{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:W7PANAWVOVUOAWEUXG3FPM2MIX","short_pith_number":"pith:W7PANAWV","canonical_record":{"source":{"id":"1703.10722","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-31T00:50:37Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"edf04fa8a20cf625be0086f87a3ec7df601d0da1023f29b8dc083e306d899aac","abstract_canon_sha256":"2796bf7b8f958215557116173b1e7e5463be3a3a53ec19d89b6edbb0ed1798c0"},"schema_version":"1.0"},"canonical_sha256":"b7de0682d57568e05894b9b657b34c45fc2ad90468179c23960983b839cde772","source":{"kind":"arxiv","id":"1703.10722","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.10722","created_at":"2026-05-18T00:22:39Z"},{"alias_kind":"arxiv_version","alias_value":"1703.10722v3","created_at":"2026-05-18T00:22:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.10722","created_at":"2026-05-18T00:22:39Z"},{"alias_kind":"pith_short_12","alias_value":"W7PANAWVOVUO","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"W7PANAWVOVUOAWEU","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"W7PANAWV","created_at":"2026-05-18T12:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:W7PANAWVOVUOAWEUXG3FPM2MIX","target":"record","payload":{"canonical_record":{"source":{"id":"1703.10722","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-31T00:50:37Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"edf04fa8a20cf625be0086f87a3ec7df601d0da1023f29b8dc083e306d899aac","abstract_canon_sha256":"2796bf7b8f958215557116173b1e7e5463be3a3a53ec19d89b6edbb0ed1798c0"},"schema_version":"1.0"},"canonical_sha256":"b7de0682d57568e05894b9b657b34c45fc2ad90468179c23960983b839cde772","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:39.970903Z","signature_b64":"k4uq7BRSm2P8oZsAcNIS5YofIGZ82SjuaNSv3kjwi3Zs7LJJupe3nwO0UyZ5ifqjL3fwouM05Y0lmGhMlWADCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7de0682d57568e05894b9b657b34c45fc2ad90468179c23960983b839cde772","last_reissued_at":"2026-05-18T00:22:39.970459Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:39.970459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.10722","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:22:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hJ1sl5IZsuXHNKInu01mgyiB+swgZpe9X7G4hjDWoOrgeYrbhuJT6W7rNud70QP1UOj7CIDBAaL4zM8PQPPtBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T10:38:38.153799Z"},"content_sha256":"1ef4e20bb31067b6af9fe9f310b2a8f076187e7e62ba20fa20711697afaa64cc","schema_version":"1.0","event_id":"sha256:1ef4e20bb31067b6af9fe9f310b2a8f076187e7e62ba20fa20711697afaa64cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:W7PANAWVOVUOAWEUXG3FPM2MIX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Factorization tricks for LSTM networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.CL","authors_text":"Boris Ginsburg, Oleksii Kuchaiev","submitted_at":"2017-03-31T00:50:37Z","abstract_excerpt":"We present two simple ways of reducing the number of parameters and accelerating the training of large Long Short-Term Memory (LSTM) networks: the first one is \"matrix factorization by design\" of LSTM matrix into the product of two smaller matrices, and the second one is partitioning of LSTM matrix, its inputs and states into the independent groups. Both approaches allow us to train large LSTM networks significantly faster to the near state-of the art perplexity while using significantly less RNN parameters."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.10722","kind":"arxiv","version":3},"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":"2026-05-18T00:22:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j5OKRMctmDKZf2J7I1oNzhGnhXcDtGjetkkMtBvSZBcqMQuSfpdTLsSJ6PSWvTTjb6kZvWQlbEw+SesFLnYLCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T10:38:38.154535Z"},"content_sha256":"643c63b82eef0131eecce68bd0aa7605154935b82bd126658b3568a23707e724","schema_version":"1.0","event_id":"sha256:643c63b82eef0131eecce68bd0aa7605154935b82bd126658b3568a23707e724"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W7PANAWVOVUOAWEUXG3FPM2MIX/bundle.json","state_url":"https://