{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OQDKRNSSBY6ZLCEKKOSW2AU6YG","short_pith_number":"pith:OQDKRNSS","schema_version":"1.0","canonical_sha256":"7406a8b6520e3d95888a53a56d029ec1be9bafc8600d9ee117559666465c98a6","source":{"kind":"arxiv","id":"2608.09510","version":1},"attestation_state":"computed","paper":{"title":"Build it, Break it, Repeat: Benchmarking and improving LLM-manipulated disinformation detection in social media posts","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.SI"],"primary_cat":"cs.CL","authors_text":"Cameron Tovey, Carolina Scarton, Elliott Pert, Jo\\~ao A. Leite, Kevin Thomas, Milosz Kasprzyk, Olesya Razuvayevskaya, Reuel C Igbokwe Onuigbo","submitted_at":"2026-08-10T12:13:41Z","abstract_excerpt":"Detecting machine-generated disinformation on social media is increasingly difficult as large language models (LLMs) make it easier to generate and rewrite misleading content at scale. Static benchmark evaluations, measuring detector performance on fixed held-out datasets, do not capture how detectors behave when posts are deliberately transformed to evade classification. This paper adapts the Build it, Break it, Fix it framework into Build it, Break it, Repeat (BiBiR): iterative sessions designed to stress-test detectors' robustness under iterative adversarial conditions, evaluating whether m"},"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":"2608.09510","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-10T12:13:41Z","cross_cats_sorted":["cs.AI","cs.SI"],"title_canon_sha256":"58fc4c88d34650abf9ba81042e5ff29f7221b9357a9c424be7b2cb41dcf4b9a6","abstract_canon_sha256":"f5c38ae91dfab4df9673e77a29d3dcca67903aa41835446ac1f1dfed1b02e2eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T02:24:22.251870Z","signature_b64":"bM6S88KdgqC4rQZCrfBqvjXtDcqLHt4K28Y7UObTwlx/Qkywn017kdDeTLyYMe+3BgX5DN28Ygs4jSec++5WBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7406a8b6520e3d95888a53a56d029ec1be9bafc8600d9ee117559666465c98a6","last_reissued_at":"2026-08-11T02:24:22.250281Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T02:24:22.250281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Build it, Break it, Repeat: Benchmarking and improving LLM-manipulated disinformation detection in social media posts","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.SI"],"primary_cat":"cs.CL","authors_text":"Cameron Tovey, Carolina Scarton, Elliott Pert, Jo\\~ao A. Leite, Kevin Thomas, Milosz Kasprzyk, Olesya Razuvayevskaya, Reuel C Igbokwe Onuigbo","submitted_at":"2026-08-10T12:13:41Z","abstract_excerpt":"Detecting machine-generated disinformation on social media is increasingly difficult as large language models (LLMs) make it easier to generate and rewrite misleading content at scale. Static benchmark evaluations, measuring detector performance on fixed held-out datasets, do not capture how detectors behave when posts are deliberately transformed to evade classification. This paper adapts the Build it, Break it, Fix it framework into Build it, Break it, Repeat (BiBiR): iterative sessions designed to stress-test detectors' robustness under iterative adversarial conditions, evaluating whether m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09510","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/2608.09510/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":"2608.09510","created_at":"2026-08-11T02:24:22.250890+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.09510v1","created_at":"2026-08-11T02:24:22.250890+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09510","created_at":"2026-08-11T02:24:22.250890+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQDKRNSSBY6Z","created_at":"2026-08-11T02:24:22.250890+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQDKRNSSBY6ZLCEK","created_at":"2026-08-11T02:24:22.250890+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQDKRNSS","created_at":"2026-08-11T02:24:22.250890+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/OQDKRNSSBY6ZLCEKKOSW2AU6YG","json":"https://pith.science/pith/OQDKRNSSBY6ZLCEKKOSW2AU6YG.json","graph_json":"https://pith.science/api/pith-number/OQDKRNSSBY6ZLCEKKOSW2AU6YG/graph.json","events_json":"https://pith.science/api/pith-number/OQDKRNSSBY6ZLCEKKOSW2AU6YG/events.json","paper":"https://pith.science/paper/OQDKRNSS"},"agent_actions":{"view_html":"https://pith.science/pith/OQDKRNSSBY6ZLCEKKOSW2AU6YG","download_json":"https://pith.science/pith/OQDKRNSSBY6ZLCEKKOSW2AU6YG.json","view_paper":"https://pith.science/paper/OQDKRNSS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.09510&json=true","fetch_graph":"https://pith.science/api/pith-number/OQDKRNSSBY6ZLCEKKOSW2AU6YG/graph.json","fetch_events":"https://pith.science/api/pith-number/OQDKRNSSBY6ZLCEKKOSW2AU6YG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQDKRNSSBY6ZLCEKKOSW2AU6YG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQDKRNSSBY6ZLCEKKOSW2AU6YG/action/storage_attestation","attest_author":"https://pith.science/pith/OQDKRNSSBY6ZLCEKKOSW2AU6YG/action/author_attestation","sign_citation":"https://pith.science/pith/OQDKRNSSBY6ZLCEKKOSW2AU6YG/action/citation_signature","submit_replication":"https://pith.science/pith/OQDKRNSSBY6ZLCEKKOSW2AU6YG/action/replication_record"}},"created_at":"2026-08-11T02:24:22.250890+00:00","updated_at":"2026-08-11T02:24:22.250890+00:00"}