{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VTS4FYGPL5HDKSOANCOC5C3PYD","short_pith_number":"pith:VTS4FYGP","schema_version":"1.0","canonical_sha256":"ace5c2e0cf5f4e3549c0689c2e8b6fc0c31af8791d9f9c7e955ea666a80aa92c","source":{"kind":"arxiv","id":"2605.14381","version":1},"attestation_state":"computed","paper":{"title":"NodeSynth: Socially Aligned Synthetic Data for AI Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"NodeSynth generates synthetic queries via a fine-tuned taxonomy generator that cause mainstream LLMs to fail at rates up to five times higher than human benchmarks.","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Darlene Neal, Erin van Liemt, Jamila Smith-Loud, Kshitij Pancholi, Qazi Mamunur Rashid, Xuan Yang, Yanzhou Pan, Zhengzhe Yang","submitted_at":"2026-05-14T05:06:50Z","abstract_excerpt":"Recent advancements in generative AI facilitate large-scale synthetic data generation for model evaluation. However, without targeted approaches, these datasets often lack the sociotechnical nuance required for sensitive domains. We introduce NodeSynth, an evidence-grounded methodology that generates socially relevant synthetic queries by leveraging a fine-tuned taxonomy generator (TaG) anchored in real-world evidence. Evaluated against four mainstream LLMs (e.g., Claude 4.5 Haiku), NodeSynth elicited failure rates up to five times higher than human-authored benchmarks. Ablation studies confir"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.14381","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T05:06:50Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"263d734e60d3ddbd1ba6b2d605a0e9370e07088b3965fa962d22dcc9127bb2e1","abstract_canon_sha256":"e6dad8f25c97add073feca94bb5ff6baac0b8f85b79c684b69bb68ace65cf674"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:07.723676Z","signature_b64":"vLFV4eENNA7ZtSW/kRV50ELFd9SIMXwBsFuzQbRc7Lw5DXlTaOfOmxdRnKCgrvhcmBfc+1AZSokHP8/dyjifCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ace5c2e0cf5f4e3549c0689c2e8b6fc0c31af8791d9f9c7e955ea666a80aa92c","last_reissued_at":"2026-05-17T23:39:07.722958Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:07.722958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NodeSynth: Socially Aligned Synthetic Data for AI Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"NodeSynth generates synthetic queries via a fine-tuned taxonomy generator that cause mainstream LLMs to fail at rates up to five times higher than human benchmarks.","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Darlene Neal, Erin van Liemt, Jamila Smith-Loud, Kshitij Pancholi, Qazi Mamunur Rashid, Xuan Yang, Yanzhou Pan, Zhengzhe Yang","submitted_at":"2026-05-14T05:06:50Z","abstract_excerpt":"Recent advancements in generative AI facilitate large-scale synthetic data generation for model evaluation. However, without targeted approaches, these datasets often lack the sociotechnical nuance required for sensitive domains. We introduce NodeSynth, an evidence-grounded methodology that generates socially relevant synthetic queries by leveraging a fine-tuned taxonomy generator (TaG) anchored in real-world evidence. Evaluated against four mainstream LLMs (e.g., Claude 4.5 Haiku), NodeSynth elicited failure rates up to five times higher than human-authored benchmarks. Ablation studies confir"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Evaluated against four mainstream LLMs, NodeSynth elicited failure rates up to five times higher than human-authored benchmarks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The synthetic queries produced by the fine-tuned TaG are representative of genuine sociotechnical risks without introducing new biases or artifacts that inflate failure rates.