{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:TQXBBP3TUHGHY74WUMKQ7H4UGY","short_pith_number":"pith:TQXBBP3T","canonical_record":{"source":{"id":"1711.01068","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-03T09:05:44Z","cross_cats_sorted":[],"title_canon_sha256":"48f895580998743ad2a1b43c958f0aa4d2d2293f9dca9f78eb6b2fa38ef8d193","abstract_canon_sha256":"a066fcdd2f48d2779dc1a3c2e7e1a6b31d7a5948e149c01e4a31cad98b520d83"},"schema_version":"1.0"},"canonical_sha256":"9c2e10bf73a1cc7c7f96a3150f9f9436128c80a31f76bf974afa1bc788646adf","source":{"kind":"arxiv","id":"1711.01068","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.01068","created_at":"2026-05-18T00:30:21Z"},{"alias_kind":"arxiv_version","alias_value":"1711.01068v2","created_at":"2026-05-18T00:30:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.01068","created_at":"2026-05-18T00:30:21Z"},{"alias_kind":"pith_short_12","alias_value":"TQXBBP3TUHGH","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"TQXBBP3TUHGHY74W","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"TQXBBP3T","created_at":"2026-05-18T12:31:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:TQXBBP3TUHGHY74WUMKQ7H4UGY","target":"record","payload":{"canonical_record":{"source":{"id":"1711.01068","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-03T09:05:44Z","cross_cats_sorted":[],"title_canon_sha256":"48f895580998743ad2a1b43c958f0aa4d2d2293f9dca9f78eb6b2fa38ef8d193","abstract_canon_sha256":"a066fcdd2f48d2779dc1a3c2e7e1a6b31d7a5948e149c01e4a31cad98b520d83"},"schema_version":"1.0"},"canonical_sha256":"9c2e10bf73a1cc7c7f96a3150f9f9436128c80a31f76bf974afa1bc788646adf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:21.794462Z","signature_b64":"B/hKUUCbyiPRYJ6S4oimlrLxfbURDkA4KE0TEEz2R023rRoImaxnw85sH/CL26N+aLoLnN3/1yDP7FjM0LNXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c2e10bf73a1cc7c7f96a3150f9f9436128c80a31f76bf974afa1bc788646adf","last_reissued_at":"2026-05-18T00:30:21.793565Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:21.793565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.01068","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":"2026-05-18T00:30:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DYRbp4IZRlGrmtA/Mt2e957SXK8Q0pB5keaONpvIIyk37HmNim7W6l+HlnGRV9vFWFajgc+qmzSi1DaKfNVmDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T17:26:12.185223Z"},"content_sha256":"70c02e261acc96419ebc890c45d7e90dd4ebba35bbdca15889648eb8e4899a38","schema_version":"1.0","event_id":"sha256:70c02e261acc96419ebc890c45d7e90dd4ebba35bbdca15889648eb8e4899a38"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:TQXBBP3TUHGHY74WUMKQ7H4UGY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Compressing Word Embeddings via Deep Compositional Code Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hideki Nakayama, Raphael Shu","submitted_at":"2017-11-03T09:05:44Z","abstract_excerpt":"Natural language processing (NLP) models often require a massive number of parameters for word embeddings, resulting in a large storage or memory footprint. Deploying neural NLP models to mobile devices requires compressing the word embeddings without any significant sacrifices in performance. For this purpose, we propose to construct the embeddings with few basis vectors. For each word, the composition of basis vectors is determined by a hash code. To maximize the compression rate, we adopt the multi-codebook quantization approach instead of binary coding scheme. Each code is composed of mult"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.01068","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":""},"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":"2026-05-18T00:30:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rfsSG/Ug2w5GP3t+FZi07cGgu3pfmTs8+XAuFjNZ4h52LrYvsUSmgJSVSnZouwK6nPYMx+b3qW6GR6IP9c0vBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T17:26:12.185839Z"},"content_sha256":"8bc22a333aad92f1ee9a26cbd9d5f992594108a974d458dfcd0911236ec93904","schema_version":"1.0","event_id":"sha256:8bc22a333aad92f1ee9a26cbd9d5f992594108a974d458dfcd0911236ec93904"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TQXBBP3TUHGHY74WUMKQ7H4UGY/bundle.json","