{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Y5EOGTVRIKJLBM3W63GFJQUCH4","short_pith_number":"pith:Y5EOGTVR","schema_version":"1.0","canonical_sha256":"c748e34eb14292b0b376f6cc54c2823f221bae71f4b3b748f4521a5a15d2410c","source":{"kind":"arxiv","id":"2606.00571","version":1},"attestation_state":"computed","paper":{"title":"On the Difficulty of Learning a Meta-network for Training Data Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Boyang Albert Li, Junqi Zhao, Zilin Du","submitted_at":"2026-05-30T06:47:24Z","abstract_excerpt":"Synthetic data are increasingly used to train neural networks, yet distributional mismatch with real data limits their effectiveness when used indiscriminately. A common strategy is to learn data weights via bi-level optimization, which we refer to as Meta-learning for Training-data Selection (MTS). Interestingly, in practice, MTS often performs below expectation. We identify two obstacles in properly training MTS: a poor gradient signal-to-noise ratio (GSNR), which causes optimization difficulties, and lack of informative features that correlates with data quality. We present a mathematical a"},"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":"2606.00571","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-30T06:47:24Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"02b9febffada03d08a2524de5ce0d23deead9d3a4ef0184132e98771ef54dcc2","abstract_canon_sha256":"ddb5099e1cb1404d42f0e56982b321a5786444207399834dc676c224931d91cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:58.607406Z","signature_b64":"5g46kwde5Uppg8CPrve90HXgfH0ght91Zskg9kK7RYgVcbmqsyWPYV50xF0Lx/fgIRg07cHhJ2uRR6GDdArmCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c748e34eb14292b0b376f6cc54c2823f221bae71f4b3b748f4521a5a15d2410c","last_reissued_at":"2026-06-02T01:03:58.606942Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:58.606942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Difficulty of Learning a Meta-network for Training Data Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Boyang Albert Li, Junqi Zhao, Zilin Du","submitted_at":"2026-05-30T06:47:24Z","abstract_excerpt":"Synthetic data are increasingly used to train neural networks, yet distributional mismatch with real data limits their effectiveness when used indiscriminately. A common strategy is to learn data weights via bi-level optimization, which we refer to as Meta-learning for Training-data Selection (MTS). Interestingly, in practice, MTS often performs below expectation. We identify two obstacles in properly training MTS: a poor gradient signal-to-noise ratio (GSNR), which causes optimization difficulties, and lack of informative features that correlates with data quality. We present a mathematical a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00571","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/2606.00571/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":"2606.00571","created_at":"2026-06-02T01:03:58.606997+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00571v1","created_at":"2026-06-02T01:03:58.606997+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00571","created_at":"2026-06-02T01:03:58.606997+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y5EOGTVRIKJL","created_at":"2026-06-02T01:03:58.606997+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y5EOGTVRIKJLBM3W","created_at":"2026-06-02T01:03:58.606997+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y5EOGTVR","created_at":"2026-06-02T01:03:58.606997+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/Y5EOGTVRIKJLBM3W63GFJQUCH4","json":"https://pith.science/pith/Y5EOGTVRIKJLBM3W63GFJQUCH4.json","graph_json":"https://pith.science/api/pith-number/Y5EOGTVRIKJLBM3W63GFJQUCH4/graph.json","events_json":"https://pith.science/api/pith-number/Y5EOGTVRIKJLBM3W63GFJQUCH4/events.json","paper":"https://pith.science/paper/Y5EOGTVR"},"agent_actions":{"view_html":"https://pith.science/pith/Y5EOGTVRIKJLBM3W63GFJQUCH4","download_json":"https://pith.science/pith/Y5EOGTVRIKJLBM3W63GFJQUCH4.json","view_paper":"https://pith.science/paper/Y5EOGTVR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00571&json=true","fetch_graph":"https://pith.science/api/pith-number/Y5EOGTVRIKJLBM3W63GFJQUCH4/graph.json","fetch_events":"https://pith.science/api/pith-number/Y5EOGTVRIKJLBM3W63GFJQUCH4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y5EOGTVRIKJLBM3W63GFJQUCH4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y5EOGTVRIKJLBM3W63GFJQUCH4/action/storage_attestation","attest_author":"https://pith.science/pith/Y5EOGTVRIKJLBM3W63GFJQUCH4/action/author_attestation","sign_citation":"https://pith.science/pith/Y5EOGTVRIKJLBM3W63GFJQUCH4/action/citation_signature","submit_replication":"https://pith.science/pith/Y5EOGTVRIKJLBM3W63GFJQUCH4/action/replication_record"}},"created_at":"2026-06-02T01:03:58.606997+00:00","updated_at":"2026-06-02T01:03:58.606997+00:00"}