{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GCMMOYUQIA2N7IV4EDCIMBDLNT","short_pith_number":"pith:GCMMOYUQ","canonical_record":{"source":{"id":"2507.19334","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-25T14:43:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d7d505e7228ea54651e55779ed6cf7e0a147ff55e24d215e3a127b6be7d1f44e","abstract_canon_sha256":"cb1267618794ccbba9738214900a120310db42b373d6b1cf50ce1b85fcd553b0"},"schema_version":"1.0"},"canonical_sha256":"3098c762904034dfa2bc20c486046b6cd9378aa953a2d66a585c97b98abe49d1","source":{"kind":"arxiv","id":"2507.19334","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19334","created_at":"2026-07-05T11:43:23Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19334v1","created_at":"2026-07-05T11:43:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19334","created_at":"2026-07-05T11:43:23Z"},{"alias_kind":"pith_short_12","alias_value":"GCMMOYUQIA2N","created_at":"2026-07-05T11:43:23Z"},{"alias_kind":"pith_short_16","alias_value":"GCMMOYUQIA2N7IV4","created_at":"2026-07-05T11:43:23Z"},{"alias_kind":"pith_short_8","alias_value":"GCMMOYUQ","created_at":"2026-07-05T11:43:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GCMMOYUQIA2N7IV4EDCIMBDLNT","target":"record","payload":{"canonical_record":{"source":{"id":"2507.19334","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-25T14:43:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d7d505e7228ea54651e55779ed6cf7e0a147ff55e24d215e3a127b6be7d1f44e","abstract_canon_sha256":"cb1267618794ccbba9738214900a120310db42b373d6b1cf50ce1b85fcd553b0"},"schema_version":"1.0"},"canonical_sha256":"3098c762904034dfa2bc20c486046b6cd9378aa953a2d66a585c97b98abe49d1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:23.658284Z","signature_b64":"wZ2qfLefGC/uvgFSeTKm57HepFC4OHUJN3TEfr8F6Zmq1nbU6elGUuLmTjn8qYkFL1Ocrk2hreudI0gkul8WDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3098c762904034dfa2bc20c486046b6cd9378aa953a2d66a585c97b98abe49d1","last_reissued_at":"2026-07-05T11:43:23.657686Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:23.657686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.19334","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":"2026-07-05T11:43:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VofLlsakPj7J0sLqjFTilCHF2QLZHIBoYr3RoJSFITonlKluFKuJUfSpFJGbDfOgQ5fID3RkwYUnuEfnWNlRDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:06:11.075656Z"},"content_sha256":"54b6e0e5914b36c3c0cc7e24993e1c2d15344e6198ac5c740f7d1ab59deb0172","schema_version":"1.0","event_id":"sha256:54b6e0e5914b36c3c0cc7e24993e1c2d15344e6198ac5c740f7d1ab59deb0172"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GCMMOYUQIA2N7IV4EDCIMBDLNT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Doubling Your Data in Minutes: Ultra-fast Tabular Data Generation via LLM-Induced Dependency Graphs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bardh Prenkaj, Gjergji Kasneci, Shuo Yang, Zheyu Zhang","submitted_at":"2025-07-25T14:43:50Z","abstract_excerpt":"Tabular data is critical across diverse domains, yet high-quality datasets remain scarce due to privacy concerns and the cost of collection. Contemporary approaches adopt large language models (LLMs) for tabular augmentation, but exhibit two major limitations: (1) dense dependency modeling among tabular features that can introduce bias, and (2) high computational overhead in sampling. To address these issues, we propose SPADA for SPArse Dependency-driven Augmentation, a lightweight generative framework that explicitly captures sparse dependencies via an LLM-induced graph. We treat each feature"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19334","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/2507.19334/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":"2026-07-05T11:43:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gubYe6FsQWVx1sc6sCEUl4kTB9WVYiS06dlMjwMMzdbFpQ9Q+f0hCROQsdfwUGUU84L2Yy5VJWFQd6OEo41MBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:06:11.076210Z"},"content_sha256":"e4f10f4bb6b411bbc1963be9f30a0db0b0bd12437673c818d5c0e3dc82db8880","schema_version":"1.0","event_id":"sha256:e4f10f4bb6b411bbc1963be9f30a0db0b0bd12437673c818d5c0e3dc82db8880"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GCMMOYUQIA2N7IV4EDCIMBDLNT/bundle.json","state_url":"https://