{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4QCTFJUN2NGILRTFR5UPUF6LTN","short_pith_number":"pith:4QCTFJUN","schema_version":"1.0","canonical_sha256":"e40532a68dd34c85c6658f68fa17cb9b57c954d967c5e9085dd7e79069b25999","source":{"kind":"arxiv","id":"2403.06789","version":1},"attestation_state":"computed","paper":{"title":"SPLADE-v3: New baselines for SPLADE","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Carlos Lassance, Herv\\'e D\\'ejean, St\\'ephane Clinchant, Thibault Formal","submitted_at":"2024-03-11T15:04:55Z","abstract_excerpt":"A companion to the release of the latest version of the SPLADE library. We describe changes to the training structure and present our latest series of models -- SPLADE-v3. We compare this new version to BM25, SPLADE++, as well as re-rankers, and showcase its effectiveness via a meta-analysis over more than 40 query sets. SPLADE-v3 further pushes the limit of SPLADE models: it is statistically significantly more effective than both BM25 and SPLADE++, while comparing well to cross-encoder re-rankers. Specifically, it gets more than 40 MRR@10 on the MS MARCO dev set, and improves by 2% the out-of"},"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":"2403.06789","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-03-11T15:04:55Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f527a984c2487185836700ed86433d33dc81403bbd390fcd7efc4cc9d31db71b","abstract_canon_sha256":"1f4bff2f05c1b281fce36946ea602be5d5903325517b4c89d869f88765c60867"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:42.692907Z","signature_b64":"YdTgBnQPBoX3arSN1YrmijvWDLN5+J4o9fBnfxaW5zRRgbVnAWk1xtnuOrWr2jUEiVpfOdeOfBJC2sKT7Vc0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e40532a68dd34c85c6658f68fa17cb9b57c954d967c5e9085dd7e79069b25999","last_reissued_at":"2026-07-05T07:54:42.692442Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:42.692442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPLADE-v3: New baselines for SPLADE","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Carlos Lassance, Herv\\'e D\\'ejean, St\\'ephane Clinchant, Thibault Formal","submitted_at":"2024-03-11T15:04:55Z","abstract_excerpt":"A companion to the release of the latest version of the SPLADE library. We describe changes to the training structure and present our latest series of models -- SPLADE-v3. We compare this new version to BM25, SPLADE++, as well as re-rankers, and showcase its effectiveness via a meta-analysis over more than 40 query sets. SPLADE-v3 further pushes the limit of SPLADE models: it is statistically significantly more effective than both BM25 and SPLADE++, while comparing well to cross-encoder re-rankers. Specifically, it gets more than 40 MRR@10 on the MS MARCO dev set, and improves by 2% the out-of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06789","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/2403.06789/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":"2403.06789","created_at":"2026-07-05T07:54:42.692499+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.06789v1","created_at":"2026-07-05T07:54:42.692499+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06789","created_at":"2026-07-05T07:54:42.692499+00:00"},{"alias_kind":"pith_short_12","alias_value":"4QCTFJUN2NGI","created_at":"2026-07-05T07:54:42.692499+00:00"},{"alias_kind":"pith_short_16","alias_value":"4QCTFJUN2NGILRTF","created_at":"2026-07-05T07:54:42.692499+00:00"},{"alias_kind":"pith_short_8","alias_value":"4QCTFJUN","created_at":"2026-07-05T07:54:42.692499+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"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":29,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26441","citing_title":"GPUSparse: GPU-Accelerated Learned Sparse Retrieval with Parallel Inverted Indices","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22778","citing_title":"HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions","ref_index":101,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18811","citing_title":"Rescaling MLM-Head for Neural Sparse Retrieval","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13550","citing_title":"Uncertainty-Aware Hybrid Retrieval for Long-Document RAG","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05568","citing_title":"ColBERTSaR: Sparsified ColBERT Index via Product Quantization","ref_index":14,"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":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31692","citing_title":"Overview of the TalentCLEF 2026: Skill and Job Title Intelligence for Human Capital Management","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27559","citing_title":"A Sensitivity-Aware Test Collection for Search Among Personal Information","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2404.10981","citing_title":"A Survey on Retrieval-Augmented Text Generation for Large Language Models","ref_index":82,"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":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19628","citing_title":"Understanding Wacky Weights: A Dissection of SPLADE's Learned Term Importance","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2509.12539","citing_title":"LEAF: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representations","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2603.08819","citing_title":"Beyond Relevance: On the Relationship Between Retrieval and RAG Information Coverage","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28142","citing_title":"Efficient Multivector Retrieval with Token-Aware Clustering and Hierarchical Indexing","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26483","citing_title":"Efficient Listwise Reranking with Compressed Document Representations","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03824","citing_title":"Reproducing Complex Set-Compositional Information Retrieval","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22722","citing_title":"Aligning Dense Retrievers with LLM Utility via Distillation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12047","citing_title":"Empirical Evaluation of PDF Parsing and Chunking for Financial Question Answering with RAG","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05766","citing_title":"The LLM Effect on IR Benchmarks: A Meta-Analysis of Effectiveness, Baselines, and Contamination","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15591","citing_title":"BioHiCL: Hierarchical Multi-Label Contrastive Learning for Biomedical Retrieval with MeSH Labels","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4QCTFJUN2NGILRTFR5UPUF6LTN","json":"https://pith.science/pith/4QCTFJUN2NGILRTFR5UPUF6LTN.json","graph_json":"https://pith.science/api/pith-number/4QCTFJUN2NGILRTFR5UPUF6LTN/graph.json","events_json":"https://pith.science/api/pith-number/4QCTFJUN2NGILRTFR5UPUF6LTN/events.json","paper":"https://pith.science/paper/4QCTFJUN"},"agent_actions":{"view_html":"https://pith.science/pith/4QCTFJUN2NGILRTFR5UPUF6LTN","download_json":"https://pith.science/pith/4QCTFJUN2NGILRTFR5UPUF6LTN.json","view_paper":"https://pith.science/paper/4QCTFJUN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.06789&json=true","fetch_graph":"https://pith.science/api/pith-number/4QCTFJUN2NGILRTFR5UPUF6LTN/graph.json","fetch_events":"https://pith.science/api/pith-number/4QCTFJUN2NGILRTFR5UPUF6LTN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4QCTFJUN2NGILRTFR5UPUF6LTN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4QCTFJUN2NGILRTFR5UPUF6LTN/action/storage_attestation","attest_author":"https://pith.science/pith/4QCTFJUN2NGILRTFR5UPUF6LTN/action/author_attestation","sign_citation":"https://pith.science/pith/4QCTFJUN2NGILRTFR5UPUF6LTN/action/citation_signature","submit_replication":"https://pith.science/pith/4QCTFJUN2NGILRTFR5UPUF6LTN/action/replication_record"}},"created_at":"2026-07-05T07:54:42.692499+00:00","updated_at":"2026-07-05T07:54:42.692499+00:00"}