{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:UYOUYI6IUCTWAHROFJDFRB4PKD","short_pith_number":"pith:UYOUYI6I","canonical_record":{"source":{"id":"1910.06720","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-02T16:40:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"be44319e738c997c7a9acf98a3941f5af7777a605d9889d7aad4cf4eba44b8b2","abstract_canon_sha256":"e2196595a6ac8a28f228432518b3ece247d69507411c8b3093014709f7afefca"},"schema_version":"1.0"},"canonical_sha256":"a61d4c23c8a0a7601e2e2a4658878f50da258b1ec03d02174ce6c323fe54acc3","source":{"kind":"arxiv","id":"1910.06720","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.06720","created_at":"2026-07-05T01:50:46Z"},{"alias_kind":"arxiv_version","alias_value":"1910.06720v2","created_at":"2026-07-05T01:50:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.06720","created_at":"2026-07-05T01:50:46Z"},{"alias_kind":"pith_short_12","alias_value":"UYOUYI6IUCTW","created_at":"2026-07-05T01:50:46Z"},{"alias_kind":"pith_short_16","alias_value":"UYOUYI6IUCTWAHRO","created_at":"2026-07-05T01:50:46Z"},{"alias_kind":"pith_short_8","alias_value":"UYOUYI6I","created_at":"2026-07-05T01:50:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:UYOUYI6IUCTWAHROFJDFRB4PKD","target":"record","payload":{"canonical_record":{"source":{"id":"1910.06720","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-02T16:40:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"be44319e738c997c7a9acf98a3941f5af7777a605d9889d7aad4cf4eba44b8b2","abstract_canon_sha256":"e2196595a6ac8a28f228432518b3ece247d69507411c8b3093014709f7afefca"},"schema_version":"1.0"},"canonical_sha256":"a61d4c23c8a0a7601e2e2a4658878f50da258b1ec03d02174ce6c323fe54acc3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:50:46.460550Z","signature_b64":"ox0eogWEngEiFHnllqaHB5gXxJcvzi37cQoOJuiHOGNPCwxu74zLQP7yEXGRwipUSVTtRawWaQofr5DXvlLKAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a61d4c23c8a0a7601e2e2a4658878f50da258b1ec03d02174ce6c323fe54acc3","last_reissued_at":"2026-07-05T01:50:46.460066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:50:46.460066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.06720","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":"2026-07-05T01:50:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ufQzAzDDfTIbWiWD4jTxJt99p9VFvmBUA2h5VhXyltmV7palOhRy56xEMbBNwIf++jYBzfwoQGMBZb6XG8kIBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:06:38.812599Z"},"content_sha256":"e35a1af692d4fbf422b9a0ffd3fabf58cc8c098434b7a2e4dcfcc539fd3aa440","schema_version":"1.0","event_id":"sha256:e35a1af692d4fbf422b9a0ffd3fabf58cc8c098434b7a2e4dcfcc539fd3aa440"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:UYOUYI6IUCTWAHROFJDFRB4PKD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Word Embedding Factorization for Compression Using Distilled Nonlinear Neural Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ahmad Rashid, Krtin Kumar, Md Akmal Haidar, Mehdi Rezagholizadeh, Vasileios Lioutas","submitted_at":"2019-10-02T16:40:03Z","abstract_excerpt":"Word-embeddings are vital components of Natural Language Processing (NLP) models and have been extensively explored. However, they consume a lot of memory which poses a challenge for edge deployment. Embedding matrices, typically, contain most of the parameters for language models and about a third for machine translation systems. In this paper, we propose Distilled Embedding, an (input/output) embedding compression method based on low-rank matrix decomposition and knowledge distillation. First, we initialize the weights of our decomposed matrices by learning to reconstruct the full pre-traine"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.06720","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/1910.06720/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":"2026-07-05T01:50:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i2LAdUKCFlSMHLA77SCGjzTTCH3/Kc0voJ2Yd2O+3gjJg2fqCZxEI9vJWsz0+KzooTIxG71oY+gSp6rth+uuBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:06:38.812969Z"},"content_sha256":"45504fbfbddd0f730424256e07638faba0f2f1e227693d4014b4431340d663b1","schema_version":"1.0","event_id":"sha256:45504fbfbddd0f730424256e07638faba0f2f1e227693d4014b4431340d663b1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UYOUYI6IUCTWAHROFJDFRB4PKD/bundle.json","state_url":"https://pith.science