pith.science/pith/GCMMOYUQIA2N7IV4EDCIMBDLNT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GCMMOYUQIA2N7IV4EDCIMBDLNT/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":"2026-08-06T09:06:11Z","links":{"resolver":"https://pith.science/pith/GCMMOYUQIA2N7IV4EDCIMBDLNT","bundle":"https://pith.science/pith/GCMMOYUQIA2N7IV4EDCIMBDLNT/bundle.json","state":"https://pith.science/pith/GCMMOYUQIA2N7IV4EDCIMBDLNT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GCMMOYUQIA2N7IV4EDCIMBDLNT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GCMMOYUQIA2N7IV4EDCIMBDLNT","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":"cb1267618794ccbba9738214900a120310db42b373d6b1cf50ce1b85fcd553b0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-25T14:43:50Z","title_canon_sha256":"d7d505e7228ea54651e55779ed6cf7e0a147ff55e24d215e3a127b6be7d1f44e"},"schema_version":"1.0","source":{"id":"2507.19334","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19334","created_at":"2026-07-05T11:43:23Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19334v1","created_at":"2026-07-05T11:43:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19334","created_at":"2026-07-05T11:43:23Z"},{"alias_kind":"pith_short_12","alias_value":"GCMMOYUQIA2N","created_at":"2026-07-05T11:43:23Z"},{"alias_kind":"pith_short_16","alias_value":"GCMMOYUQIA2N7IV4","created_at":"2026-07-05T11:43:23Z"},{"alias_kind":"pith_short_8","alias_value":"GCMMOYUQ","created_at":"2026-07-05T11:43:23Z"}],"graph_snapshots":[{"event_id":"sha256:e4f10f4bb6b411bbc1963be9f30a0db0b0bd12437673c818d5c0e3dc82db8880","target":"graph","created_at":"2026-07-05T11:43:23Z","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/2507.19334/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tabular data is critical across diverse domains, yet high-quality datasets remain scarce due to privacy concerns and the cost of collection. Contemporary approaches adopt large language models (LLMs) for tabular augmentation, but exhibit two major limitations: (1) dense dependency modeling among tabular features that can introduce bias, and (2) high computational overhead in sampling. To address these issues, we propose SPADA for SPArse Dependency-driven Augmentation, a lightweight generative framework that explicitly captures sparse dependencies via an LLM-induced graph. We treat each feature","authors_text":"Bardh Prenkaj, Gjergji Kasneci, Shuo Yang, Zheyu Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-25T14:43:50Z","title":"Doubling Your Data in Minutes: Ultra-fast Tabular Data Generation via LLM-Induced Dependency Graphs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19334","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":"sha256:54b6e0e5914b36c3c0cc7e24993e1c2d15344e6198ac5c740f7d1ab59deb0172","target":"record","created_at":"2026-07-05T11:43:23Z","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":"cb1267618794ccbba9738214900a120310db42b373d6b1cf50ce1b85fcd553b0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-25T14:43:50Z","title_canon_sha256":"d7d505e7228ea54651e55779ed6cf7e0a147ff55e24d215e3a127b6be7d1f44e"},"schema_version":"1.0","source":{"id":"2507.19334","kind":"arxiv","version":1}},"canonical_sha256":"3098c762904034dfa2bc20c486046b6cd9378aa953a2d66a585c97b98abe49d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3098c762904034dfa2bc20c486046b6cd9378aa953a2d66a585c97b98abe49d1","first_computed_at":"2026-07-05T11:43:23.657686Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:23.657686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wZ2qfLefGC/uvgFSeTKm57HepFC4OHUJN3TEfr8F6Zmq1nbU6elGUuLmTjn8qYkFL1Ocrk2hreudI0gkul8WDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:23.658284Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.19334","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54b6e0e5914b36c3c0cc7e24993e1c2d15344e6198ac5c740f7d1ab59deb0172","sha256:e4f10f4bb6b411bbc1963be9f30a0db0b0bd12437673c818d5c0e3dc82db8880"],"state_sha256":"c189c2ef3a0ccfe759da71273124aafff2af599ed7ae65f473f617de8959d060"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kVvVSoT/2Azv4GfeMaK705GQ//LM7l2h7nuo86QG+1hI0/KqtJMQ4OPRjiqXEVv9Z0fo3CPoSnGrtKocjS+zBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T09:06:11.080384Z","bundle_sha256":"43ab5c016ec2328d57435ff9eff25ba8bd38e7af19189d5b992885603c16da5c"}}