{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VTS4FYGPL5HDKSOANCOC5C3PYD","short_pith_number":"pith:VTS4FYGP","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"},"canonical_sha256":"ace5c2e0cf5f4e3549c0689c2e8b6fc0c31af8791d9f9c7e955ea666a80aa92c","source":{"kind":"arxiv","id":"2605.14381","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14381","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14381v1","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14381","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"pith_short_12","alias_value":"VTS4FYGPL5HD","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"VTS4FYGPL5HDKSOA","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"VTS4FYGP","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VTS4FYGPL5HDKSOANCOC5C3PYD","target":"record","payload":{"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"},"canonical_sha256":"ace5c2e0cf5f4e3549c0689c2e8b6fc0c31af8791d9f9c7e955ea666a80aa92c","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"},"source_kind":"arxiv","source_id":"2605.14381","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O5+Jcz8eNGLONN5/P90dvrd9NOQSlSblwbQhEtwQJSSwzFqzLH7Axox22356lwQk6FqLvFH841XkgQBDx9JNAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T13:46:33.225908Z"},"content_sha256":"b76d141f4f17905e72d3eb4541b87970c05492badacc0d10bee8f5acc8ca0f1a","schema_version":"1.0","event_id":"sha256:b76d141f4f17905e72d3eb4541b87970c05492badacc0d10bee8f5acc8ca0f1a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VTS4FYGPL5HDKSOANCOC5C3PYD","target":"graph","payload":{"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"},"verdict_id":"518124b9-cf1e-4531-88a2-96abe160579a"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aJ5Ph8H6rjF30660uZa6VdUybGBaByBdGUCCwJZnIOaFG2rtizgFrJxi0vooSPgipL3nJg5NKKDGphYYfKQRBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T13:46:33.226536Z"},"content_sha256":"2e519ddd6d1092e0846e3bd8ed191aed811d94d3b397e74078dda349db02b59d","schema_version":"1.0","event_id":"sha256:2e519ddd6d1092e0846e3bd8ed191aed811d94d3b397e74078dda349db02b59d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VTS4FYGPL5HDKSOANCOC5C3PYD/bundle.json","state_url":"https://pith.science/pith/VTS4FYGPL5HDKSOANCOC5C3PYD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VTS4FYGPL5HDKSOANCOC5C3PYD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-27T13:46:33Z","links":{"resolver":"https://pith.science/pith/VTS4FYGPL5HDKSOANCOC5C3PYD","bundle":"https://pith.science/pith/VTS4FYGPL5HDKSOANCOC5C3PYD/bundle.json","state":"https://pith.science/pith/VTS4FYGPL5HDKSOANCOC5C3PYD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VTS4FYGPL5HDKSOANCOC5C3PYD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VTS4FYGPL5HDKSOANCOC5C3PYD","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":"e6dad8f25c97add073feca94bb5ff6baac0b8f85b79c684b69bb68ace65cf674","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T05:06:50Z","title_canon_sha256":"263d734e60d3ddbd1ba6b2d605a0e9370e07088b3965fa962d22dcc9127bb2e1"},"schema_version":"1.0","source":{"id":"2605.14381","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14381","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14381v1","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14381","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"pith_short_12","alias_value":"VTS4FYGPL5HD","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"VTS4FYGPL5HDKSOA","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"VTS4FYGP","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:2e519ddd6d1092e0846e3bd8ed191aed811d94d3b397e74078dda349db02b59d","target":"graph","created_at":"2026-05-17T23:39:07Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Evaluated against four mainstream LLMs, NodeSynth elicited failure rates up to five times higher than human-authored benchmarks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"NodeSynth generates evidence-anchored synthetic queries that trigger up to five times higher failure rates in mainstream LLMs than human-authored benchmarks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","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."}],"snapshot_sha256":"df512049aca8f432ed0f1018b7418ce36aeec7e48bf7331b6a38d7484e7c5fea"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"12ac72d2387adf47e73ac9813713fe539819fcecb01b2bccb590a11e487d1545"},"paper":{"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","authors_text":"Darlene Neal, Erin van Liemt, Jamila Smith-Loud, Kshitij Pancholi, Qazi Mamunur Rashid, Xuan Yang, Yanzhou Pan, Zhengzhe Yang","cross_cats":["cs.CL"],"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.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T05:06:50Z","title":"NodeSynth: Socially Aligned Synthetic Data for AI Evaluation"},"references":{"count":53,"internal_anchors":3,"resolved_work":53,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"On llms-driven synthetic data generation, curation, and evaluation: A survey","work_id":"d8efa201-fecf-4ca6-90f0-02640ce6452b","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Synthetic data in ai: Challenges, applications, and ethical implications.arXiv preprint arXiv:2401.01629, 2024","work_id":"3a0c03f2-d0f9-44ff-b974-336150c54e9c","year":2024},{"cited_arxiv_id":"2406.08464","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing","work_id":"4df6cdce-69a0-402e-ab53-59e5c10b8cae","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Self-instruct: Aligning language models with self-generated instruc- tions","work_id":"40d20eeb-4469-4548-b78d-d83166af6146","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Examining the expanding role of synthetic data throughout the ai development pipeline","work_id":"61800835-745c-4c41-b94c-42dda3b576ec","year":2025}],"snapshot_sha256":"080025d427f0b1bddbba18deb351013e2cae84fbd3aa4900a0534a031d69a915"},"source":{"id":"2605.14381","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T02:35:10.015065Z","id":"518124b9-cf1e-4531-88a2-96abe160579a","model_set":{"reader":"grok-4.3"},"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","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.","strongest_claim":"Evaluated against four mainstream LLMs, NodeSynth elicited failure rates up to five times higher than human-authored benchmarks.","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."}},"verdict_id":"518124b9-cf1e-4531-88a2-96abe160579a"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b76d141f4f17905e72d3eb4541b87970c05492badacc0d10bee8f5acc8ca0f1a","target":"record","created_at":"2026-05-17T23:39:07Z","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":"e6dad8f25c97add073feca94bb5ff6baac0b8f85b79c684b69bb68ace65cf674","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T05:06:50Z","title_canon_sha256":"263d734e60d3ddbd1ba6b2d605a0e9370e07088b3965fa962d22dcc9127bb2e1"},"schema_version":"1.0","source":{"id":"2605.14381","kind":"arxiv","version":1}},"canonical_sha256":"ace5c2e0cf5f4e3549c0689c2e8b6fc0c31af8791d9f9c7e955ea666a80aa92c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ace5c2e0cf5f4e3549c0689c2e8b6fc0c31af8791d9f9c7e955ea666a80aa92c","first_computed_at":"2026-05-17T23:39:07.722958Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:07.722958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vLFV4eENNA7ZtSW/kRV50ELFd9SIMXwBsFuzQbRc7Lw5DXlTaOfOmxdRnKCgrvhcmBfc+1AZSokHP8/dyjifCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:07.723676Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14381","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b76d141f4f17905e72d3eb4541b87970c05492badacc0d10bee8f5acc8ca0f1a","sha256:2e519ddd6d1092e0846e3bd8ed191aed811d94d3b397e74078dda349db02b59d"],"state_sha256":"8b1199006e20f1227b27aec6ef8a80cc186ddb82f9a56d72706822205fa8b156"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mSg5B5Qto3YNlaM/bsNkDS08zDhXxN9K5qu6fB/mdoLF6kXb5SWmJdSrxlnLvKvs0LOFRpgDgaPWjo/0NSzSCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T13:46:33.229451Z","bundle_sha256":"1a633ef20f39f0a28f639d8a7953317d8ce09fb9998a8068f64f265101b5adce"}}