{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:B6DGJSQ62XPXHNVLDS453EMYUV","short_pith_number":"pith:B6DGJSQ6","schema_version":"1.0","canonical_sha256":"0f8664ca1ed5df73b6ab1cb9dd9198a5697e33f50efe2b752bf62a17e662ad53","source":{"kind":"arxiv","id":"2109.10086","version":1},"attestation_state":"computed","paper":{"title":"SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Benjamin Piwowarski, Carlos Lassance, St\\'ephane Clinchant, Thibault Formal","submitted_at":"2021-09-21T10:43:42Z","abstract_excerpt":"In neural Information Retrieval (IR), ongoing research is directed towards improving the first retriever in ranking pipelines. Learning dense embeddings to conduct retrieval using efficient approximate nearest neighbors methods has proven to work well. Meanwhile, there has been a growing interest in learning \\emph{sparse} representations for documents and queries, that could inherit from the desirable properties of bag-of-words models such as the exact matching of terms and the efficiency of inverted indexes. Introduced recently, the SPLADE model provides highly sparse representations and comp"},"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":"2109.10086","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2021-09-21T10:43:42Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"bda79c76d61fbe53dca4084a6486513a58fc7f18e7f80ac20f1e361464acff34","abstract_canon_sha256":"cfbe19b47f4ef696448b1ef3333c02627b7cc3e4a4393819055fa90507dd3240"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:58.014305Z","signature_b64":"fMxH7c9LV8uQIFz/Wr2lgRz8+8BwSEX8xze7XAWiOvwEKwxzI2mO7HPyksLhWtLREh1RbibeHHEnp8OPFdzXCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f8664ca1ed5df73b6ab1cb9dd9198a5697e33f50efe2b752bf62a17e662ad53","last_reissued_at":"2026-07-05T03:15:58.013804Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:58.013804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Benjamin Piwowarski, Carlos Lassance, St\\'ephane Clinchant, Thibault Formal","submitted_at":"2021-09-21T10:43:42Z","abstract_excerpt":"In neural Information Retrieval (IR), ongoing research is directed towards improving the first retriever in ranking pipelines. Learning dense embeddings to conduct retrieval using efficient approximate nearest neighbors methods has proven to work well. Meanwhile, there has been a growing interest in learning \\emph{sparse} representations for documents and queries, that could inherit from the desirable properties of bag-of-words models such as the exact matching of terms and the efficiency of inverted indexes. Introduced recently, the SPLADE model provides highly sparse representations and comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.10086","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2109.10086/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":"2109.10086","created_at":"2026-07-05T03:15:58.013864+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.10086v1","created_at":"2026-07-05T03:15:58.013864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.10086","created_at":"2026-07-05T03:15:58.013864+00:00"},{"alias_kind":"pith_short_12","alias_value":"B6DGJSQ62XPX","created_at":"2026-07-05T03:15:58.013864+00:00"},{"alias_kind":"pith_short_16","alias_value":"B6DGJSQ62XPXHNVL","created_at":"2026-07-05T03:15:58.013864+00:00"},{"alias_kind":"pith_short_8","alias_value":"B6DGJSQ6","created_at":"2026-07-05T03:15:58.013864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":24,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.00004","citing_title":"Why Advanced Encoders Lag on Sparse Retrieval? The Answer and an Approach to Bridging Vocabulary Gaps","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26441","citing_title":"GPUSparse: GPU-Accelerated Learned Sparse Retrieval with Parallel Inverted Indices","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24937","citing_title":"The Hitchhiker's Guide to Agentic AI: From Foundations to Systems","ref_index":296,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18811","citing_title":"Rescaling MLM-Head for Neural Sparse Retrieval","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10621","citing_title":"STORM: Stepwise Token Optimization with Reward-Guided Beam Search","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08673","citing_title":"ClinicalAligner26AM: A Cross-Lingual Aligner for Dataset Translation; Evidences from the MultiClinCorpus Shared Task","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05568","citing_title":"ColBERTSaR: Sparsified ColBERT Index via Product Quantization","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04650","citing_title":"Improving the Efficiency and Effectiveness of LLM Knowledge Distillation for Conversational Search","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27559","citing_title":"A Sensitivity-Aware Test Collection for Search Among Personal Information","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2507.08480","citing_title":"Improving Korean-English Cross-Lingual Retrieval: A Data-Centric Study of Language Composition and Model Merging","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17762","citing_title":"Surface-Form Neural Sparse Retrieval: Robust Fuzzy Matching for Industrial Music Search","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19628","citing_title":"Understanding Wacky Weights: A Dissection of SPLADE's Learned Term Importance","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2509.16621","citing_title":"The Role of Vocabularies in Learning Sparse Representations for Ranking","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2208.03299","citing_title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2602.15423","citing_title":"GaiaFlow: Semantic-Guided Diffusion Tuning for Carbon-Frugal Search","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2201.10005","citing_title":"Text and Code Embeddings by Contrastive Pre-Training","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2603.09933","citing_title":"A Voronoi Cell Formulation for Principled Token Pruning in Late-Interaction Retrieval Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15184","citing_title":"Is Grep All You Need? How Agent Harnesses Reshape Agentic Search","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03676","citing_title":"Are LLM-Based Retrievers Worth Their Cost? An Empirical Study of Efficiency, Robustness, and Reasoning Overhead","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2112.09118","citing_title":"Unsupervised Dense Information Retrieval with Contrastive Learning","ref_index":129,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28142","citing_title":"Efficient Multivector Retrieval with Token-Aware Clustering and Hierarchical Indexing","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19566","citing_title":"Diagnosable ColBERT: Debugging Late-Interaction Retrieval Models Using a Learned Latent Space as Reference","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18584","citing_title":"MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13728","citing_title":"Hybrid Retrieval for COVID-19 Literature: Comparing Rank Fusion and Projection Fusion with Diversity Reranking","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B6DGJSQ62XPXHNVLDS453EMYUV","json":"https://pith.science/pith/B6DGJSQ62XPXHNVLDS453EMYUV.json","graph_json":"https://pith.science/api/pith-number/B6DGJSQ62XPXHNVLDS453EMYUV/graph.json","events_json":"https://pith.science/api/pith-number/B6DGJSQ62XPXHNVLDS453EMYUV/events.json","paper":"https://pith.science/paper/B6DGJSQ6"},"agent_actions":{"view_html":"https://pith.science/pith/B6DGJSQ62XPXHNVLDS453EMYUV","download_json":"https://pith.science/pith/B6DGJSQ62XPXHNVLDS453EMYUV.json","view_paper":"https://pith.science/paper/B6DGJSQ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.10086&json=true","fetch_graph":"https://pith.science/api/pith-number/B6DGJSQ62XPXHNVLDS453EMYUV/graph.json","fetch_events":"https://pith.science/api/pith-number/B6DGJSQ62XPXHNVLDS453EMYUV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B6DGJSQ62XPXHNVLDS453EMYUV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B6DGJSQ62XPXHNVLDS453EMYUV/action/storage_attestation","attest_author":"https://pith.science/pith/B6DGJSQ62XPXHNVLDS453EMYUV/action/author_attestation","sign_citation":"https://pith.science/pith/B6DGJSQ62XPXHNVLDS453EMYUV/action/citation_signature","submit_replication":"https://pith.science/pith/B6DGJSQ62XPXHNVLDS453EMYUV/action/replication_record"}},"created_at":"2026-07-05T03:15:58.013864+00:00","updated_at":"2026-07-05T03:15:58.013864+00:00"}