{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:DN4KOSV32RUAR2256254FOSVMI","short_pith_number":"pith:DN4KOSV3","canonical_record":{"source":{"id":"2010.04963","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-10T09:58:43Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"657b12e33b88ea28de1a2f0d731215a26b75ac20c6a33b5eaca160ba5a9dcfb3","abstract_canon_sha256":"94c4fcf384401d31a012b2ddf0bd2ff87f58e0f97697c77f37a4891895417bff"},"schema_version":"1.0"},"canonical_sha256":"1b78a74abbd46808eb5df6bbc2ba556206f70435ea42ffc2294b7c6956960cc4","source":{"kind":"arxiv","id":"2010.04963","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.04963","created_at":"2026-07-05T02:00:32Z"},{"alias_kind":"arxiv_version","alias_value":"2010.04963v2","created_at":"2026-07-05T02:00:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.04963","created_at":"2026-07-05T02:00:32Z"},{"alias_kind":"pith_short_12","alias_value":"DN4KOSV32RUA","created_at":"2026-07-05T02:00:32Z"},{"alias_kind":"pith_short_16","alias_value":"DN4KOSV32RUAR225","created_at":"2026-07-05T02:00:32Z"},{"alias_kind":"pith_short_8","alias_value":"DN4KOSV3","created_at":"2026-07-05T02:00:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:DN4KOSV32RUAR2256254FOSVMI","target":"record","payload":{"canonical_record":{"source":{"id":"2010.04963","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-10T09:58:43Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"657b12e33b88ea28de1a2f0d731215a26b75ac20c6a33b5eaca160ba5a9dcfb3","abstract_canon_sha256":"94c4fcf384401d31a012b2ddf0bd2ff87f58e0f97697c77f37a4891895417bff"},"schema_version":"1.0"},"canonical_sha256":"1b78a74abbd46808eb5df6bbc2ba556206f70435ea42ffc2294b7c6956960cc4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:00:32.461496Z","signature_b64":"01V8lYi6KHUIgdczSnxo5F0sol1V5aYleHQiemZZWh2RJ38nkQNOjqmGKpdvKWc9uRuEegnXFtVBIOAOwPGnCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b78a74abbd46808eb5df6bbc2ba556206f70435ea42ffc2294b7c6956960cc4","last_reissued_at":"2026-07-05T02:00:32.461142Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:00:32.461142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.04963","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:00:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i8dE2Mh6gXuEB0EXFd6466cHdHS6eeAtTcBCd6na7xMf9yt+cwE48tgqA7OaIiWmBvu95haZWOC1HfoNUM1DBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T18:33:48.565539Z"},"content_sha256":"7b1893b0906b90be5514bb65ae2a916dd9e9b32500f55e5944574d571f152222","schema_version":"1.0","event_id":"sha256:7b1893b0906b90be5514bb65ae2a916dd9e9b32500f55e5944574d571f152222"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:DN4KOSV32RUAR2256254FOSVMI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Block-term Tensor Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Di Chen, Guangxi Li, Haiqin Yang, Jinmian Ye, Shandian Zhe, Zenglin Xu","submitted_at":"2020-10-10T09:58:43Z","abstract_excerpt":"Deep neural networks (DNNs) have achieved outstanding performance in a wide range of applications, e.g., image classification, natural language processing, etc. Despite the good performance, the huge number of parameters in DNNs brings challenges to efficient training of DNNs and also their deployment in low-end devices with limited computing resources. In this paper, we explore the correlations in the weight matrices, and approximate the weight matrices with the low-rank block-term tensors. We name the new corresponding structure as block-term tensor layers (BT-layers), which can be easily ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.04963","kind":"arxiv","version":2},"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/2010.04963/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":"2026-07-05T02:00:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a2zLCYVMNk+h3QyoQ5kV9jeDKSLhtPAJPwDZmVIc6j/0zem3ifXacLPx6x2QkOAjBXgeCvKGQM/CufQKgkHECw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T18:33:48.566067Z"},"content_sha256":"a8c378859f65f98e7384d9933b36e24dfd66248a309ffcef18dc46aa774f32bc","schema_version":"1.0","event_id":"sha256:a8c378859f65f98e7384d9933b36e24dfd66248a309ffcef18dc46aa774f32bc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DN4KOSV32RUAR2256254FOSVMI/bundle.json","state_url":"https://pith.science/pith