pith.science/pith/W7PANAWVOVUOAWEUXG3FPM2MIX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W7PANAWVOVUOAWEUXG3FPM2MIX/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":"2026-05-26T10:38:38Z","links":{"resolver":"https://pith.science/pith/W7PANAWVOVUOAWEUXG3FPM2MIX","bundle":"https://pith.science/pith/W7PANAWVOVUOAWEUXG3FPM2MIX/bundle.json","state":"https://pith.science/pith/W7PANAWVOVUOAWEUXG3FPM2MIX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W7PANAWVOVUOAWEUXG3FPM2MIX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:W7PANAWVOVUOAWEUXG3FPM2MIX","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":"2796bf7b8f958215557116173b1e7e5463be3a3a53ec19d89b6edbb0ed1798c0","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-31T00:50:37Z","title_canon_sha256":"edf04fa8a20cf625be0086f87a3ec7df601d0da1023f29b8dc083e306d899aac"},"schema_version":"1.0","source":{"id":"1703.10722","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.10722","created_at":"2026-05-18T00:22:39Z"},{"alias_kind":"arxiv_version","alias_value":"1703.10722v3","created_at":"2026-05-18T00:22:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.10722","created_at":"2026-05-18T00:22:39Z"},{"alias_kind":"pith_short_12","alias_value":"W7PANAWVOVUO","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"W7PANAWVOVUOAWEU","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"W7PANAWV","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:643c63b82eef0131eecce68bd0aa7605154935b82bd126658b3568a23707e724","target":"graph","created_at":"2026-05-18T00:22:39Z","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":"We present two simple ways of reducing the number of parameters and accelerating the training of large Long Short-Term Memory (LSTM) networks: the first one is \"matrix factorization by design\" of LSTM matrix into the product of two smaller matrices, and the second one is partitioning of LSTM matrix, its inputs and states into the independent groups. Both approaches allow us to train large LSTM networks significantly faster to the near state-of the art perplexity while using significantly less RNN parameters.","authors_text":"Boris Ginsburg, Oleksii Kuchaiev","cross_cats":["cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-31T00:50:37Z","title":"Factorization tricks for LSTM networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.10722","kind":"arxiv","version":3},"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":"sha256:1ef4e20bb31067b6af9fe9f310b2a8f076187e7e62ba20fa20711697afaa64cc","target":"record","created_at":"2026-05-18T00:22:39Z","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":"2796bf7b8f958215557116173b1e7e5463be3a3a53ec19d89b6edbb0ed1798c0","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-31T00:50:37Z","title_canon_sha256":"edf04fa8a20cf625be0086f87a3ec7df601d0da1023f29b8dc083e306d899aac"},"schema_version":"1.0","source":{"id":"1703.10722","kind":"arxiv","version":3}},"canonical_sha256":"b7de0682d57568e05894b9b657b34c45fc2ad90468179c23960983b839cde772","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7de0682d57568e05894b9b657b34c45fc2ad90468179c23960983b839cde772","first_computed_at":"2026-05-18T00:22:39.970459Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:39.970459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k4uq7BRSm2P8oZsAcNIS5YofIGZ82SjuaNSv3kjwi3Zs7LJJupe3nwO0UyZ5ifqjL3fwouM05Y0lmGhMlWADCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:39.970903Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.10722","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ef4e20bb31067b6af9fe9f310b2a8f076187e7e62ba20fa20711697afaa64cc","sha256:643c63b82eef0131eecce68bd0aa7605154935b82bd126658b3568a23707e724"],"state_sha256":"89b2549814b047dd79f86912188630ae493ccf4358bcfbd174906d081f43817d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HQ6sDOhljwvpyX3yEpvcXN9Q5wRpzArV2v/0KLG6PpzZ2ra4QF4mIs+hdYx3Z4btn7rzRmFvKzLeFTXNCFyaBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T10:38:38.158241Z","bundle_sha256":"0ce34939ef8b4d994687d62a6a04f36fe135d32430faa01921ca72a4ad387ab0"}}