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"NodeSynth generates evidence-anchored synthetic queries that trigger up to five times higher failure rates in mainstream LLMs than human-authored benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"NodeSynth generates synthetic queries via a fine-tuned taxonomy generator that cause mainstream LLMs to fail at rates up to five times higher than human benchmarks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"df512049aca8f432ed0f1018b7418ce36aeec7e48bf7331b6a38d7484e7c5fea"},"source":{"id":"2605.14381","kind":"arxiv","version":1},"verdict":{"id":"518124b9-cf1e-4531-88a2-96abe160579a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:35:10.015065Z","strongest_claim":"Evaluated against four mainstream LLMs, NodeSynth elicited failure rates up to five times higher than human-authored benchmarks.","one_line_summary":"NodeSynth generates evidence-anchored synthetic queries that trigger up to five times higher failure rates in mainstream LLMs than human-authored benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The synthetic queries produced by the fine-tuned TaG are representative of genuine sociotechnical risks without introducing new biases or artifacts that inflate failure rates.","pith_extraction_headline":"NodeSynth generates synthetic queries via a fine-tuned taxonomy generator that cause mainstream LLMs to fail at rates up to five times higher than human benchmarks."},"references":{"count":53,"sample":[{"doi":"","year":2024,"title":"On llms-driven synthetic data generation, curation, and evaluation: A survey","work_id":"d8efa201-fecf-4ca6-90f0-02640ce6452b","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Synthetic data in ai: Challenges, applications, and ethical implications.arXiv preprint arXiv:2401.01629, 2024","work_id":"3a0c03f2-d0f9-44ff-b974-336150c54e9c","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing","work_id":"4df6cdce-69a0-402e-ab53-59e5c10b8cae","ref_index":3,"cited_arxiv_id":"2406.08464","is_internal_anchor":true},{"doi":"","year":2023,"title":"Self-instruct: Aligning language models with self-generated instruc- tions","work_id":"40d20eeb-4469-4548-b78d-d83166af6146","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Examining the expanding role of synthetic data throughout the ai development pipeline","work_id":"61800835-745c-4c41-b94c-42dda3b576ec","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":53,"snapshot_sha256":"080025d427f0b1bddbba18deb351013e2cae84fbd3aa4900a0534a031d69a915","internal_anchors":3},"formal_canon":{"evidence_count":2,"snapshot_sha256":"12ac72d2387adf47e73ac9813713fe539819fcecb01b2bccb590a11e487d1545"},"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":"2605.14381","created_at":"2026-05-17T23:39:07.723052+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14381v1","created_at":"2026-05-17T23:39:07.723052+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14381","created_at":"2026-05-17T23:39:07.723052+00:00"},{"alias_kind":"pith_short_12","alias_value":"VTS4FYGPL5HD","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"VTS4FYGPL5HDKSOA","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"VTS4FYGP","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VTS4FYGPL5HDKSOANCOC5C3PYD","json":"https://pith.science/pith/VTS4FYGPL5HDKSOANCOC5C3PYD.json","graph_json":"https://pith.science/api/pith-number/VTS4FYGPL5HDKSOANCOC5C3PYD/graph.json","events_json":"https://pith.science/api/pith-number/VTS4FYGPL5HDKSOANCOC5C3PYD/events.json","paper":"https://pith.science/paper/VTS4FYGP"},"agent_actions":{"view_html":"https://pith.science/pith/VTS4FYGPL5HDKSOANCOC5C3PYD","download_json":"https://pith.science/pith/VTS4FYGPL5HDKSOANCOC5C3PYD.json","view_paper":"https://pith.science/paper/VTS4FYGP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14381&json=true","fetch_graph":"https://pith.science/api/pith-number/VTS4FYGPL5HDKSOANCOC5C3PYD/graph.json","fetch_events":"https://pith.science/api/pith-number/VTS4FYGPL5HDKSOANCOC5C3PYD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VTS4FYGPL5HDKSOANCOC5C3PYD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VTS4FYGPL5HDKSOANCOC5C3PYD/action/storage_attestation","attest_author":"https://pith.science/pith/VTS4FYGPL5HDKSOANCOC5C3PYD/action/author_attestation","sign_citation":"https://pith.science/pith/VTS4FYGPL5HDKSOANCOC5C3PYD/action/citation_signature","submit_replication":"https://pith.science/pith/VTS4FYGPL5HDKSOANCOC5C3PYD/action/replication_record"}},"created_at":"2026-05-17T23:39:07.723052+00:00","updated_at":"2026-05-17T23:39:07.723052+00:00"}