/DN4KOSV32RUAR2256254FOSVMI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DN4KOSV32RUAR2256254FOSVMI/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":"2026-08-14T18:33:48Z","links":{"resolver":"https://pith.science/pith/DN4KOSV32RUAR2256254FOSVMI","bundle":"https://pith.science/pith/DN4KOSV32RUAR2256254FOSVMI/bundle.json","state":"https://pith.science/pith/DN4KOSV32RUAR2256254FOSVMI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DN4KOSV32RUAR2256254FOSVMI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:DN4KOSV32RUAR2256254FOSVMI","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":"94c4fcf384401d31a012b2ddf0bd2ff87f58e0f97697c77f37a4891895417bff","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-10T09:58:43Z","title_canon_sha256":"657b12e33b88ea28de1a2f0d731215a26b75ac20c6a33b5eaca160ba5a9dcfb3"},"schema_version":"1.0","source":{"id":"2010.04963","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.04963","created_at":"2026-07-05T02:00:32Z"},{"alias_kind":"arxiv_version","alias_value":"2010.04963v2","created_at":"2026-07-05T02:00:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.04963","created_at":"2026-07-05T02:00:32Z"},{"alias_kind":"pith_short_12","alias_value":"DN4KOSV32RUA","created_at":"2026-07-05T02:00:32Z"},{"alias_kind":"pith_short_16","alias_value":"DN4KOSV32RUAR225","created_at":"2026-07-05T02:00:32Z"},{"alias_kind":"pith_short_8","alias_value":"DN4KOSV3","created_at":"2026-07-05T02:00:32Z"}],"graph_snapshots":[{"event_id":"sha256:a8c378859f65f98e7384d9933b36e24dfd66248a309ffcef18dc46aa774f32bc","target":"graph","created_at":"2026-07-05T02:00:32Z","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/2010.04963/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep neural networks (DNNs) have achieved outstanding performance in a wide range of applications, e.g., image classification, natural language processing, etc. Despite the good performance, the huge number of parameters in DNNs brings challenges to efficient training of DNNs and also their deployment in low-end devices with limited computing resources. In this paper, we explore the correlations in the weight matrices, and approximate the weight matrices with the low-rank block-term tensors. We name the new corresponding structure as block-term tensor layers (BT-layers), which can be easily ad","authors_text":"Di Chen, Guangxi Li, Haiqin Yang, Jinmian Ye, Shandian Zhe, Zenglin Xu","cross_cats":["cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-10T09:58:43Z","title":"Block-term Tensor Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.04963","kind":"arxiv","version":2},"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":"sha256:7b1893b0906b90be5514bb65ae2a916dd9e9b32500f55e5944574d571f152222","target":"record","created_at":"2026-07-05T02:00:32Z","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":"94c4fcf384401d31a012b2ddf0bd2ff87f58e0f97697c77f37a4891895417bff","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-10T09:58:43Z","title_canon_sha256":"657b12e33b88ea28de1a2f0d731215a26b75ac20c6a33b5eaca160ba5a9dcfb3"},"schema_version":"1.0","source":{"id":"2010.04963","kind":"arxiv","version":2}},"canonical_sha256":"1b78a74abbd46808eb5df6bbc2ba556206f70435ea42ffc2294b7c6956960cc4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b78a74abbd46808eb5df6bbc2ba556206f70435ea42ffc2294b7c6956960cc4","first_computed_at":"2026-07-05T02:00:32.461142Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:00:32.461142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"01V8lYi6KHUIgdczSnxo5F0sol1V5aYleHQiemZZWh2RJ38nkQNOjqmGKpdvKWc9uRuEegnXFtVBIOAOwPGnCA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:00:32.461496Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.04963","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7b1893b0906b90be5514bb65ae2a916dd9e9b32500f55e5944574d571f152222","sha256:a8c378859f65f98e7384d9933b36e24dfd66248a309ffcef18dc46aa774f32bc"],"state_sha256":"ac90bf7ee7ebffc39d54616249d57ebd048005fdb722cadf87b117069af123ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zCGJ/XVN69usFJnRHLFDJBZXvaR+EJSB67aedpIlnqi/Z1K0L4NJR5DcAmw+11AwCT9bYq+oGmOE+omuZaG6CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T18:33:48.574113Z","bundle_sha256":"23f3f9fc071dd035b137d04a78b491a87139738a08fe1f4bd0b9669bb29569db"}}