{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EKMO2PEPDCKJIE5BBF6WKF25BA","short_pith_number":"pith:EKMO2PEP","schema_version":"1.0","canonical_sha256":"2298ed3c8f18949413a1097d65175d08393c3f6d317afcccd99dd55fe01cdc68","source":{"kind":"arxiv","id":"2405.10700","version":1},"attestation_state":"computed","paper":{"title":"SynDy: Synthetic Dynamic Dataset Generation Framework for Misinformation Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CY"],"primary_cat":"cs.IR","authors_text":"Ashkan Kazemi, Michael Shliselberg, Scott A. Hale, Shiri Dori-Hacohen","submitted_at":"2024-05-17T11:14:55Z","abstract_excerpt":"Diaspora communities are disproportionately impacted by off-the-radar misinformation and often neglected by mainstream fact-checking efforts, creating a critical need to scale-up efforts of nascent fact-checking initiatives. In this paper we present SynDy, a framework for Synthetic Dynamic Dataset Generation to leverage the capabilities of the largest frontier Large Language Models (LLMs) to train local, specialized language models. To the best of our knowledge, SynDy is the first paper utilizing LLMs to create fine-grained synthetic labels for tasks of direct relevance to misinformation mitig"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2405.10700","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-05-17T11:14:55Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CY"],"title_canon_sha256":"7a2fe3e090996ea5949b8be17767e1ae74522e80f65ea7a26913d1a24305c903","abstract_canon_sha256":"2f1925d1abc9b31ff24563ca772dcb8f1cbe3f20c1138079bd7c4ca705378447"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:15.929366Z","signature_b64":"ZdWZAhIX0Joec5oQAsN+dNtb81yM1BOL6B37uSuANAAgroafnbSCerAAGcnJqxrNbGYET0P/vS1oDBLL2jtqBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2298ed3c8f18949413a1097d65175d08393c3f6d317afcccd99dd55fe01cdc68","last_reissued_at":"2026-07-05T08:20:15.928958Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:15.928958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SynDy: Synthetic Dynamic Dataset Generation Framework for Misinformation Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CY"],"primary_cat":"cs.IR","authors_text":"Ashkan Kazemi, Michael Shliselberg, Scott A. Hale, Shiri Dori-Hacohen","submitted_at":"2024-05-17T11:14:55Z","abstract_excerpt":"Diaspora communities are disproportionately impacted by off-the-radar misinformation and often neglected by mainstream fact-checking efforts, creating a critical need to scale-up efforts of nascent fact-checking initiatives. In this paper we present SynDy, a framework for Synthetic Dynamic Dataset Generation to leverage the capabilities of the largest frontier Large Language Models (LLMs) to train local, specialized language models. To the best of our knowledge, SynDy is the first paper utilizing LLMs to create fine-grained synthetic labels for tasks of direct relevance to misinformation mitig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10700","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/2405.10700/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2405.10700","created_at":"2026-07-05T08:20:15.929013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.10700v1","created_at":"2026-07-05T08:20:15.929013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10700","created_at":"2026-07-05T08:20:15.929013+00:00"},{"alias_kind":"pith_short_12","alias_value":"EKMO2PEPDCKJ","created_at":"2026-07-05T08:20:15.929013+00:00"},{"alias_kind":"pith_short_16","alias_value":"EKMO2PEPDCKJIE5B","created_at":"2026-07-05T08:20:15.929013+00:00"},{"alias_kind":"pith_short_8","alias_value":"EKMO2PEP","created_at":"2026-07-05T08:20:15.929013+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EKMO2PEPDCKJIE5BBF6WKF25BA","json":"https://pith.science/pith/EKMO2PEPDCKJIE5BBF6WKF25BA.json","graph_json":"https://pith.science/api/pith-number/EKMO2PEPDCKJIE5BBF6WKF25BA/graph.json","events_json":"https://pith.science/api/pith-number/EKMO2PEPDCKJIE5BBF6WKF25BA/events.json","paper":"https://pith.science/paper/EKMO2PEP"},"agent_actions":{"view_html":"https://pith.science/pith/EKMO2PEPDCKJIE5BBF6WKF25BA","download_json":"https://pith.science/pith/EKMO2PEPDCKJIE5BBF6WKF25BA.json","view_paper":"https://pith.science/paper/EKMO2PEP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.10700&json=true","fetch_graph":"https://pith.science/api/pith-number/EKMO2PEPDCKJIE5BBF6WKF25BA/graph.json","fetch_events":"https://pith.science/api/pith-number/EKMO2PEPDCKJIE5BBF6WKF25BA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EKMO2PEPDCKJIE5BBF6WKF25BA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EKMO2PEPDCKJIE5BBF6WKF25BA/action/storage_attestation","attest_author":"https://pith.science/pith/EKMO2PEPDCKJIE5BBF6WKF25BA/action/author_attestation","sign_citation":"https://pith.science/pith/EKMO2PEPDCKJIE5BBF6WKF25BA/action/citation_signature","submit_replication":"https://pith.science/pith/EKMO2PEPDCKJIE5BBF6WKF25BA/action/replication_record"}},"created_at":"2026-07-05T08:20:15.929013+00:00","updated_at":"2026-07-05T08:20:15.929013+00:00"}