{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JAQKJF4G5SVFVQV2LR3DZKKHDI","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":"6dd08fb9bdcbd76ac5d5d4a30463c602e07b5c49da0a678a4a11a2679fe9e393","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-22T11:01:41Z","title_canon_sha256":"7fa9134de93ca46f57cd54b2f5c7ce462a1e636dbb48e0b91f3414442a44461d"},"schema_version":"1.0","source":{"id":"2506.17989","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17989","created_at":"2026-07-05T11:25:26Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17989v1","created_at":"2026-07-05T11:25:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17989","created_at":"2026-07-05T11:25:26Z"},{"alias_kind":"pith_short_12","alias_value":"JAQKJF4G5SVF","created_at":"2026-07-05T11:25:26Z"},{"alias_kind":"pith_short_16","alias_value":"JAQKJF4G5SVFVQV2","created_at":"2026-07-05T11:25:26Z"},{"alias_kind":"pith_short_8","alias_value":"JAQKJF4G","created_at":"2026-07-05T11:25:26Z"}],"graph_snapshots":[{"event_id":"sha256:d9e78416aa779460034e26abf774e036aa875b53fa39b7991da25cabc9de4ac3","target":"graph","created_at":"2026-07-05T11:25:26Z","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/2506.17989/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training models on uncurated Text Embeddings (TEs) derived from raw tabular data can lead to a severe failure mode known as model collapse, where predictions converge to a single class regardless of input. By comparing models trained with identical hyper-parameter configurations on both raw tabular data and their TE-derived counterparts, we find that collapse is a consistent failure mode in the latter setting. We introduce a set of metrics that capture the extent of model collapse, offering a new perspective on TE quality as a proxy for data curation. Our results reveal that TE alone does not ","authors_text":"Lucas Mattioli, Martin Gonzalez, Sabrina Chaouche, Youness Ait Hadichou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-22T11:01:41Z","title":"Data Curation Matters: Model Collapse and Spurious Shift Performance Prediction from Training on Uncurated Text Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17989","kind":"arxiv","version":1},"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:cc52568381dda31680279854a30b07893c65e9b4d1216ba02df2446b50b1adfe","target":"record","created_at":"2026-07-05T11:25:26Z","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":"6dd08fb9bdcbd76ac5d5d4a30463c602e07b5c49da0a678a4a11a2679fe9e393","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-22T11:01:41Z","title_canon_sha256":"7fa9134de93ca46f57cd54b2f5c7ce462a1e636dbb48e0b91f3414442a44461d"},"schema_version":"1.0","source":{"id":"2506.17989","kind":"arxiv","version":1}},"canonical_sha256":"4820a49786ecaa5ac2ba5c763ca9471a27248c600862d4b459ebf16dc8c42ed4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4820a49786ecaa5ac2ba5c763ca9471a27248c600862d4b459ebf16dc8c42ed4","first_computed_at":"2026-07-05T11:25:26.658494Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:26.658494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GykT9O0gx91bpxtnXMu2rWaAKbIIuzlZmpZ9eDGw6TMiHGrYhthLJ8dmSx3fnjBwg066fHr2IMuCXBo9728OBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:26.658976Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.17989","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc52568381dda31680279854a30b07893c65e9b4d1216ba02df2446b50b1adfe","sha256:d9e78416aa779460034e26abf774e036aa875b53fa39b7991da25cabc9de4ac3"],"state_sha256":"c680e0ea2822a09095d4a41a9015b7013505cbfbdf215a05dd2a8af076071d55"}