{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ISAW6Q7BXLZUH2A4BXQZGE74RH","short_pith_number":"pith:ISAW6Q7B","canonical_record":{"source":{"id":"1905.10478","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T23:18:17Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c9fbaf97757452bb0c19fe520271b49bf859305c1178fa5cbe7149221a2b0a89","abstract_canon_sha256":"2694b9d0b536264cd54e64dafb28c9a7de7c499fe58733076f6732ade3fc68b2"},"schema_version":"1.0"},"canonical_sha256":"44816f43e1baf343e81c0de19313fc89efd2d379af1038481be989adf3ded6df","source":{"kind":"arxiv","id":"1905.10478","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10478","created_at":"2026-05-17T23:45:08Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10478v1","created_at":"2026-05-17T23:45:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10478","created_at":"2026-05-17T23:45:08Z"},{"alias_kind":"pith_short_12","alias_value":"ISAW6Q7BXLZU","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"ISAW6Q7BXLZUH2A4","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"ISAW6Q7B","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ISAW6Q7BXLZUH2A4BXQZGE74RH","target":"record","payload":{"canonical_record":{"source":{"id":"1905.10478","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T23:18:17Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c9fbaf97757452bb0c19fe520271b49bf859305c1178fa5cbe7149221a2b0a89","abstract_canon_sha256":"2694b9d0b536264cd54e64dafb28c9a7de7c499fe58733076f6732ade3fc68b2"},"schema_version":"1.0"},"canonical_sha256":"44816f43e1baf343e81c0de19313fc89efd2d379af1038481be989adf3ded6df","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:08.410353Z","signature_b64":"UYF5COmfXjiGwt/3VR5iWLDQv00uFRn2/fv5392wQP9iwJ4iCMsq07knXfClpy3txDp22YAo51UEoV/oj43dBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44816f43e1baf343e81c0de19313fc89efd2d379af1038481be989adf3ded6df","last_reissued_at":"2026-05-17T23:45:08.409685Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:08.409685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.10478","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":"2026-05-17T23:45:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CDq5NpZ9WmXO16atNr72YWAMLiJ+MAYq20jAHWbmPMG0/+qp7pgwdkVztSXqYaqV515tR2fEWaq5HWSVGxZeAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:22:40.688401Z"},"content_sha256":"8796fa100a4c28273eddc1b7be8f491a315693d46d3600cec5cd84b4055a1924","schema_version":"1.0","event_id":"sha256:8796fa100a4c28273eddc1b7be8f491a315693d46d3600cec5cd84b4055a1924"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ISAW6Q7BXLZUH2A4BXQZGE74RH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bayesian Tensorized Neural Networks with Automatic Rank Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cole Hawkins, Zheng Zhang","submitted_at":"2019-05-24T23:18:17Z","abstract_excerpt":"Tensor decomposition is an effective approach to compress over-parameterized neural networks and to enable their deployment on resource-constrained hardware platforms. However, directly applying tensor compression in the training process is a challenging task due to the difficulty of choosing a proper tensor rank. In order to achieve this goal, this paper proposes a Bayesian tensorized neural network. Our Bayesian method performs automatic model compression via an adaptive tensor rank determination. We also present approaches for posterior density calculation and maximum a posteriori (MAP) est"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10478","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":""},"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":"2026-05-17T23:45:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DRZ4eUVM7mJkKRCQEHmlLnywQ1j6Z7l8LWjactxxnyjpz55olSyMxpHlJUoMGTvaWRj7iFnB/Gg/KcuNWkoFCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:22:40.689060Z"},"content_sha256":"8982c0e6431a0273e6f1657f70af7e94824200ba45e7ff6ff0dbd1bdcd47ed0a","schema_version":"1.0","event_id":"sha256:8982c0e6431a0273e6f1657f70af7e94824200ba45e7ff6ff0dbd1bdcd47ed0a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ISAW6Q7BXLZUH2A4BXQZGE74RH/bundle.json","state_url":"