{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HFAQUUKNY4TZ4GINRSOGRFOK77","short_pith_number":"pith:HFAQUUKN","canonical_record":{"source":{"id":"2504.15548","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T02:59:03Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"b0d4ed47ce87d99f69c4cae8a80c221bd3faa415744c31aec32c9c55aa56630b","abstract_canon_sha256":"901266f63d4c380a11efdc4518041d47e8cb312a689c7c3bd04f03f4c3da419f"},"schema_version":"1.0"},"canonical_sha256":"39410a514dc7279e190d8c9c6895caffd21bca02413a48f1cafab66b6941e378","source":{"kind":"arxiv","id":"2504.15548","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.15548","created_at":"2026-07-05T10:52:26Z"},{"alias_kind":"arxiv_version","alias_value":"2504.15548v1","created_at":"2026-07-05T10:52:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15548","created_at":"2026-07-05T10:52:26Z"},{"alias_kind":"pith_short_12","alias_value":"HFAQUUKNY4TZ","created_at":"2026-07-05T10:52:26Z"},{"alias_kind":"pith_short_16","alias_value":"HFAQUUKNY4TZ4GIN","created_at":"2026-07-05T10:52:26Z"},{"alias_kind":"pith_short_8","alias_value":"HFAQUUKN","created_at":"2026-07-05T10:52:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HFAQUUKNY4TZ4GINRSOGRFOK77","target":"record","payload":{"canonical_record":{"source":{"id":"2504.15548","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T02:59:03Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"b0d4ed47ce87d99f69c4cae8a80c221bd3faa415744c31aec32c9c55aa56630b","abstract_canon_sha256":"901266f63d4c380a11efdc4518041d47e8cb312a689c7c3bd04f03f4c3da419f"},"schema_version":"1.0"},"canonical_sha256":"39410a514dc7279e190d8c9c6895caffd21bca02413a48f1cafab66b6941e378","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:26.376885Z","signature_b64":"gPvz+MtzuYPIYQ2wwCkKryOj/69xLD019Z6E7BDigD/wRGW7t8yo9ko+g3fCunIXnhiq+rwow7tlcP2bRY88DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39410a514dc7279e190d8c9c6895caffd21bca02413a48f1cafab66b6941e378","last_reissued_at":"2026-07-05T10:52:26.376390Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:26.376390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.15548","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":"2026-07-05T10:52:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C4aiM8hwEzpg8Ty7MSFEJDWf6Ic4hNxBQ8LS8szkiphEet0Cg2FrvPq9nOyG5hQzYEnSZdMVA6D58/FWy0txDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T21:22:26.189424Z"},"content_sha256":"1eacbfeb3f9b00ec7a90c0c03e03610302e08addb846f781df45539766128ef1","schema_version":"1.0","event_id":"sha256:1eacbfeb3f9b00ec7a90c0c03e03610302e08addb846f781df45539766128ef1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HFAQUUKNY4TZ4GINRSOGRFOK77","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM-based Semantic Augmentation for Harmful Content Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Assaad Zeghina, Elyas Meguellati, Gianluca Demartini, Shazia Sadiq","submitted_at":"2025-04-22T02:59:03Z","abstract_excerpt":"Recent advances in large language models (LLMs) have demonstrated strong performance on simple text classification tasks, frequently under zero-shot settings. However, their efficacy declines when tackling complex social media challenges such as propaganda detection, hateful meme classification, and toxicity identification. Much of the existing work has focused on using LLMs to generate synthetic training data, overlooking the potential of LLM-based text preprocessing and semantic augmentation. In this paper, we introduce an approach that prompts LLMs to clean noisy text and provide