{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CQSHHOBEVPUZNKBVGNTSMEWSPQ","short_pith_number":"pith:CQSHHOBE","canonical_record":{"source":{"id":"2606.20400","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-18T15:53:22Z","cross_cats_sorted":[],"title_canon_sha256":"b06f42a8fe9cf3239adfdac7c760ed877ca4ff88ab61a6e1d280497013ccdea9","abstract_canon_sha256":"35ac4a30e1560084bcff5c640d278cc23f1e8dda04c6bdb2e855a00a23316960"},"schema_version":"1.0"},"canonical_sha256":"142473b824abe996a83533672612d27c210940313f16fcc8f7836eadce8a23df","source":{"kind":"arxiv","id":"2606.20400","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.20400","created_at":"2026-06-19T16:13:11Z"},{"alias_kind":"arxiv_version","alias_value":"2606.20400v1","created_at":"2026-06-19T16:13:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20400","created_at":"2026-06-19T16:13:11Z"},{"alias_kind":"pith_short_12","alias_value":"CQSHHOBEVPUZ","created_at":"2026-06-19T16:13:11Z"},{"alias_kind":"pith_short_16","alias_value":"CQSHHOBEVPUZNKBV","created_at":"2026-06-19T16:13:11Z"},{"alias_kind":"pith_short_8","alias_value":"CQSHHOBE","created_at":"2026-06-19T16:13:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CQSHHOBEVPUZNKBVGNTSMEWSPQ","target":"record","payload":{"canonical_record":{"source":{"id":"2606.20400","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-18T15:53:22Z","cross_cats_sorted":[],"title_canon_sha256":"b06f42a8fe9cf3239adfdac7c760ed877ca4ff88ab61a6e1d280497013ccdea9","abstract_canon_sha256":"35ac4a30e1560084bcff5c640d278cc23f1e8dda04c6bdb2e855a00a23316960"},"schema_version":"1.0"},"canonical_sha256":"142473b824abe996a83533672612d27c210940313f16fcc8f7836eadce8a23df","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:13:11.621690Z","signature_b64":"I5qwxdT1ZolUmtN+KF/PMBfQplscOHmRaLlzdzYWx7lCZSfZJFelcPYFhRhIcWuII6WdLCwP86RKgORbnG+cBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"142473b824abe996a83533672612d27c210940313f16fcc8f7836eadce8a23df","last_reissued_at":"2026-06-19T16:13:11.621287Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:13:11.621287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.20400","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":"2026-06-19T16:13:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oVdv9+6x47npb+Fo8AYG8WFOorE+ZuEU4ioIWWx0kOKtqw2N6mEHBAHBPnx9M/g1dPjRsPsTSE064iTZA8PPBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T06:03:03.558963Z"},"content_sha256":"b033f0b060b6ca53a602549f8b7f7881e13687c17858e16646d39136c301d6e0","schema_version":"1.0","event_id":"sha256:b033f0b060b6ca53a602549f8b7f7881e13687c17858e16646d39136c301d6e0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CQSHHOBEVPUZNKBVGNTSMEWSPQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Significance of Style Diversity in Annotation-Free Synthetic Data Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Mohammad Aliannejadi, Omar Essam, Zahra Abbasiantaeb, Zeno Belligoli","submitted_at":"2026-06-18T15:53:22Z","abstract_excerpt":"Generating high-utility synthetic data for intent classification typically requires human-annotated seed data, which is often unavailable in fast-paced industrial settings. In this paper, we propose a framework for synthetic dialogue generation that works entirely without human-annotated data, relying solely on intent definitions. Our proposed dialogue generation framework utilizes two different types of topic and style attributes to improve data diversity. Also, we propose two novel post-hoc stylization models called Univ and Exam to transform synthetic LLM-generated utterances into more vari"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20400","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/2606.20400/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-19T16:13:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x8jAuRpQmUDbKabH17s6zT+6H832suHtUVB3nhga67HXgb0cgTG8/q+VjPw80etic3t/H4DdS8QNwfqB+BM3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T06:03:03.559342Z"},"content_sha256":"056ea95da6acb733021c012151a56b8eaa3279f95712904f9c155d62bdb2d432","schema_version":"1.0","event_id":"sha256:056ea95da6acb733021c012151a56b8eaa3279f95712904f9c155d62bdb2d432"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CQSHHOBEVPUZNKBVGNTSMEWSPQ/bundle.json","state_url":"https://pith.science