https://pith.science/pith/ISAW6Q7BXLZUH2A4BXQZGE74RH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ISAW6Q7BXLZUH2A4BXQZGE74RH/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":"2026-05-27T14:22:40Z","links":{"resolver":"https://pith.science/pith/ISAW6Q7BXLZUH2A4BXQZGE74RH","bundle":"https://pith.science/pith/ISAW6Q7BXLZUH2A4BXQZGE74RH/bundle.json","state":"https://pith.science/pith/ISAW6Q7BXLZUH2A4BXQZGE74RH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ISAW6Q7BXLZUH2A4BXQZGE74RH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ISAW6Q7BXLZUH2A4BXQZGE74RH","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":"2694b9d0b536264cd54e64dafb28c9a7de7c499fe58733076f6732ade3fc68b2","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T23:18:17Z","title_canon_sha256":"c9fbaf97757452bb0c19fe520271b49bf859305c1178fa5cbe7149221a2b0a89"},"schema_version":"1.0","source":{"id":"1905.10478","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10478","created_at":"2026-05-17T23:45:08Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10478v1","created_at":"2026-05-17T23:45:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10478","created_at":"2026-05-17T23:45:08Z"},{"alias_kind":"pith_short_12","alias_value":"ISAW6Q7BXLZU","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"ISAW6Q7BXLZUH2A4","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"ISAW6Q7B","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:8982c0e6431a0273e6f1657f70af7e94824200ba45e7ff6ff0dbd1bdcd47ed0a","target":"graph","created_at":"2026-05-17T23:45:08Z","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"},"paper":{"abstract_excerpt":"Tensor decomposition is an effective approach to compress over-parameterized neural networks and to enable their deployment on resource-constrained hardware platforms. However, directly applying tensor compression in the training process is a challenging task due to the difficulty of choosing a proper tensor rank. In order to achieve this goal, this paper proposes a Bayesian tensorized neural network. Our Bayesian method performs automatic model compression via an adaptive tensor rank determination. We also present approaches for posterior density calculation and maximum a posteriori (MAP) est","authors_text":"Cole Hawkins, Zheng Zhang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T23:18:17Z","title":"Bayesian Tensorized Neural Networks with Automatic Rank Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10478","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":"sha256:8796fa100a4c28273eddc1b7be8f491a315693d46d3600cec5cd84b4055a1924","target":"record","created_at":"2026-05-17T23:45:08Z","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":"2694b9d0b536264cd54e64dafb28c9a7de7c499fe58733076f6732ade3fc68b2","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T23:18:17Z","title_canon_sha256":"c9fbaf97757452bb0c19fe520271b49bf859305c1178fa5cbe7149221a2b0a89"},"schema_version":"1.0","source":{"id":"1905.10478","kind":"arxiv","version":1}},"canonical_sha256":"44816f43e1baf343e81c0de19313fc89efd2d379af1038481be989adf3ded6df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"44816f43e1baf343e81c0de19313fc89efd2d379af1038481be989adf3ded6df","first_computed_at":"2026-05-17T23:45:08.409685Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:08.409685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UYF5COmfXjiGwt/3VR5iWLDQv00uFRn2/fv5392wQP9iwJ4iCMsq07knXfClpy3txDp22YAo51UEoV/oj43dBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:08.410353Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.10478","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8796fa100a4c28273eddc1b7be8f491a315693d46d3600cec5cd84b4055a1924","sha256:8982c0e6431a0273e6f1657f70af7e94824200ba45e7ff6ff0dbd1bdcd47ed0a"],"state_sha256":"e539fc3b34da6427b9d1cc9a5b6f4c7666802a739aacefae6049de54b0c9361d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YZgVKbTFbhO+s6XIICAlsEouHO5xB+H7H1CxGLM2r80Ij+BSTLaYdbfFJuHKwb+iJV7Bg6xcJ3Mo2MBe7E5BBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T14:22:40.692804Z","bundle_sha256":"3b89e107723abc5f81acc269ba0a01824bc6484ebf2e104f340ab0f33977f04f"}}