{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:743UENTK3CEVCE4HCFYEYXYOXY","short_pith_number":"pith:743UENTK","canonical_record":{"source":{"id":"2203.02617","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-05T00:17:04Z","cross_cats_sorted":["cs.CV","math.OC"],"title_canon_sha256":"c86f142b7b8d387bbfe1f2d8272289bd89c48b1844103a858b382165089fbc8b","abstract_canon_sha256":"6c1b03b1b24a5a7c23bdada96f19b8385fb7a0244f104d1a340785d32573ddc6"},"schema_version":"1.0"},"canonical_sha256":"ff3742366ad88951138711704c5f0ebe2e0074c05609eb846db4c968560a9151","source":{"kind":"arxiv","id":"2203.02617","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.02617","created_at":"2026-07-05T04:02:25Z"},{"alias_kind":"arxiv_version","alias_value":"2203.02617v1","created_at":"2026-07-05T04:02:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.02617","created_at":"2026-07-05T04:02:25Z"},{"alias_kind":"pith_short_12","alias_value":"743UENTK3CEV","created_at":"2026-07-05T04:02:25Z"},{"alias_kind":"pith_short_16","alias_value":"743UENTK3CEVCE4H","created_at":"2026-07-05T04:02:25Z"},{"alias_kind":"pith_short_8","alias_value":"743UENTK","created_at":"2026-07-05T04:02:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:743UENTK3CEVCE4HCFYEYXYOXY","target":"record","payload":{"canonical_record":{"source":{"id":"2203.02617","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-05T00:17:04Z","cross_cats_sorted":["cs.CV","math.OC"],"title_canon_sha256":"c86f142b7b8d387bbfe1f2d8272289bd89c48b1844103a858b382165089fbc8b","abstract_canon_sha256":"6c1b03b1b24a5a7c23bdada96f19b8385fb7a0244f104d1a340785d32573ddc6"},"schema_version":"1.0"},"canonical_sha256":"ff3742366ad88951138711704c5f0ebe2e0074c05609eb846db4c968560a9151","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:02:25.134478Z","signature_b64":"TqnTCZa/k+D9wj+MnPw9O7bf8aLQmbLevQFFet+o69uaqH26xZAELkT6RfSiR4b66tImrjapsRR5IS3SpoyiCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff3742366ad88951138711704c5f0ebe2e0074c05609eb846db4c968560a9151","last_reissued_at":"2026-07-05T04:02:25.133982Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:02:25.133982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.02617","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:02:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IO7D3SYvI3jB97g22WcIpEgSi7sJvi9eUQSO6blDTqffXvYOBMWmR/BxQMkRcMD+xts39IoF2vcL2fLPjJq8CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T02:15:17.731013Z"},"content_sha256":"883d7e98e3d41169b7df20cb485ab9cb588a87c94faba68844b467f1fdd80c62","schema_version":"1.0","event_id":"sha256:883d7e98e3d41169b7df20cb485ab9cb588a87c94faba68844b467f1fdd80c62"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:743UENTK3CEVCE4HCFYEYXYOXY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How to Train Unstable Looped Tensor Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","math.OC"],"primary_cat":"cs.LG","authors_text":"Andrzej Cichocki, Anh-Huy Phan, Dmitry Ermilov, Igor Vorona, Konstantin Sobolev, Nikolay Kozyrskiy, Petr Tichavsky","submitted_at":"2022-03-05T00:17:04Z","abstract_excerpt":"A rising problem in the compression of Deep Neural Networks is how to reduce the number of parameters in convolutional kernels and the complexity of these layers by low-rank tensor approximation. Canonical polyadic tensor decomposition (CPD) and Tucker tensor decomposition (TKD) are two solutions to this problem and provide promising results. However, CPD often fails due to degeneracy, making the networks unstable and hard to fine-tune. TKD does not provide much compression if the core tensor is big. This motivates using a hybrid model of CPD and TKD, a decomposition with multiple Tucker model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.02617","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/2203.02617/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:02:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gGPg5FeNp/s9Ohhscwwm25gMP9OYBJrMy8xNdMPm5TYAeOlpSfJpU35TMoDewQCJv9hogWrSs3QooEhShiSiDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T02:15:17.731396Z"},"content_sha256":"ed7e57cca1e4c4a5786e9aad1620c20b8dc8787a1eabdc42952e9b717f1e518f","schema_version":"1.0","event_id":"sha256:ed7e57cca1e4c4a5786e9aad1620c20b8dc8787a1eabdc42952e9b717f1e518f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/743UENTK3CEVCE4HCFYEYXYOXY/bundle.json","state_url":"https://pith.science/pith