{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BJA5CWKWU7BXSM6WM2CET3AZWQ","short_pith_number":"pith:BJA5CWKW","canonical_record":{"source":{"id":"2505.20132","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T15:32:28Z","cross_cats_sorted":["cs.AI","quant-ph"],"title_canon_sha256":"ee9d5e224ddc9c4fc917fc4f870bb3dd3ef71b4e45d8caa711ca7258e653f371","abstract_canon_sha256":"1ec7475c64746aa5eae11d0b878fc1868e4bf2be54e25a79081cf63df6cb5d34"},"schema_version":"1.0"},"canonical_sha256":"0a41d15956a7c37933d6668449ec19b438c7234188015cb705dda0c332a27e7d","source":{"kind":"arxiv","id":"2505.20132","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20132","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20132v1","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20132","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"pith_short_12","alias_value":"BJA5CWKWU7BX","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"pith_short_16","alias_value":"BJA5CWKWU7BXSM6W","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"pith_short_8","alias_value":"BJA5CWKW","created_at":"2026-07-05T11:09:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BJA5CWKWU7BXSM6WM2CET3AZWQ","target":"record","payload":{"canonical_record":{"source":{"id":"2505.20132","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T15:32:28Z","cross_cats_sorted":["cs.AI","quant-ph"],"title_canon_sha256":"ee9d5e224ddc9c4fc917fc4f870bb3dd3ef71b4e45d8caa711ca7258e653f371","abstract_canon_sha256":"1ec7475c64746aa5eae11d0b878fc1868e4bf2be54e25a79081cf63df6cb5d34"},"schema_version":"1.0"},"canonical_sha256":"0a41d15956a7c37933d6668449ec19b438c7234188015cb705dda0c332a27e7d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:53.026393Z","signature_b64":"PJyNYb1hANRBadwkuTqYK3i52PX4WjOrGbY+gWqcFK2iAlOsE+tI/vXFgwhVZQx5tgy+AnBZe1xtOBllnVqWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a41d15956a7c37933d6668449ec19b438c7234188015cb705dda0c332a27e7d","last_reissued_at":"2026-07-05T11:09:53.025853Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:53.025853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.20132","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":"2026-07-05T11:09:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ceMrpKyMXABcGufrPo+LOW+8cXRvEeIGucLcSmK0sWpC8mN/QDEXs90eV0ROjbgcRcv2nuHYs+tJ7DEvumz+Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:51:51.036841Z"},"content_sha256":"4ba87a345b26838060b1b71b448f3c810ac6f4c427c838cc5e1fa02790f71049","schema_version":"1.0","event_id":"sha256:4ba87a345b26838060b1b71b448f3c810ac6f4c427c838cc5e1fa02790f71049"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BJA5CWKWU7BXSM6WM2CET3AZWQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tensorization is a powerful but underexplored tool for compression and interpretability of neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","quant-ph"],"primary_cat":"cs.LG","authors_text":"Rom\\'an Or\\'us, Safa Hamreras, Sukhbinder Singh","submitted_at":"2025-05-26T15:32:28Z","abstract_excerpt":"Tensorizing a neural network involves reshaping some or all of its dense weight matrices into higher-order tensors and approximating them using low-rank tensor network decompositions. This technique has shown promise as a model compression strategy for large-scale neural networks. However, despite encouraging empirical results, tensorized neural networks (TNNs) remain underutilized in mainstream deep learning. In this position paper, we offer a perspective on both the potential and current limitations of TNNs. We argue that TNNs represent a powerful yet underexplored framework for deep learnin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20132","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/2505.20132/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":"2026-07-05T11:09:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A50zrDgY1AMRuyvEfR89OK6g3g1w4N9ciSFqeqdhJXYy3aLRWV9/IDPg3gUrqUYVDz/k1/ZGMggrPXwAn2tBAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:51:51.037399Z"},"content_sha256":"1342c0e601d13d5ac8403245efdc83943a0bff4dc914c7608a82f7d4803b9347","schema_version":"1.0","event_id":"sha256:1342c0e601d13d5ac8403245efdc83943a0bff4dc914c7608a82f7d4803b9347"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BJA5CWKWU7BXSM6WM2CET3AZWQ/bundle.json","state_url":"https://pith.science/pith/BJA5CWKWU7BXSM6WM2CET3AZWQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BJA5CWKWU7BXSM6WM2CET3AZWQ/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":"2026-08-09T04:51:51Z","links":{"resolver":"https://pith.science/pith/BJA5CWKWU7BXSM6WM2CET3AZWQ","bundle":"https://pith.science/pith/BJA5CWKWU7BXSM6WM2CET3AZWQ/bundle.json","state":"https://pith.science/pith/BJA5CWKWU7BXSM6WM2CET3AZWQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BJA5CWKWU7BXSM6WM2CET3AZWQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BJA5CWKWU7BXSM6WM2CET3AZWQ","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":"1ec7475c64746aa5eae11d0b878fc1868e4bf2be54e25a79081cf63df6cb5d34","cross_cats_sorted":["cs.AI","quant-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T15:32:28Z","title_canon_sha256":"ee9d5e224ddc9c4fc917fc4f870bb3dd3ef71b4e45d8caa711ca7258e653f371"},"schema_version":"1.0","source":{"id":"2505.20132","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20132","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20132v1","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20132","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"pith_short_12","alias_value":"BJA5CWKWU7BX","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"pith_short_16","alias_value":"BJA5CWKWU7BXSM6W","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"pith_short_8","alias_value":"BJA5CWKW","created_at":"2026-07-05T11:09:53Z"}],"graph_snapshots":[{"event_id":"sha256:1342c0e601d13d5ac8403245efdc83943a0bff4dc914c7608a82f7d4803b9347","target":"graph","created_at":"2026-07-05T11:09:53Z","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/2505.20132/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tensorizing a neural network involves reshaping some or all of its dense weight matrices into higher-order tensors and approximating them using low-rank tensor network decompositions. This technique has shown promise as a model compression strategy for large-scale neural networks. However, despite encouraging empirical results, tensorized neural networks (TNNs) remain underutilized in mainstream deep learning. In this position paper, we offer a perspective on both the potential and current limitations of TNNs. We argue that TNNs represent a powerful yet underexplored framework for deep learnin","authors_text":"Rom\\'an Or\\'us, Safa Hamreras, Sukhbinder Singh","cross_cats":["cs.AI","quant-ph"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T15:32:28Z","title":"Tensorization is a powerful but underexplored tool for compression and interpretability of neural networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20132","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":"sha256:4ba87a345b26838060b1b71b448f3c810ac6f4c427c838cc5e1fa02790f71049","target":"record","created_at":"2026-07-05T11:09:53Z","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":"1ec7475c64746aa5eae11d0b878fc1868e4bf2be54e25a79081cf63df6cb5d34","cross_cats_sorted":["cs.AI","quant-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T15:32:28Z","title_canon_sha256":"ee9d5e224ddc9c4fc917fc4f870bb3dd3ef71b4e45d8caa711ca7258e653f371"},"schema_version":"1.0","source":{"id":"2505.20132","kind":"arxiv","version":1}},"canonical_sha256":"0a41d15956a7c37933d6668449ec19b438c7234188015cb705dda0c332a27e7d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a41d15956a7c37933d6668449ec19b438c7234188015cb705dda0c332a27e7d","first_computed_at":"2026-07-05T11:09:53.025853Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:53.025853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PJyNYb1hANRBadwkuTqYK3i52PX4WjOrGbY+gWqcFK2iAlOsE+tI/vXFgwhVZQx5tgy+AnBZe1xtOBllnVqWDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:53.026393Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20132","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ba87a345b26838060b1b71b448f3c810ac6f4c427c838cc5e1fa02790f71049","sha256:1342c0e601d13d5ac8403245efdc83943a0bff4dc914c7608a82f7d4803b9347"],"state_sha256":"bdc7200f4a92efd2001be448aaf1b65a1fd0dae28a99afdda11e95ec15346611"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v8dBoupzwuQLyrXAqjBX71BfEWcibfNPsYVgQ3Vp5gFxC52lZ9zMX/zQka/0v4bzVqu4XV62HMMKI4HHqgMdDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:51:51.041356Z","bundle_sha256":"0ce08abcc113fb60aee9be064c25b3d3571e4bf37f37b58a7cbf1aa5d23f0c6b"}}