{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:QR55YROTLDGCOIWXG7FRO5N3XN","short_pith_number":"pith:QR55YROT","schema_version":"1.0","canonical_sha256":"847bdc45d358cc2722d737cb1775bbbb6b81fdae6e155e81c1c1728a831a4b08","source":{"kind":"arxiv","id":"1803.09065","version":3},"attestation_state":"computed","paper":{"title":"Near-lossless Binarization of Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amaury Habrard, Christophe Gravier, Julien Tissier","submitted_at":"2018-03-24T06:21:56Z","abstract_excerpt":"Word embeddings are commonly used as a starting point in many NLP models to achieve state-of-the-art performances. However, with a large vocabulary and many dimensions, these floating-point representations are expensive both in terms of memory and calculations which makes them unsuitable for use on low-resource devices. The method proposed in this paper transforms real-valued embeddings into binary embeddings while preserving semantic information, requiring only 128 or 256 bits for each vector. This leads to a small memory footprint and fast vector operations. The model is based on an autoenco"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1803.09065","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-24T06:21:56Z","cross_cats_sorted":[],"title_canon_sha256":"e1a8a50bda3a6f27cc05a8d9a07b17f39b32e5f2942cf88a15d7a2745a12a052","abstract_canon_sha256":"a22783391fb59775ba07d2721ca554a0b23777f9f2e67caab736ce020cf56dc8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:34:59.111233Z","signature_b64":"F5Yu++shO0MgKKeNNBjbpKhAtDnvuVW7q4g4OoATPgPWjhgdI0C/tX7Iz9gbh0sEQmbvtWKXjRGk/fATNSjvAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"847bdc45d358cc2722d737cb1775bbbb6b81fdae6e155e81c1c1728a831a4b08","last_reissued_at":"2026-07-05T00:34:59.110888Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:34:59.110888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Near-lossless Binarization of Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amaury Habrard, Christophe Gravier, Julien Tissier","submitted_at":"2018-03-24T06:21:56Z","abstract_excerpt":"Word embeddings are commonly used as a starting point in many NLP models to achieve state-of-the-art performances. However, with a large vocabulary and many dimensions, these floating-point representations are expensive both in terms of memory and calculations which makes them unsuitable for use on low-resource devices. The method proposed in this paper transforms real-valued embeddings into binary embeddings while preserving semantic information, requiring only 128 or 256 bits for each vector. This leads to a small memory footprint and fast vector operations. The model is based on an autoenco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.09065","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1803.09065/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1803.09065","created_at":"2026-07-05T00:34:59.110940+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.09065v3","created_at":"2026-07-05T00:34:59.110940+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.09065","created_at":"2026-07-05T00:34:59.110940+00:00"},{"alias_kind":"pith_short_12","alias_value":"QR55YROTLDGC","created_at":"2026-07-05T00:34:59.110940+00:00"},{"alias_kind":"pith_short_16","alias_value":"QR55YROTLDGCOIWX","created_at":"2026-07-05T00:34:59.110940+00:00"},{"alias_kind":"pith_short_8","alias_value":"QR55YROT","created_at":"2026-07-05T00:34:59.110940+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.05541","citing_title":"Hamming Sentence Embeddings for Information Retrieval","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QR55YROTLDGCOIWXG7FRO5N3XN","json":"https://pith.science/pith/QR55YROTLDGCOIWXG7FRO5N3XN.json","graph_json":"https://pith.science/api/pith-number/QR55YROTLDGCOIWXG7FRO5N3XN/graph.json","events_json":"https://pith.science/api/pith-number/QR55YROTLDGCOIWXG7FRO5N3XN/events.json","paper":"https://pith.science/paper/QR55YROT"},"agent_actions":{"view_html":"https://pith.science/pith/QR55YROTLDGCOIWXG7FRO5N3XN","download_json":"https://pith.science/pith/QR55YROTLDGCOIWXG7FRO5N3XN.json","view_paper":"https://pith.science/paper/QR55YROT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.09065&json=true","fetch_graph":"https://pith.science/api/pith-number/QR55YROTLDGCOIWXG7FRO5N3XN/graph.json","fetch_events":"https://pith.science/api/pith-number/QR55YROTLDGCOIWXG7FRO5N3XN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QR55YROTLDGCOIWXG7FRO5N3XN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QR55YROTLDGCOIWXG7FRO5N3XN/action/storage_attestation","attest_author":"https://pith.science/pith/QR55YROTLDGCOIWXG7FRO5N3XN/action/author_attestation","sign_citation":"https://pith.science/pith/QR55YROTLDGCOIWXG7FRO5N3XN/action/citation_signature","submit_replication":"https://pith.science/pith/QR55YROTLDGCOIWXG7FRO5N3XN/action/replication_record"}},"created_at":"2026-07-05T00:34:59.110940+00:00","updated_at":"2026-07-05T00:34:59.110940+00:00"}