{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:ETVPW5JVXCYF3WV42BE5BOCBLZ","short_pith_number":"pith:ETVPW5JV","schema_version":"1.0","canonical_sha256":"24eafb7535b8b05ddabcd049d0b8415e5847e2dcc27ce1db3759423aa062fa8e","source":{"kind":"arxiv","id":"1612.03651","version":1},"attestation_state":"computed","paper":{"title":"FastText.zip: Compressing text classification models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Armand Joulin, Edouard Grave, H\\'erve J\\'egou, Matthijs Douze, Piotr Bojanowski, Tomas Mikolov","submitted_at":"2016-12-12T12:51:03Z","abstract_excerpt":"We consider the problem of producing compact architectures for text classification, such that the full model fits in a limited amount of memory. After considering different solutions inspired by the hashing literature, we propose a method built upon product quantization to store word embeddings. While the original technique leads to a loss in accuracy, we adapt this method to circumvent quantization artefacts. Our experiments carried out on several benchmarks show that our approach typically requires two orders of magnitude less memory than fastText while being only slightly inferior with resp"},"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":"1612.03651","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-12T12:51:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7abc0fb5896f8e347d4447582e3b810378a0e1a11c87641ef333d9bf0132ddcc","abstract_canon_sha256":"7525db0b33b446297b1d60d7798c866587903d6396516c30eceea8cb13290f35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:54:52.352132Z","signature_b64":"1dtVMUuYlUWPF7MAs70pXWxHCjB0+XcnF8IhFg1U2ayMFQENLa0lVsoejBn/DuE7iBDLiwc5mpzieAcTJC2iDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24eafb7535b8b05ddabcd049d0b8415e5847e2dcc27ce1db3759423aa062fa8e","last_reissued_at":"2026-05-18T00:54:52.351626Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:54:52.351626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FastText.zip: Compressing text classification models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Armand Joulin, Edouard Grave, H\\'erve J\\'egou, Matthijs Douze, Piotr Bojanowski, Tomas Mikolov","submitted_at":"2016-12-12T12:51:03Z","abstract_excerpt":"We consider the problem of producing compact architectures for text classification, such that the full model fits in a limited amount of memory. After considering different solutions inspired by the hashing literature, we propose a method built upon product quantization to store word embeddings. While the original technique leads to a loss in accuracy, we adapt this method to circumvent quantization artefacts. Our experiments carried out on several benchmarks show that our approach typically requires two orders of magnitude less memory than fastText while being only slightly inferior with resp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.03651","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1612.03651","created_at":"2026-05-18T00:54:52.351705+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.03651v1","created_at":"2026-05-18T00:54:52.351705+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.03651","created_at":"2026-05-18T00:54:52.351705+00:00"},{"alias_kind":"pith_short_12","alias_value":"ETVPW5JVXCYF","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_16","alias_value":"ETVPW5JVXCYF3WV4","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_8","alias_value":"ETVPW5JV","created_at":"2026-05-18T12:30:15.759754+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":31,"internal_anchor_count":19,"sample":[{"citing_arxiv_id":"2607.06613","citing_title":"Pre-Training on Software Engineering Texts: Effects on Domain Adaptation and General-Language Understanding","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2607.01456","citing_title":"From Anatomy to Smells: An Empirical Study of SKILL.md in Agent Skills","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2606.12234","citing_title":"On The Effectiveness-Fluency Trade-Off In LLM Conditioning: A Systematic Study","ref_index":94,"is_internal_anchor":true},{"citing_arxiv_id":"2606.10772","citing_title":"Structural Under-Representation of Women in News: Nonparametric Bayesian Mixtures Capture Time-Dependent Dynamics","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2606.08994","citing_title":"Language-Aware Token Boosting: LLM Language Confusion Reduction Without Tuning","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2606.05958","citing_title":"Steering Vectors are an Adversarial Attack Surface","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2606.01802","citing_title":"MOSS-Audio Technical Report","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2606.02100","citing_title":"PortBERT: Navigating the Depths of Portuguese Language Models","ref_index":69,"is_internal_anchor":true},{"citing_arxiv_id":"1906.09543","citing_title":"Cross-lingual Data Transformation and Combination for Text Classification","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"1906.11604","citing_title":"Gated Embeddings in End-to-End Speech Recognition for Conversational-Context Fusion","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23036","citing_title":"Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selection","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2309.11381","citing_title":"Studying Lobby Influence in the European Parliament","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2402.03300","citing_title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12623","citing_title":"DocAtlas: Multilingual Document Understanding Across 80+ Languages","ref_index":71,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21614","citing_title":"Exploring the Effectiveness of Using LLMs for Automated Assessment of Student Self Explanations in Programming Education","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15613","citing_title":"Toward LLMs Beyond English-Centric Development","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15956","citing_title":"TeraGram: A Structured Longitudinal Dataset of the Telegram Messenger","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2406.11931","citing_title":"DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12623","citing_title":"DocAtlas: Multilingual Document Understanding Across 80+ Languages","ref_index":78,"is_internal_anchor":true},{"citing_arxiv_id":"2306.01116","citing_title":"The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2502.02737","citing_title":"SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model","ref_index":184,"is_internal_anchor":false},{"citing_arxiv_id":"2406.17557","citing_title":"The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10129","citing_title":"Synthetic Pre-Pre-Training Improves Language Model Robustness to Noisy Pre-Training Data","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05566","citing_title":"Nonsense Helps: Prompt Space Perturbation Broadens Reasoning Exploration","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21593","citing_title":"Language as a Latent Variable for Reasoning Optimization","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ETVPW5JVXCYF3WV42BE5BOCBLZ","json":"https://pith.science/pith/ETVPW5JVXCYF3WV42BE5BOCBLZ.json","graph_json":"https://pith.science/api/pith-number/ETVPW5JVXCYF3WV42BE5BOCBLZ/graph.json","events_json":"https://pith.science/api/pith-number/ETVPW5JVXCYF3WV42BE5BOCBLZ/events.json","paper":"https://pith.science/paper/ETVPW5JV"},"agent_actions":{"view_html":"https://pith.science/pith/ETVPW5JVXCYF3WV42BE5BOCBLZ","download_json":"https://pith.science/pith/ETVPW5JVXCYF3WV42BE5BOCBLZ.json","view_paper":"https://pith.science/paper/ETVPW5JV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.03651&json=true","fetch_graph":"https://pith.science/api/pith-number/ETVPW5JVXCYF3WV42BE5BOCBLZ/graph.json","fetch_events":"https://pith.science/api/pith-number/ETVPW5JVXCYF3WV42BE5BOCBLZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ETVPW5JVXCYF3WV42BE5BOCBLZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ETVPW5JVXCYF3WV42BE5BOCBLZ/action/storage_attestation","attest_author":"https://pith.science/pith/ETVPW5JVXCYF3WV42BE5BOCBLZ/action/author_attestation","sign_citation":"https://pith.science/pith/ETVPW5JVXCYF3WV42BE5BOCBLZ/action/citation_signature","submit_replication":"https://pith.science/pith/ETVPW5JVXCYF3WV42BE5BOCBLZ/action/replication_record"}},"created_at":"2026-05-18T00:54:52.351705+00:00","updated_at":"2026-05-18T00:54:52.351705+00:00"}