{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FP2MSO5DHKWHA4CJSY4RPHTV72","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":"ffc0895107e56a96ef006bbb0c0e02f39eb0f4d379754264da347d3b61abfbd0","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-07T18:48:55Z","title_canon_sha256":"bfb11de42e918261dda1d4c31e8115b54a9ef3959381aa2e737948b41f7369e8"},"schema_version":"1.0","source":{"id":"2303.04132","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.04132","created_at":"2026-07-05T07:06:24Z"},{"alias_kind":"arxiv_version","alias_value":"2303.04132v2","created_at":"2026-07-05T07:06:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.04132","created_at":"2026-07-05T07:06:24Z"},{"alias_kind":"pith_short_12","alias_value":"FP2MSO5DHKWH","created_at":"2026-07-05T07:06:24Z"},{"alias_kind":"pith_short_16","alias_value":"FP2MSO5DHKWHA4CJ","created_at":"2026-07-05T07:06:24Z"},{"alias_kind":"pith_short_8","alias_value":"FP2MSO5D","created_at":"2026-07-05T07:06:24Z"}],"graph_snapshots":[{"event_id":"sha256:2349d4d482358dd0182dd8e35ae83956b94cb32ea3e2fce7d36697d24b2a1681","target":"graph","created_at":"2026-07-05T07:06:24Z","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/2303.04132/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have great potential for synthetic data generation. This work shows that useful data can be synthetically generated even for tasks that cannot be solved directly by LLMs: for problems with structured outputs, it is possible to prompt an LLM to perform the task in the reverse direction, by generating plausible input text for a target output structure. Leveraging this asymmetry in task difficulty makes it possible to produce large-scale, high-quality data for complex tasks. We demonstrate the effectiveness of this approach on closed information extraction, where coll","authors_text":"Marija Sakota, Martin Josifoski, Maxime Peyrard, Robert West","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-07T18:48:55Z","title":"Exploiting Asymmetry for Synthetic Training Data Generation: SynthIE and the Case of Information Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.04132","kind":"arxiv","version":2},"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:f6644cf41f553a13c3698f5f85a126070ad436511bf0bf984bf55ae13449c9fe","target":"record","created_at":"2026-07-05T07:06:24Z","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":"ffc0895107e56a96ef006bbb0c0e02f39eb0f4d379754264da347d3b61abfbd0","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-07T18:48:55Z","title_canon_sha256":"bfb11de42e918261dda1d4c31e8115b54a9ef3959381aa2e737948b41f7369e8"},"schema_version":"1.0","source":{"id":"2303.04132","kind":"arxiv","version":2}},"canonical_sha256":"2bf4c93ba33aac7070499639179e75fea3adfbd934f4245fdfa3bc9d9286ada8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2bf4c93ba33aac7070499639179e75fea3adfbd934f4245fdfa3bc9d9286ada8","first_computed_at":"2026-07-05T07:06:24.030575Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:24.030575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7yNTXPbZxhTPCKiuKM9Klv6ZZAatO8Dj+T7r2JtQAfRKjKedLoOrJAs2iLV8KCiSPsKt1zZ6THWxdyC55Gm+Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:24.031066Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.04132","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6644cf41f553a13c3698f5f85a126070ad436511bf0bf984bf55ae13449c9fe","sha256:2349d4d482358dd0182dd8e35ae83956b94cb32ea3e2fce7d36697d24b2a1681"],"state_sha256":"8ab23e8f8128ad322c9cf5ecb3810f05b0ecd2711e8313996e8c7652b589ec47"}