{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:DZ2ISH2OM2CMOF5KUIM2XQWD2A","short_pith_number":"pith:DZ2ISH2O","canonical_record":{"source":{"id":"1604.02594","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-04-09T19:09:22Z","cross_cats_sorted":["cs.CL","cs.NE"],"title_canon_sha256":"7a8b49e484052e40cdd157cab3c5186c51a26eda8b19df4972975149a8f0b3be","abstract_canon_sha256":"0236c6f4a4b573b4dc8ba29f4b66aff406cb4f8994b8dbeaaa399a0bc60ea517"},"schema_version":"1.0"},"canonical_sha256":"1e74891f4e6684c717aaa219abc2c3d01cfc337d472f1db209fbc4db4017a203","source":{"kind":"arxiv","id":"1604.02594","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1604.02594","created_at":"2026-05-18T01:17:22Z"},{"alias_kind":"arxiv_version","alias_value":"1604.02594v1","created_at":"2026-05-18T01:17:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.02594","created_at":"2026-05-18T01:17:22Z"},{"alias_kind":"pith_short_12","alias_value":"DZ2ISH2OM2CM","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"DZ2ISH2OM2CMOF5K","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"DZ2ISH2O","created_at":"2026-05-18T12:30:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:DZ2ISH2OM2CMOF5KUIM2XQWD2A","target":"record","payload":{"canonical_record":{"source":{"id":"1604.02594","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-04-09T19:09:22Z","cross_cats_sorted":["cs.CL","cs.NE"],"title_canon_sha256":"7a8b49e484052e40cdd157cab3c5186c51a26eda8b19df4972975149a8f0b3be","abstract_canon_sha256":"0236c6f4a4b573b4dc8ba29f4b66aff406cb4f8994b8dbeaaa399a0bc60ea517"},"schema_version":"1.0"},"canonical_sha256":"1e74891f4e6684c717aaa219abc2c3d01cfc337d472f1db209fbc4db4017a203","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:22.651564Z","signature_b64":"ubVDOVukkHFbH6laWWEFpENc8YPaun1k2VviGB8h6YNOldeVeYpivJ30hRoTv2M1FgwTBqQ9uRy5vY3hch1CAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e74891f4e6684c717aaa219abc2c3d01cfc337d472f1db209fbc4db4017a203","last_reissued_at":"2026-05-18T01:17:22.651120Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:22.651120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1604.02594","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":"2026-05-18T01:17:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w1V5A9rbnhOL/RyHVA41Hab0SM/0LDePHuSVE2b7PmgM+nIVcWUUlLMrsBgJkvPEDFDTp6Xvje6QG9MnGAEVCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T17:51:25.770624Z"},"content_sha256":"9e47b9691c1eeb1dadaef1b110570dc9cafc29b80163258896d15e6c8473041f","schema_version":"1.0","event_id":"sha256:9e47b9691c1eeb1dadaef1b110570dc9cafc29b80163258896d15e6c8473041f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:DZ2ISH2OM2CMOF5KUIM2XQWD2A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Compact Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.NE"],"primary_cat":"cs.LG","authors_text":"Tara N. Sainath, Vikas Sindhwani, Zhiyun Lu","submitted_at":"2016-04-09T19:09:22Z","abstract_excerpt":"Recurrent neural networks (RNNs), including long short-term memory (LSTM) RNNs, have produced state-of-the-art results on a variety of speech recognition tasks. However, these models are often too large in size for deployment on mobile devices with memory and latency constraints. In this work, we study mechanisms for learning compact RNNs and LSTMs via low-rank factorizations and parameter sharing schemes. Our goal is to investigate redundancies in recurrent architectures where compression can be admitted without losing performance. A hybrid strategy of using structured matrices in the bottom "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.02594","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":"2026-05-18T01:17:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MjfNHPaVkpc5A09Jrhl5RTTentTRb1EgJ1352VM6CteBtoaPmgYCXZDRTJt2OuJy2Jx5Z+vD+R+36AE5Bh/hAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T17:51:25.770972Z"},"content_sha256":"bfd8226f64e37eae0c6d23f77ac2b307e2d6db161288fb733a634173fb656e19","schema_version":"1.0","event_id":"sha256:bfd8226f64e37eae0c6d23f77ac2b307e2d6db161288fb733a634173fb656e19"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DZ2ISH2OM2CMOF5KUIM2XQWD2A/bundle.json","state_url":"https://pith.science/pith/DZ2ISH2OM2