{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IDQ4I5GTFJLADY2OMYKZ6G2ZCM","short_pith_number":"pith:IDQ4I5GT","canonical_record":{"source":{"id":"2408.08379","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-15T18:43:50Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"c88f6124f16c395153f75a507fd4116d0349779ef10016861db1e844d4410669","abstract_canon_sha256":"d033a117ce7daf72a2604e89a10436e87a016dee9ed268a5f0826ff8196083a7"},"schema_version":"1.0"},"canonical_sha256":"40e1c474d32a5601e34e66159f1b591339bcf8722977836a17869889af1ee932","source":{"kind":"arxiv","id":"2408.08379","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.08379","created_at":"2026-07-05T08:55:53Z"},{"alias_kind":"arxiv_version","alias_value":"2408.08379v1","created_at":"2026-07-05T08:55:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08379","created_at":"2026-07-05T08:55:53Z"},{"alias_kind":"pith_short_12","alias_value":"IDQ4I5GTFJLA","created_at":"2026-07-05T08:55:53Z"},{"alias_kind":"pith_short_16","alias_value":"IDQ4I5GTFJLADY2O","created_at":"2026-07-05T08:55:53Z"},{"alias_kind":"pith_short_8","alias_value":"IDQ4I5GT","created_at":"2026-07-05T08:55:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IDQ4I5GTFJLADY2OMYKZ6G2ZCM","target":"record","payload":{"canonical_record":{"source":{"id":"2408.08379","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-15T18:43:50Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"c88f6124f16c395153f75a507fd4116d0349779ef10016861db1e844d4410669","abstract_canon_sha256":"d033a117ce7daf72a2604e89a10436e87a016dee9ed268a5f0826ff8196083a7"},"schema_version":"1.0"},"canonical_sha256":"40e1c474d32a5601e34e66159f1b591339bcf8722977836a17869889af1ee932","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:53.567372Z","signature_b64":"TwBXFvpQ16YmW5XnX4ZwnGR0ydbv2J+2OSh6GdcP0qQqe9VuGTbC0gIbIzMNTwu0fSN/0R56REW5CzOGOg/sCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40e1c474d32a5601e34e66159f1b591339bcf8722977836a17869889af1ee932","last_reissued_at":"2026-07-05T08:55:53.566929Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:53.566929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.08379","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":"2026-07-05T08:55:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qyZ6UwKZg7gMjnzGtOavkw0uwUjWIbGnOmCuF0oe8vRFsofVZjkp2SBRM/VqalLBKD+2I6jT04K877C0nkdVDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T02:54:50.638966Z"},"content_sha256":"53a7a0481f3fe073c477daff69af233f848e7e79c8f63d9dd9c4763e4351fd3c","schema_version":"1.0","event_id":"sha256:53a7a0481f3fe073c477daff69af233f848e7e79c8f63d9dd9c4763e4351fd3c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IDQ4I5GTFJLADY2OMYKZ6G2ZCM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Realistic Synthetic User-Generated Content: A Scaffolding Approach to Generating Online Discussions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Barbara Ikica, Filip Radlinski, Hamidreza Alvari, John Palowitch, Krisztian Balog, Mehdi Manshadi","submitted_at":"2024-08-15T18:43:50Z","abstract_excerpt":"The emergence of synthetic data represents a pivotal shift in modern machine learning, offering a solution to satisfy the need for large volumes of data in domains where real data is scarce, highly private, or difficult to obtain. We investigate the feasibility of creating realistic, large-scale synthetic datasets of user-generated content, noting that such content is increasingly prevalent and a source of frequently sought information. Large language models (LLMs) offer a starting point for generating synthetic social media discussion threads, due to their ability to produce diverse responses"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08379","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/2408.08379/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":"2026-07-05T08:55:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sni3H5UkBfoTNAWoA33GWXhkc0roHyq3ix0RLfNw5x0CN6CukgcjQAjULeB/YADooenYRtDwxMp0AJEN+hk3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T02:54:50.639365Z"},"content_sha256":"f7454eb525f2c9a58cd8dcf91eec4939d64e6212da94bbcbb03c7de51d0ec36c","schema_version":"1.0","event_id":"sha256:f7454eb525f2c9a58cd8dcf91eec4939d64e6212da94bbcbb03c7de51d0ec36c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IDQ4I5GTFJLADY2OMYKZ6G2ZCM/bundle.json","state_url":"https://pith.science