Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andrzej Cichocki, Michal Wietczak","submitted_at":"2026-05-28T19:43:10Z","abstract_excerpt":"We study Automatically Differentiable Nonlinear Tensor Networks (ADNTNs), a family of structured weight generators whose compact core tensors are trained end-to-end by reverse-mode automatic differentiation (AD). The approach can be viewed as a natural extension of low-rank adaptation and tensor factorisation: instead of using one low-rank matrix update, an ADNTN builds a large weight tensor through a hierarchy of small cores, nonlinear activations, and optional lateral mixing tensors. The paper focuses on three architectures: Tree Tensor Networks (TTNs), augmented TTNs (aTTNs) with boundary d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00130","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/2606.00130/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":"2606.00130","created_at":"2026-06-02T01:03:19.171497+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00130v1","created_at":"2026-06-02T01:03:19.171497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00130","created_at":"2026-06-02T01:03:19.171497+00:00"},{"alias_kind":"pith_short_12","alias_value":"OHPRM7LHU4LX","created_at":"2026-06-02T01:03:19.171497+00:00"},{"alias_kind":"pith_short_16","alias_value":"OHPRM7LHU4LXUHST","created_at":"2026-06-02T01:03:19.171497+00:00"},{"alias_kind":"pith_short_8","alias_value":"OHPRM7LH","created_at":"2026-06-02T01:03:19.171497+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/OHPRM7LHU4LXUHSTYZJSLOAIJB","json":"https://pith.science/pith/OHPRM7LHU4LXUHSTYZJSLOAIJB.json","graph_json":"https://pith.science/api/pith-number/OHPRM7LHU4LXUHSTYZJSLOAIJB/graph.json","events_json":"https://pith.science/api/pith-number/OHPRM7LHU4LXUHSTYZJSLOAIJB/events.json","paper":"https://pith.science/paper/OHPRM7LH"},"agent_actions":{"view_html":"https://pith.science/pith/OHPRM7LHU4LXUHSTYZJSLOAIJB","download_json":"https://pith.science/pith/OHPRM7LHU4LXUHSTYZJSLOAIJB.json","view_paper":"https://pith.science/paper/OHPRM7LH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00130&json=true","fetch_graph":"https://pith.science/api/pith-number/OHPRM7LHU4LXUHSTYZJSLOAIJB/graph.json","fetch_events":"https://pith.science/api/pith-number/OHPRM7LHU4LXUHSTYZJSLOAIJB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OHPRM7LHU4LXUHSTYZJSLOAIJB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OHPRM7LHU4LXUHSTYZJSLOAIJB/action/storage_attestation","attest_author":"https://pith.science/pith/OHPRM7LHU4LXUHSTYZJSLOAIJB/action/author_attestation","sign_citation":"https://pith.science/pith/OHPRM7LHU4LXUHSTYZJSLOAIJB/action/citation_signature","submit_replication":"https://pith.science/pith/OHPRM7LHU4LXUHSTYZJSLOAIJB/action/replication_record"}},"created_at":"2026-06-02T01:03:19.171497+00:00","updated_at":"2026-06-02T01:03:19.171497+00:00"}