{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BS62WIYD43W2U5UCJ5XFVXVVIR","short_pith_number":"pith:BS62WIYD","schema_version":"1.0","canonical_sha256":"0cbdab2303e6edaa76824f6e5adeb5444ff2ef58ab1ef80e9e59e947bfe8f434","source":{"kind":"arxiv","id":"2509.06184","version":1},"attestation_state":"computed","paper":{"title":"Understanding the Influence of Synthetic Data for Text Embedders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aditi Raghunathan, Jacob Mitchell Springer, Marius Mosbach, Siva Reddy, Vaibhav Adlakha","submitted_at":"2025-09-07T19:28:52Z","abstract_excerpt":"Recent progress in developing general purpose text embedders has been driven by training on ever-growing corpora of synthetic LLM-generated data. Nonetheless, no publicly available synthetic dataset exists, posing a barrier to studying its role for generalization. To address this issue, we first reproduce and publicly release the synthetic data proposed by Wang et al. (Mistral-E5). Our synthetic data is high quality and leads to consistent improvements in performance. Next, we critically examine where exactly synthetic data improves model generalization. Our analysis reveals that benefits from"},"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":"2509.06184","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-07T19:28:52Z","cross_cats_sorted":[],"title_canon_sha256":"542711450bf6625dd653cbb2e55eaa569dcced6467da704b4e921898023cecc1","abstract_canon_sha256":"983e3a81c6ceeb83ecfd71bd3dee2550b6e7df580468355a5484bf31a7e7df9b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:31.248165Z","signature_b64":"Fd0tb3IqJiWeaFwh0FuUHDh2X1v+VYyZBApz79WkRGEjlwZ8LqbvqZVoFeNk3G07SzftIAo+pyYBI7ogRwoYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0cbdab2303e6edaa76824f6e5adeb5444ff2ef58ab1ef80e9e59e947bfe8f434","last_reissued_at":"2026-07-05T12:06:31.247633Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:31.247633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding the Influence of Synthetic Data for Text Embedders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aditi Raghunathan, Jacob Mitchell Springer, Marius Mosbach, Siva Reddy, Vaibhav Adlakha","submitted_at":"2025-09-07T19:28:52Z","abstract_excerpt":"Recent progress in developing general purpose text embedders has been driven by training on ever-growing corpora of synthetic LLM-generated data. Nonetheless, no publicly available synthetic dataset exists, posing a barrier to studying its role for generalization. To address this issue, we first reproduce and publicly release the synthetic data proposed by Wang et al. (Mistral-E5). Our synthetic data is high quality and leads to consistent improvements in performance. Next, we critically examine where exactly synthetic data improves model generalization. Our analysis reveals that benefits from"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06184","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/2509.06184/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":"2509.06184","created_at":"2026-07-05T12:06:31.247686+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.06184v1","created_at":"2026-07-05T12:06:31.247686+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06184","created_at":"2026-07-05T12:06:31.247686+00:00"},{"alias_kind":"pith_short_12","alias_value":"BS62WIYD43W2","created_at":"2026-07-05T12:06:31.247686+00:00"},{"alias_kind":"pith_short_16","alias_value":"BS62WIYD43W2U5UC","created_at":"2026-07-05T12:06:31.247686+00:00"},{"alias_kind":"pith_short_8","alias_value":"BS62WIYD","created_at":"2026-07-05T12:06:31.247686+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BS62WIYD43W2U5UCJ5XFVXVVIR","json":"https://pith.science/pith/BS62WIYD43W2U5UCJ5XFVXVVIR.json","graph_json":"https://pith.science/api/pith-number/BS62WIYD43W2U5UCJ5XFVXVVIR/graph.json","events_json":"https://pith.science/api/pith-number/BS62WIYD43W2U5UCJ5XFVXVVIR/events.json","paper":"https://pith.science/paper/BS62WIYD"},"agent_actions":{"view_html":"https://pith.science/pith/BS62WIYD43W2U5UCJ5XFVXVVIR","download_json":"https://pith.science/pith/BS62WIYD43W2U5UCJ5XFVXVVIR.json","view_paper":"https://pith.science/paper/BS62WIYD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.06184&json=true","fetch_graph":"https://pith.science/api/pith-number/BS62WIYD43W2U5UCJ5XFVXVVIR/graph.json","fetch_events":"https://pith.science/api/pith-number/BS62WIYD43W2U5UCJ5XFVXVVIR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BS62WIYD43W2U5UCJ5XFVXVVIR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BS62WIYD43W2U5UCJ5XFVXVVIR/action/storage_attestation","attest_author":"https://pith.science/pith/BS62WIYD43W2U5UCJ5XFVXVVIR/action/author_attestation","sign_citation":"https://pith.science/pith/BS62WIYD43W2U5UCJ5XFVXVVIR/action/citation_signature","submit_replication":"https://pith.science/pith/BS62WIYD43W2U5UCJ5XFVXVVIR/action/replication_record"}},"created_at":"2026-07-05T12:06:31.247686+00:00","updated_at":"2026-07-05T12:06:31.247686+00:00"}