/pith/UYOUYI6IUCTWAHROFJDFRB4PKD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UYOUYI6IUCTWAHROFJDFRB4PKD/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":"2026-07-06T23:06:38Z","links":{"resolver":"https://pith.science/pith/UYOUYI6IUCTWAHROFJDFRB4PKD","bundle":"https://pith.science/pith/UYOUYI6IUCTWAHROFJDFRB4PKD/bundle.json","state":"https://pith.science/pith/UYOUYI6IUCTWAHROFJDFRB4PKD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UYOUYI6IUCTWAHROFJDFRB4PKD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:UYOUYI6IUCTWAHROFJDFRB4PKD","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":"e2196595a6ac8a28f228432518b3ece247d69507411c8b3093014709f7afefca","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-02T16:40:03Z","title_canon_sha256":"be44319e738c997c7a9acf98a3941f5af7777a605d9889d7aad4cf4eba44b8b2"},"schema_version":"1.0","source":{"id":"1910.06720","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.06720","created_at":"2026-07-05T01:50:46Z"},{"alias_kind":"arxiv_version","alias_value":"1910.06720v2","created_at":"2026-07-05T01:50:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.06720","created_at":"2026-07-05T01:50:46Z"},{"alias_kind":"pith_short_12","alias_value":"UYOUYI6IUCTW","created_at":"2026-07-05T01:50:46Z"},{"alias_kind":"pith_short_16","alias_value":"UYOUYI6IUCTWAHRO","created_at":"2026-07-05T01:50:46Z"},{"alias_kind":"pith_short_8","alias_value":"UYOUYI6I","created_at":"2026-07-05T01:50:46Z"}],"graph_snapshots":[{"event_id":"sha256:45504fbfbddd0f730424256e07638faba0f2f1e227693d4014b4431340d663b1","target":"graph","created_at":"2026-07-05T01:50:46Z","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/1910.06720/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Word-embeddings are vital components of Natural Language Processing (NLP) models and have been extensively explored. However, they consume a lot of memory which poses a challenge for edge deployment. Embedding matrices, typically, contain most of the parameters for language models and about a third for machine translation systems. In this paper, we propose Distilled Embedding, an (input/output) embedding compression method based on low-rank matrix decomposition and knowledge distillation. First, we initialize the weights of our decomposed matrices by learning to reconstruct the full pre-traine","authors_text":"Ahmad Rashid, Krtin Kumar, Md Akmal Haidar, Mehdi Rezagholizadeh, Vasileios Lioutas","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-02T16:40:03Z","title":"Improving Word Embedding Factorization for Compression Using Distilled Nonlinear Neural Decomposition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.06720","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:e35a1af692d4fbf422b9a0ffd3fabf58cc8c098434b7a2e4dcfcc539fd3aa440","target":"record","created_at":"2026-07-05T01:50:46Z","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":"e2196595a6ac8a28f228432518b3ece247d69507411c8b3093014709f7afefca","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-02T16:40:03Z","title_canon_sha256":"be44319e738c997c7a9acf98a3941f5af7777a605d9889d7aad4cf4eba44b8b2"},"schema_version":"1.0","source":{"id":"1910.06720","kind":"arxiv","version":2}},"canonical_sha256":"a61d4c23c8a0a7601e2e2a4658878f50da258b1ec03d02174ce6c323fe54acc3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a61d4c23c8a0a7601e2e2a4658878f50da258b1ec03d02174ce6c323fe54acc3","first_computed_at":"2026-07-05T01:50:46.460066Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:50:46.460066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ox0eogWEngEiFHnllqaHB5gXxJcvzi37cQoOJuiHOGNPCwxu74zLQP7yEXGRwipUSVTtRawWaQofr5DXvlLKAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:50:46.460550Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.06720","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e35a1af692d4fbf422b9a0ffd3fabf58cc8c098434b7a2e4dcfcc539fd3aa440","sha256:45504fbfbddd0f730424256e07638faba0f2f1e227693d4014b4431340d663b1"],"state_sha256":"e8b12a606de050dc55ee2752fc04c79785620c66a16846575226a8eaa55ff82e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IYOmyQt/ez31p7xVnC21noKPrVY4ZaQ6qUpJ2JOLaP+i7zGt9dZT9VsG6EfsWqWpxV07ZxQIX8SUT43PLMEGBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:06:38.814931Z","bundle_sha256":"6a0c363aa2f4d8d372246d1bfe0b86a73024b38ddceacf0ad796205123cbdf6e"}}