/pith/IDQ4I5GTFJLADY2OMYKZ6G2ZCM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IDQ4I5GTFJLADY2OMYKZ6G2ZCM/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":"2026-07-08T02:54:50Z","links":{"resolver":"https://pith.science/pith/IDQ4I5GTFJLADY2OMYKZ6G2ZCM","bundle":"https://pith.science/pith/IDQ4I5GTFJLADY2OMYKZ6G2ZCM/bundle.json","state":"https://pith.science/pith/IDQ4I5GTFJLADY2OMYKZ6G2ZCM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IDQ4I5GTFJLADY2OMYKZ6G2ZCM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IDQ4I5GTFJLADY2OMYKZ6G2ZCM","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":"d033a117ce7daf72a2604e89a10436e87a016dee9ed268a5f0826ff8196083a7","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-15T18:43:50Z","title_canon_sha256":"c88f6124f16c395153f75a507fd4116d0349779ef10016861db1e844d4410669"},"schema_version":"1.0","source":{"id":"2408.08379","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.08379","created_at":"2026-07-05T08:55:53Z"},{"alias_kind":"arxiv_version","alias_value":"2408.08379v1","created_at":"2026-07-05T08:55:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08379","created_at":"2026-07-05T08:55:53Z"},{"alias_kind":"pith_short_12","alias_value":"IDQ4I5GTFJLA","created_at":"2026-07-05T08:55:53Z"},{"alias_kind":"pith_short_16","alias_value":"IDQ4I5GTFJLADY2O","created_at":"2026-07-05T08:55:53Z"},{"alias_kind":"pith_short_8","alias_value":"IDQ4I5GT","created_at":"2026-07-05T08:55:53Z"}],"graph_snapshots":[{"event_id":"sha256:f7454eb525f2c9a58cd8dcf91eec4939d64e6212da94bbcbb03c7de51d0ec36c","target":"graph","created_at":"2026-07-05T08:55:53Z","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/2408.08379/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The emergence of synthetic data represents a pivotal shift in modern machine learning, offering a solution to satisfy the need for large volumes of data in domains where real data is scarce, highly private, or difficult to obtain. We investigate the feasibility of creating realistic, large-scale synthetic datasets of user-generated content, noting that such content is increasingly prevalent and a source of frequently sought information. Large language models (LLMs) offer a starting point for generating synthetic social media discussion threads, due to their ability to produce diverse responses","authors_text":"Barbara Ikica, Filip Radlinski, Hamidreza Alvari, John Palowitch, Krisztian Balog, Mehdi Manshadi","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-15T18:43:50Z","title":"Towards Realistic Synthetic User-Generated Content: A Scaffolding Approach to Generating Online Discussions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08379","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":"sha256:53a7a0481f3fe073c477daff69af233f848e7e79c8f63d9dd9c4763e4351fd3c","target":"record","created_at":"2026-07-05T08:55:53Z","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":"d033a117ce7daf72a2604e89a10436e87a016dee9ed268a5f0826ff8196083a7","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-15T18:43:50Z","title_canon_sha256":"c88f6124f16c395153f75a507fd4116d0349779ef10016861db1e844d4410669"},"schema_version":"1.0","source":{"id":"2408.08379","kind":"arxiv","version":1}},"canonical_sha256":"40e1c474d32a5601e34e66159f1b591339bcf8722977836a17869889af1ee932","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40e1c474d32a5601e34e66159f1b591339bcf8722977836a17869889af1ee932","first_computed_at":"2026-07-05T08:55:53.566929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:55:53.566929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TwBXFvpQ16YmW5XnX4ZwnGR0ydbv2J+2OSh6GdcP0qQqe9VuGTbC0gIbIzMNTwu0fSN/0R56REW5CzOGOg/sCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:55:53.567372Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.08379","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53a7a0481f3fe073c477daff69af233f848e7e79c8f63d9dd9c4763e4351fd3c","sha256:f7454eb525f2c9a58cd8dcf91eec4939d64e6212da94bbcbb03c7de51d0ec36c"],"state_sha256":"1adb67562df3b39caa26c5c02522f02ecfc88a55dbcb2397bae3217c17afb75e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BAb5oMvbT4bop2dfxfGqicwU3nKfpFNHr9zv12cqpqyrZAhwBLcdktDfSkcZxbeMHAd9BFVrY1gKWje641bzBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T02:54:50.641439Z","bundle_sha256":"8ee55c902e82114f31e8eb2c0d51dee298a523075f6c7279fa14c41ae8ac86ea"}}