{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EVQ4XBCU23LVFG4ID5CFA4PTZW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8df17d2865d226056852e0105ebd292550d2305c3377f0dddc0e71b7a403532c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-11-14T07:51:59Z","title_canon_sha256":"19c743577b23c138682ab01906f609f70d868ed15149c1d8b4f0cd02afecd24c"},"schema_version":"1.0","source":{"id":"2511.11041","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.11041","created_at":"2026-06-09T01:04:39Z"},{"alias_kind":"arxiv_version","alias_value":"2511.11041v2","created_at":"2026-06-09T01:04:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.11041","created_at":"2026-06-09T01:04:39Z"},{"alias_kind":"pith_short_12","alias_value":"EVQ4XBCU23LV","created_at":"2026-06-09T01:04:39Z"},{"alias_kind":"pith_short_16","alias_value":"EVQ4XBCU23LVFG4I","created_at":"2026-06-09T01:04:39Z"},{"alias_kind":"pith_short_8","alias_value":"EVQ4XBCU","created_at":"2026-06-09T01:04:39Z"}],"graph_snapshots":[{"event_id":"sha256:f5f8febf5d0aac3a829955867058777571b3d371dc720d55de9646c13d5e4cfc","target":"graph","created_at":"2026-06-09T01:04:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2511.11041/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We find that current sentence-embedding models produce outputs with a consistent bias: every embedding $e$ decomposes as $\\tilde e + \\mu$, where the mean $\\mu$ is near-identical across all sentences. We study two training-free corrections -- subtracting $\\mu$ directly (R1), or projecting each embedding off the mean direction (R2) -- and show, via a first-order error-propagation argument, that R2 cancels the parallel component of mean-estimation error that R1 retains. Across 38 models on the Massive Multilingual Text Embedding Benchmark (MMTEB)~\\citep{MMTEB}, R2 yields consistent classification","authors_text":"Haoyu Liang, Xingyu Ren, Youran Sun","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-11-14T07:51:59Z","title":"Correcting Mean Bias in Text Embeddings: A Refined Renormalization with Training-Free Improvements on MMTEB"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.11041","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:489d501313eb86f69d591db7b4480d45d83308a09bc5d03d4c9e5bf340022b18","target":"record","created_at":"2026-06-09T01:04:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8df17d2865d226056852e0105ebd292550d2305c3377f0dddc0e71b7a403532c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-11-14T07:51:59Z","title_canon_sha256":"19c743577b23c138682ab01906f609f70d868ed15149c1d8b4f0cd02afecd24c"},"schema_version":"1.0","source":{"id":"2511.11041","kind":"arxiv","version":2}},"canonical_sha256":"2561cb8454d6d7529b881f445071f3cdb92f14bf8dfe3ff5fc8f2ab89a04c899","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2561cb8454d6d7529b881f445071f3cdb92f14bf8dfe3ff5fc8f2ab89a04c899","first_computed_at":"2026-06-09T01:04:39.990146Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:04:39.990146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VltkeVSeBDjgjsTUjNPlrOKDpbe4K23YLBplOf+vi2pQCRdXFiWbuoKjFX5E4XTxb3LD3DJld+wqcfxwoh5MDA==","signature_status":"signed_v1","signed_at":"2026-06-09T01:04:39.990625Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.11041","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:489d501313eb86f69d591db7b4480d45d83308a09bc5d03d4c9e5bf340022b18","sha256:f5f8febf5d0aac3a829955867058777571b3d371dc720d55de9646c13d5e4cfc"],"state_sha256":"7c4b8ac4df7a5053472ead7be4a0563433339982624d00ac8ea56018cf5200b9"}