state_url":"https://pith.science/pith/TQXBBP3TUHGHY74WUMKQ7H4UGY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TQXBBP3TUHGHY74WUMKQ7H4UGY/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":"2026-06-04T17:26:12Z","links":{"resolver":"https://pith.science/pith/TQXBBP3TUHGHY74WUMKQ7H4UGY","bundle":"https://pith.science/pith/TQXBBP3TUHGHY74WUMKQ7H4UGY/bundle.json","state":"https://pith.science/pith/TQXBBP3TUHGHY74WUMKQ7H4UGY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TQXBBP3TUHGHY74WUMKQ7H4UGY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:TQXBBP3TUHGHY74WUMKQ7H4UGY","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":"a066fcdd2f48d2779dc1a3c2e7e1a6b31d7a5948e149c01e4a31cad98b520d83","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-03T09:05:44Z","title_canon_sha256":"48f895580998743ad2a1b43c958f0aa4d2d2293f9dca9f78eb6b2fa38ef8d193"},"schema_version":"1.0","source":{"id":"1711.01068","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.01068","created_at":"2026-05-18T00:30:21Z"},{"alias_kind":"arxiv_version","alias_value":"1711.01068v2","created_at":"2026-05-18T00:30:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.01068","created_at":"2026-05-18T00:30:21Z"},{"alias_kind":"pith_short_12","alias_value":"TQXBBP3TUHGH","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"TQXBBP3TUHGHY74W","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"TQXBBP3T","created_at":"2026-05-18T12:31:46Z"}],"graph_snapshots":[{"event_id":"sha256:8bc22a333aad92f1ee9a26cbd9d5f992594108a974d458dfcd0911236ec93904","target":"graph","created_at":"2026-05-18T00:30:21Z","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":"Natural language processing (NLP) models often require a massive number of parameters for word embeddings, resulting in a large storage or memory footprint. Deploying neural NLP models to mobile devices requires compressing the word embeddings without any significant sacrifices in performance. For this purpose, we propose to construct the embeddings with few basis vectors. For each word, the composition of basis vectors is determined by a hash code. To maximize the compression rate, we adopt the multi-codebook quantization approach instead of binary coding scheme. Each code is composed of mult","authors_text":"Hideki Nakayama, Raphael Shu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-03T09:05:44Z","title":"Compressing Word Embeddings via Deep Compositional Code Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.01068","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":"sha256:70c02e261acc96419ebc890c45d7e90dd4ebba35bbdca15889648eb8e4899a38","target":"record","created_at":"2026-05-18T00:30:21Z","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":"a066fcdd2f48d2779dc1a3c2e7e1a6b31d7a5948e149c01e4a31cad98b520d83","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-03T09:05:44Z","title_canon_sha256":"48f895580998743ad2a1b43c958f0aa4d2d2293f9dca9f78eb6b2fa38ef8d193"},"schema_version":"1.0","source":{"id":"1711.01068","kind":"arxiv","version":2}},"canonical_sha256":"9c2e10bf73a1cc7c7f96a3150f9f9436128c80a31f76bf974afa1bc788646adf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c2e10bf73a1cc7c7f96a3150f9f9436128c80a31f76bf974afa1bc788646adf","first_computed_at":"2026-05-18T00:30:21.793565Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:30:21.793565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B/hKUUCbyiPRYJ6S4oimlrLxfbURDkA4KE0TEEz2R023rRoImaxnw85sH/CL26N+aLoLnN3/1yDP7FjM0LNXCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:30:21.794462Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.01068","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70c02e261acc96419ebc890c45d7e90dd4ebba35bbdca15889648eb8e4899a38","sha256:8bc22a333aad92f1ee9a26cbd9d5f992594108a974d458dfcd0911236ec93904"],"state_sha256":"ff149cf553b997821243a78001c4d60a35696c008865f76f4451af3c29f985da"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rp4plKp9GD7jZ6HK8uC4ivsfLCbiThbSOOefc8yufF8ttlHtlXg8YDb/0IpS9XZ0L2LcjP2Ks7/pkUQYz6WfDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T17:26:12.187992Z","bundle_sha256":"f6dfdaa92b40c506f7cc3ccea74deeb2ccaa4034933f81f0febd6871b7e1700b"}}