{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GJFDDZVGQBXIDRCU2LE4GLWZBA","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":"d8ae345fa48844759e9a2d5f03849d8ddb74a0893c61d4334c586300e6168a72","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T17:36:18Z","title_canon_sha256":"72d66f14eb09f00f8f8a489398722240784b982ac8ae29e9056321558917205b"},"schema_version":"1.0","source":{"id":"2506.00649","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00649","created_at":"2026-07-05T11:13:38Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00649v1","created_at":"2026-07-05T11:13:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00649","created_at":"2026-07-05T11:13:38Z"},{"alias_kind":"pith_short_12","alias_value":"GJFDDZVGQBXI","created_at":"2026-07-05T11:13:38Z"},{"alias_kind":"pith_short_16","alias_value":"GJFDDZVGQBXIDRCU","created_at":"2026-07-05T11:13:38Z"},{"alias_kind":"pith_short_8","alias_value":"GJFDDZVG","created_at":"2026-07-05T11:13:38Z"}],"graph_snapshots":[{"event_id":"sha256:2d655a9f65ca363edf4320c9f0ccf715017506da9adab74f4b1dfbd62a9c96f9","target":"graph","created_at":"2026-07-05T11:13:38Z","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/2506.00649/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Information Extraction (IE) systems are traditionally domain-specific, requiring costly adaptation that involves expert schema design, data annotation, and model training. While Large Language Models have shown promise in zero-shot IE, performance degrades significantly in unseen domains where label definitions differ. This paper introduces GUIDEX, a novel method that automatically defines domain-specific schemas, infers guidelines, and generates synthetically labeled instances, allowing for better out-of-domain generalization. Fine-tuning Llama 3.1 with GUIDEX sets a new state-of-the-art acro","authors_text":"Eneko Agirre, Iker Garc\\'ia-Ferrero, Neil De La Fuente, Oscar Sainz","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T17:36:18Z","title":"GuideX: Guided Synthetic Data Generation for Zero-Shot Information Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00649","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":"sha256:4633a868bba76a085a3bbf45f860493118e9125848e203f62ff5688871533404","target":"record","created_at":"2026-07-05T11:13:38Z","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":"d8ae345fa48844759e9a2d5f03849d8ddb74a0893c61d4334c586300e6168a72","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T17:36:18Z","title_canon_sha256":"72d66f14eb09f00f8f8a489398722240784b982ac8ae29e9056321558917205b"},"schema_version":"1.0","source":{"id":"2506.00649","kind":"arxiv","version":1}},"canonical_sha256":"324a31e6a6806e81c454d2c9c32ed9080599a6b12e81685c252fb5fe1c2f9888","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"324a31e6a6806e81c454d2c9c32ed9080599a6b12e81685c252fb5fe1c2f9888","first_computed_at":"2026-07-05T11:13:38.157368Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:38.157368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c9hLU43DA6Qk0jneqQYdhrYl6eK/g4ZUIz/nWt0hNlBmEpLnRg6/cTJRRBGXBBKIDkosG4SGqFxqk4UCkKFwAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:38.157783Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00649","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4633a868bba76a085a3bbf45f860493118e9125848e203f62ff5688871533404","sha256:2d655a9f65ca363edf4320c9f0ccf715017506da9adab74f4b1dfbd62a9c96f9"],"state_sha256":"8d3cf7b0b9ed86a1c68c2bb533dea90ea6b66470aff71dec282526ae91ed1c33"}