{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QBJYTLBTI5YOR7AJLR525O2GEY","short_pith_number":"pith:QBJYTLBT","schema_version":"1.0","canonical_sha256":"805389ac334770e8fc095c7baebb462617750616d17d0caac3d8b5778e0dd14a","source":{"kind":"arxiv","id":"2605.18776","version":1},"attestation_state":"computed","paper":{"title":"Mask-to-Correct$^+$: Leveraging Retriever Diversity for Masking-guided Faithful Fact Correction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Lavisha Sharma, Madhusudan Ghosh, Partha Basuchowdhuri, Payel Santra","submitted_at":"2026-04-21T14:13:07Z","abstract_excerpt":"The rapid spread of misinformation on social media highlights the need for robust, automated fact correction frameworks. However, existing works rely on supervised learning from manually annotated claim-evidence pairs, which are scarce and prone to biases, limiting their generalization across domains. Moreover, these methods overlook semantic faithfulness in their correction process. To address these challenges, we propose Mask-to-Correct (M$_2$C), a training-free, inference-only Retrieval Augmented Generation (RAG) based framework that leverages diversity-aware masking to identify erroneous s"},"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":"2605.18776","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-04-21T14:13:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7e9b26caef544c3724cb5e2f0109930e3ac42ac0650ce01c32a4eaa5312deb04","abstract_canon_sha256":"733a2f71a73d31b2c2c823d1ed83d961c846c44f8b4ea2013fd6c6b3f0f21ebc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:21.614466Z","signature_b64":"o6If3eidHlQMPqotEp69DyuT1dlU4LprLeVjRUfOelgq9p9LmC4kDM7MBJ3Dd01xABrsQHKQA12EJClD38kWDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"805389ac334770e8fc095c7baebb462617750616d17d0caac3d8b5778e0dd14a","last_reissued_at":"2026-05-20T00:06:21.613571Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:21.613571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mask-to-Correct$^+$: Leveraging Retriever Diversity for Masking-guided Faithful Fact Correction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Lavisha Sharma, Madhusudan Ghosh, Partha Basuchowdhuri, Payel Santra","submitted_at":"2026-04-21T14:13:07Z","abstract_excerpt":"The rapid spread of misinformation on social media highlights the need for robust, automated fact correction frameworks. However, existing works rely on supervised learning from manually annotated claim-evidence pairs, which are scarce and prone to biases, limiting their generalization across domains. Moreover, these methods overlook semantic faithfulness in their correction process. To address these challenges, we propose Mask-to-Correct (M$_2$C), a training-free, inference-only Retrieval Augmented Generation (RAG) based framework that leverages diversity-aware masking to identify erroneous s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18776","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/2605.18776/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":"2605.18776","created_at":"2026-05-20T00:06:21.613704+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18776v1","created_at":"2026-05-20T00:06:21.613704+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18776","created_at":"2026-05-20T00:06:21.613704+00:00"},{"alias_kind":"pith_short_12","alias_value":"QBJYTLBTI5YO","created_at":"2026-05-20T00:06:21.613704+00:00"},{"alias_kind":"pith_short_16","alias_value":"QBJYTLBTI5YOR7AJ","created_at":"2026-05-20T00:06:21.613704+00:00"},{"alias_kind":"pith_short_8","alias_value":"QBJYTLBT","created_at":"2026-05-20T00:06:21.613704+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/QBJYTLBTI5YOR7AJLR525O2GEY","json":"https://pith.science/pith/QBJYTLBTI5YOR7AJLR525O2GEY.json","graph_json":"https://pith.science/api/pith-number/QBJYTLBTI5YOR7AJLR525O2GEY/graph.json","events_json":"https://pith.science/api/pith-number/QBJYTLBTI5YOR7AJLR525O2GEY/events.json","paper":"https://pith.science/paper/QBJYTLBT"},"agent_actions":{"view_html":"https://pith.science/pith/QBJYTLBTI5YOR7AJLR525O2GEY","download_json":"https://pith.science/pith/QBJYTLBTI5YOR7AJLR525O2GEY.json","view_paper":"https://pith.science/paper/QBJYTLBT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18776&json=true","fetch_graph":"https://pith.science/api/pith-number/QBJYTLBTI5YOR7AJLR525O2GEY/graph.json","fetch_events":"https://pith.science/api/pith-number/QBJYTLBTI5YOR7AJLR525O2GEY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QBJYTLBTI5YOR7AJLR525O2GEY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QBJYTLBTI5YOR7AJLR525O2GEY/action/storage_attestation","attest_author":"https://pith.science/pith/QBJYTLBTI5YOR7AJLR525O2GEY/action/author_attestation","sign_citation":"https://pith.science/pith/QBJYTLBTI5YOR7AJLR525O2GEY/action/citation_signature","submit_replication":"https://pith.science/pith/QBJYTLBTI5YOR7AJLR525O2GEY/action/replication_record"}},"created_at":"2026-05-20T00:06:21.613704+00:00","updated_at":"2026-05-20T00:06:21.613704+00:00"}