/pith/CQSHHOBEVPUZNKBVGNTSMEWSPQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CQSHHOBEVPUZNKBVGNTSMEWSPQ/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":"2026-06-28T06:03:03Z","links":{"resolver":"https://pith.science/pith/CQSHHOBEVPUZNKBVGNTSMEWSPQ","bundle":"https://pith.science/pith/CQSHHOBEVPUZNKBVGNTSMEWSPQ/bundle.json","state":"https://pith.science/pith/CQSHHOBEVPUZNKBVGNTSMEWSPQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CQSHHOBEVPUZNKBVGNTSMEWSPQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CQSHHOBEVPUZNKBVGNTSMEWSPQ","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":"35ac4a30e1560084bcff5c640d278cc23f1e8dda04c6bdb2e855a00a23316960","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-18T15:53:22Z","title_canon_sha256":"b06f42a8fe9cf3239adfdac7c760ed877ca4ff88ab61a6e1d280497013ccdea9"},"schema_version":"1.0","source":{"id":"2606.20400","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.20400","created_at":"2026-06-19T16:13:11Z"},{"alias_kind":"arxiv_version","alias_value":"2606.20400v1","created_at":"2026-06-19T16:13:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20400","created_at":"2026-06-19T16:13:11Z"},{"alias_kind":"pith_short_12","alias_value":"CQSHHOBEVPUZ","created_at":"2026-06-19T16:13:11Z"},{"alias_kind":"pith_short_16","alias_value":"CQSHHOBEVPUZNKBV","created_at":"2026-06-19T16:13:11Z"},{"alias_kind":"pith_short_8","alias_value":"CQSHHOBE","created_at":"2026-06-19T16:13:11Z"}],"graph_snapshots":[{"event_id":"sha256:056ea95da6acb733021c012151a56b8eaa3279f95712904f9c155d62bdb2d432","target":"graph","created_at":"2026-06-19T16:13:11Z","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/2606.20400/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating high-utility synthetic data for intent classification typically requires human-annotated seed data, which is often unavailable in fast-paced industrial settings. In this paper, we propose a framework for synthetic dialogue generation that works entirely without human-annotated data, relying solely on intent definitions. Our proposed dialogue generation framework utilizes two different types of topic and style attributes to improve data diversity. Also, we propose two novel post-hoc stylization models called Univ and Exam to transform synthetic LLM-generated utterances into more vari","authors_text":"Mohammad Aliannejadi, Omar Essam, Zahra Abbasiantaeb, Zeno Belligoli","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-18T15:53:22Z","title":"The Significance of Style Diversity in Annotation-Free Synthetic Data Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20400","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:b033f0b060b6ca53a602549f8b7f7881e13687c17858e16646d39136c301d6e0","target":"record","created_at":"2026-06-19T16:13:11Z","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":"35ac4a30e1560084bcff5c640d278cc23f1e8dda04c6bdb2e855a00a23316960","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-18T15:53:22Z","title_canon_sha256":"b06f42a8fe9cf3239adfdac7c760ed877ca4ff88ab61a6e1d280497013ccdea9"},"schema_version":"1.0","source":{"id":"2606.20400","kind":"arxiv","version":1}},"canonical_sha256":"142473b824abe996a83533672612d27c210940313f16fcc8f7836eadce8a23df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"142473b824abe996a83533672612d27c210940313f16fcc8f7836eadce8a23df","first_computed_at":"2026-06-19T16:13:11.621287Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:13:11.621287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I5qwxdT1ZolUmtN+KF/PMBfQplscOHmRaLlzdzYWx7lCZSfZJFelcPYFhRhIcWuII6WdLCwP86RKgORbnG+cBA==","signature_status":"signed_v1","signed_at":"2026-06-19T16:13:11.621690Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.20400","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b033f0b060b6ca53a602549f8b7f7881e13687c17858e16646d39136c301d6e0","sha256:056ea95da6acb733021c012151a56b8eaa3279f95712904f9c155d62bdb2d432"],"state_sha256":"3d1f728a6f3b1c4d20ebe3496dc8695fef0751d418ea0f74ed92a4f716cc4667"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X3dShKxhM8vLgZ/+NovrjwnyPxbZ5y6HH9R3k9VJZ6bAcquvhpzUViO8/feyyeX/sf03lcD9r5cnF612xfrACw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T06:03:03.561248Z","bundle_sha256":"c0cb30bbd60eabbfdc652085a6210b7081a0d44571e79547d6f6057ba9cbe4b6"}}