/743UENTK3CEVCE4HCFYEYXYOXY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/743UENTK3CEVCE4HCFYEYXYOXY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-17T02:15:17Z","links":{"resolver":"https://pith.science/pith/743UENTK3CEVCE4HCFYEYXYOXY","bundle":"https://pith.science/pith/743UENTK3CEVCE4HCFYEYXYOXY/bundle.json","state":"https://pith.science/pith/743UENTK3CEVCE4HCFYEYXYOXY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/743UENTK3CEVCE4HCFYEYXYOXY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:743UENTK3CEVCE4HCFYEYXYOXY","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":"6c1b03b1b24a5a7c23bdada96f19b8385fb7a0244f104d1a340785d32573ddc6","cross_cats_sorted":["cs.CV","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-05T00:17:04Z","title_canon_sha256":"c86f142b7b8d387bbfe1f2d8272289bd89c48b1844103a858b382165089fbc8b"},"schema_version":"1.0","source":{"id":"2203.02617","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.02617","created_at":"2026-07-05T04:02:25Z"},{"alias_kind":"arxiv_version","alias_value":"2203.02617v1","created_at":"2026-07-05T04:02:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.02617","created_at":"2026-07-05T04:02:25Z"},{"alias_kind":"pith_short_12","alias_value":"743UENTK3CEV","created_at":"2026-07-05T04:02:25Z"},{"alias_kind":"pith_short_16","alias_value":"743UENTK3CEVCE4H","created_at":"2026-07-05T04:02:25Z"},{"alias_kind":"pith_short_8","alias_value":"743UENTK","created_at":"2026-07-05T04:02:25Z"}],"graph_snapshots":[{"event_id":"sha256:ed7e57cca1e4c4a5786e9aad1620c20b8dc8787a1eabdc42952e9b717f1e518f","target":"graph","created_at":"2026-07-05T04:02:25Z","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/2203.02617/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A rising problem in the compression of Deep Neural Networks is how to reduce the number of parameters in convolutional kernels and the complexity of these layers by low-rank tensor approximation. Canonical polyadic tensor decomposition (CPD) and Tucker tensor decomposition (TKD) are two solutions to this problem and provide promising results. However, CPD often fails due to degeneracy, making the networks unstable and hard to fine-tune. TKD does not provide much compression if the core tensor is big. This motivates using a hybrid model of CPD and TKD, a decomposition with multiple Tucker model","authors_text":"Andrzej Cichocki, Anh-Huy Phan, Dmitry Ermilov, Igor Vorona, Konstantin Sobolev, Nikolay Kozyrskiy, Petr Tichavsky","cross_cats":["cs.CV","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-05T00:17:04Z","title":"How to Train Unstable Looped Tensor Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.02617","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":"sha256:883d7e98e3d41169b7df20cb485ab9cb588a87c94faba68844b467f1fdd80c62","target":"record","created_at":"2026-07-05T04:02:25Z","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":"6c1b03b1b24a5a7c23bdada96f19b8385fb7a0244f104d1a340785d32573ddc6","cross_cats_sorted":["cs.CV","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-05T00:17:04Z","title_canon_sha256":"c86f142b7b8d387bbfe1f2d8272289bd89c48b1844103a858b382165089fbc8b"},"schema_version":"1.0","source":{"id":"2203.02617","kind":"arxiv","version":1}},"canonical_sha256":"ff3742366ad88951138711704c5f0ebe2e0074c05609eb846db4c968560a9151","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff3742366ad88951138711704c5f0ebe2e0074c05609eb846db4c968560a9151","first_computed_at":"2026-07-05T04:02:25.133982Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:02:25.133982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TqnTCZa/k+D9wj+MnPw9O7bf8aLQmbLevQFFet+o69uaqH26xZAELkT6RfSiR4b66tImrjapsRR5IS3SpoyiCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:02:25.134478Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.02617","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:883d7e98e3d41169b7df20cb485ab9cb588a87c94faba68844b467f1fdd80c62","sha256:ed7e57cca1e4c4a5786e9aad1620c20b8dc8787a1eabdc42952e9b717f1e518f"],"state_sha256":"7064611a7dfbbec86a4af3e051f995e4d16116909339ff104dec95dde9062f1f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kx/yTe97nZ1HkwbXBEvv+PVKVii6NQsZ5GfPc3bloqNDnAU+rRBsDg1yKQ2wdc6VecRxDEn2XOeb8bqN1voYBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T02:15:17.733820Z","bundle_sha256":"43c66e8f6a4af06338f4d45cb553bbaef3254a4dcc7aa3088e70c71ed2a4d1b0"}}