{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V437OCOSNPDVCWTT2UZFZ4ESKA","short_pith_number":"pith:V437OCOS","schema_version":"1.0","canonical_sha256":"af37f709d26bc7515a73d5325cf09250387154ca220bcd139f2ad5e7553c5c0b","source":{"kind":"arxiv","id":"2402.14776","version":3},"attestation_state":"computed","paper":{"title":"2D Matryoshka Sentence Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Haoran Xie, Jing Li, Qing Li, Xianming Li, Zongxi Li","submitted_at":"2024-02-22T18:35:05Z","abstract_excerpt":"Common approaches rely on fixed-length embedding vectors from language models as sentence embeddings for downstream tasks such as semantic textual similarity (STS). Such methods are limited in their flexibility due to unknown computational constraints and budgets across various applications. Matryoshka Representation Learning (MRL) \\cite{aditya2022matryoshka} encodes information at finer granularities, i.e., with lower embedding dimensions, to adaptively accommodate \\emph{ad hoc} tasks. Similar accuracy can be achieved with a smaller embedding size, leading to speedups in downstream tasks. Des"},"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":"2402.14776","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T18:35:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b41270f8086792a19eeaab47507bfe2c86e3a6e29e361c8b211f6a7522b0ad1f","abstract_canon_sha256":"760fc2286d78390ba11adc483bc472219af180f2ce754bcba1c0de752f52efd6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:23.148112Z","signature_b64":"QH4JlrKm/3Y0YEYZnuyKA2q3D+dTA5wo88P6C/dzZ9xaUka27Hi6RhulQEEGoVL5NLzKiC63EiH2DQbZyOLvCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af37f709d26bc7515a73d5325cf09250387154ca220bcd139f2ad5e7553c5c0b","last_reissued_at":"2026-07-05T09:42:23.147647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:23.147647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"2D Matryoshka Sentence Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Haoran Xie, Jing Li, Qing Li, Xianming Li, Zongxi Li","submitted_at":"2024-02-22T18:35:05Z","abstract_excerpt":"Common approaches rely on fixed-length embedding vectors from language models as sentence embeddings for downstream tasks such as semantic textual similarity (STS). Such methods are limited in their flexibility due to unknown computational constraints and budgets across various applications. Matryoshka Representation Learning (MRL) \\cite{aditya2022matryoshka} encodes information at finer granularities, i.e., with lower embedding dimensions, to adaptively accommodate \\emph{ad hoc} tasks. Similar accuracy can be achieved with a smaller embedding size, leading to speedups in downstream tasks. Des"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14776","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/2402.14776/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":"2402.14776","created_at":"2026-07-05T09:42:23.147706+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.14776v3","created_at":"2026-07-05T09:42:23.147706+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14776","created_at":"2026-07-05T09:42:23.147706+00:00"},{"alias_kind":"pith_short_12","alias_value":"V437OCOSNPDV","created_at":"2026-07-05T09:42:23.147706+00:00"},{"alias_kind":"pith_short_16","alias_value":"V437OCOSNPDVCWTT","created_at":"2026-07-05T09:42:23.147706+00:00"},{"alias_kind":"pith_short_8","alias_value":"V437OCOS","created_at":"2026-07-05T09:42:23.147706+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07654","citing_title":"MM-Matryoshka: Towards Budget-Elastic Visual Document Retrieval via a 2D Multimodal Matryoshka Training Framework","ref_index":76,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V437OCOSNPDVCWTT2UZFZ4ESKA","json":"https://pith.science/pith/V437OCOSNPDVCWTT2UZFZ4ESKA.json","graph_json":"https://pith.science/api/pith-number/V437OCOSNPDVCWTT2UZFZ4ESKA/graph.json","events_json":"https://pith.science/api/pith-number/V437OCOSNPDVCWTT2UZFZ4ESKA/events.json","paper":"https://pith.science/paper/V437OCOS"},"agent_actions":{"view_html":"https://pith.science/pith/V437OCOSNPDVCWTT2UZFZ4ESKA","download_json":"https://pith.science/pith/V437OCOSNPDVCWTT2UZFZ4ESKA.json","view_paper":"https://pith.science/paper/V437OCOS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.14776&json=true","fetch_graph":"https://pith.science/api/pith-number/V437OCOSNPDVCWTT2UZFZ4ESKA/graph.json","fetch_events":"https://pith.science/api/pith-number/V437OCOSNPDVCWTT2UZFZ4ESKA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V437OCOSNPDVCWTT2UZFZ4ESKA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V437OCOSNPDVCWTT2UZFZ4ESKA/action/storage_attestation","attest_author":"https://pith.science/pith/V437OCOSNPDVCWTT2UZFZ4ESKA/action/author_attestation","sign_citation":"https://pith.science/pith/V437OCOSNPDVCWTT2UZFZ4ESKA/action/citation_signature","submit_replication":"https://pith.science/pith/V437OCOSNPDVCWTT2UZFZ4ESKA/action/replication_record"}},"created_at":"2026-07-05T09:42:23.147706+00:00","updated_at":"2026-07-05T09:42:23.147706+00:00"}