CMOF5KUIM2XQWD2A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DZ2ISH2OM2CMOF5KUIM2XQWD2A/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":"2026-06-01T17:51:25Z","links":{"resolver":"https://pith.science/pith/DZ2ISH2OM2CMOF5KUIM2XQWD2A","bundle":"https://pith.science/pith/DZ2ISH2OM2CMOF5KUIM2XQWD2A/bundle.json","state":"https://pith.science/pith/DZ2ISH2OM2CMOF5KUIM2XQWD2A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DZ2ISH2OM2CMOF5KUIM2XQWD2A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:DZ2ISH2OM2CMOF5KUIM2XQWD2A","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":"0236c6f4a4b573b4dc8ba29f4b66aff406cb4f8994b8dbeaaa399a0bc60ea517","cross_cats_sorted":["cs.CL","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-04-09T19:09:22Z","title_canon_sha256":"7a8b49e484052e40cdd157cab3c5186c51a26eda8b19df4972975149a8f0b3be"},"schema_version":"1.0","source":{"id":"1604.02594","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1604.02594","created_at":"2026-05-18T01:17:22Z"},{"alias_kind":"arxiv_version","alias_value":"1604.02594v1","created_at":"2026-05-18T01:17:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.02594","created_at":"2026-05-18T01:17:22Z"},{"alias_kind":"pith_short_12","alias_value":"DZ2ISH2OM2CM","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"DZ2ISH2OM2CMOF5K","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"DZ2ISH2O","created_at":"2026-05-18T12:30:12Z"}],"graph_snapshots":[{"event_id":"sha256:bfd8226f64e37eae0c6d23f77ac2b307e2d6db161288fb733a634173fb656e19","target":"graph","created_at":"2026-05-18T01:17:22Z","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":"Recurrent neural networks (RNNs), including long short-term memory (LSTM) RNNs, have produced state-of-the-art results on a variety of speech recognition tasks. However, these models are often too large in size for deployment on mobile devices with memory and latency constraints. In this work, we study mechanisms for learning compact RNNs and LSTMs via low-rank factorizations and parameter sharing schemes. Our goal is to investigate redundancies in recurrent architectures where compression can be admitted without losing performance. A hybrid strategy of using structured matrices in the bottom ","authors_text":"Tara N. Sainath, Vikas Sindhwani, Zhiyun Lu","cross_cats":["cs.CL","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-04-09T19:09:22Z","title":"Learning Compact Recurrent Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.02594","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":"sha256:9e47b9691c1eeb1dadaef1b110570dc9cafc29b80163258896d15e6c8473041f","target":"record","created_at":"2026-05-18T01:17:22Z","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":"0236c6f4a4b573b4dc8ba29f4b66aff406cb4f8994b8dbeaaa399a0bc60ea517","cross_cats_sorted":["cs.CL","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-04-09T19:09:22Z","title_canon_sha256":"7a8b49e484052e40cdd157cab3c5186c51a26eda8b19df4972975149a8f0b3be"},"schema_version":"1.0","source":{"id":"1604.02594","kind":"arxiv","version":1}},"canonical_sha256":"1e74891f4e6684c717aaa219abc2c3d01cfc337d472f1db209fbc4db4017a203","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e74891f4e6684c717aaa219abc2c3d01cfc337d472f1db209fbc4db4017a203","first_computed_at":"2026-05-18T01:17:22.651120Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:17:22.651120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ubVDOVukkHFbH6laWWEFpENc8YPaun1k2VviGB8h6YNOldeVeYpivJ30hRoTv2M1FgwTBqQ9uRy5vY3hch1CAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:17:22.651564Z","signed_message":"canonical_sha256_bytes"},"source_id":"1604.02594","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e47b9691c1eeb1dadaef1b110570dc9cafc29b80163258896d15e6c8473041f","sha256:bfd8226f64e37eae0c6d23f77ac2b307e2d6db161288fb733a634173fb656e19"],"state_sha256":"477d421a68bb3e706f507ed8619c08de6b8e58693673204918f10f4c29f952e6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6T3MUUh5IHbG4JH1qaZXNfHI6CPsGqeMBn1x/GBXP5pJcOTdRUXGDoDgEZMPbVAGDG9mI91HCbkqeggl1//pAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T17:51:25.772923Z","bundle_sha256":"44b602476f95fbf76afab54d6b2805c8cb7485b20e7889db1c8348b7fcfa66c8"}}