context-ri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15548","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/2504.15548/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":"2026-07-05T10:52:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aGL8DLbc0SgeH2+CdCSa406z/n7eQmW5vxhxy36BjAoZS61Np14qKROOCdUi8/a3e3QqdYoMfrHSPtmjaAHkDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T21:22:26.189803Z"},"content_sha256":"91edc8d9b44170518ab0e84b625283341c022216f3165748bf5fe3a5b7bff604","schema_version":"1.0","event_id":"sha256:91edc8d9b44170518ab0e84b625283341c022216f3165748bf5fe3a5b7bff604"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HFAQUUKNY4TZ4GINRSOGRFOK77/bundle.json","state_url":"https://pith.science/pith/HFAQUUKNY4TZ4GINRSOGRFOK77/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HFAQUUKNY4TZ4GINRSOGRFOK77/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":"2026-08-18T21:22:26Z","links":{"resolver":"https://pith.science/pith/HFAQUUKNY4TZ4GINRSOGRFOK77","bundle":"https://pith.science/pith/HFAQUUKNY4TZ4GINRSOGRFOK77/bundle.json","state":"https://pith.science/pith/HFAQUUKNY4TZ4GINRSOGRFOK77/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HFAQUUKNY4TZ4GINRSOGRFOK77/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HFAQUUKNY4TZ4GINRSOGRFOK77","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":"901266f63d4c380a11efdc4518041d47e8cb312a689c7c3bd04f03f4c3da419f","cross_cats_sorted":["cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T02:59:03Z","title_canon_sha256":"b0d4ed47ce87d99f69c4cae8a80c221bd3faa415744c31aec32c9c55aa56630b"},"schema_version":"1.0","source":{"id":"2504.15548","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.15548","created_at":"2026-07-05T10:52:26Z"},{"alias_kind":"arxiv_version","alias_value":"2504.15548v1","created_at":"2026-07-05T10:52:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15548","created_at":"2026-07-05T10:52:26Z"},{"alias_kind":"pith_short_12","alias_value":"HFAQUUKNY4TZ","created_at":"2026-07-05T10:52:26Z"},{"alias_kind":"pith_short_16","alias_value":"HFAQUUKNY4TZ4GIN","created_at":"2026-07-05T10:52:26Z"},{"alias_kind":"pith_short_8","alias_value":"HFAQUUKN","created_at":"2026-07-05T10:52:26Z"}],"graph_snapshots":[{"event_id":"sha256:91edc8d9b44170518ab0e84b625283341c022216f3165748bf5fe3a5b7bff604","target":"graph","created_at":"2026-07-05T10:52:26Z","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/2504.15548/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in large language models (LLMs) have demonstrated strong performance on simple text classification tasks, frequently under zero-shot settings. However, their efficacy declines when tackling complex social media challenges such as propaganda detection, hateful meme classification, and toxicity identification. Much of the existing work has focused on using LLMs to generate synthetic training data, overlooking the potential of LLM-based text preprocessing and semantic augmentation. In this paper, we introduce an approach that prompts LLMs to clean noisy text and provide context-ri","authors_text":"Assaad Zeghina, Elyas Meguellati, Gianluca Demartini, Shazia Sadiq","cross_cats":["cs.CY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T02:59:03Z","title":"LLM-based Semantic Augmentation for Harmful Content Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15548","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":"sha256:1eacbfeb3f9b00ec7a90c0c03e03610302e08addb846f781df45539766128ef1","target":"record","created_at":"2026-07-05T10:52:26Z","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":"901266f63d4c380a11efdc4518041d47e8cb312a689c7c3bd04f03f4c3da419f","cross_cats_sorted":["cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T02:59:03Z","title_canon_sha256":"b0d4ed47ce87d99f69c4cae8a80c221bd3faa415744c31aec32c9c55aa56630b"},"schema_version":"1.0","source":{"id":"2504.15548","kind":"arxiv","version":1}},"canonical_sha256":"39410a514dc7279e190d8c9c6895caffd21bca02413a48f1cafab66b6941e378","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"39410a514dc7279e190d8c9c6895caffd21bca02413a48f1cafab66b6941e378","first_computed_at":"2026-07-05T10:52:26.376390Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:26.376390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gPvz+MtzuYPIYQ2wwCkKryOj/69xLD019Z6E7BDigD/wRGW7t8yo9ko+g3fCunIXnhiq+rwow7tlcP2bRY88DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:26.376885Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.15548","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1eacbfeb3f9b00ec7a90c0c03e03610302e08addb846f781df45539766128ef1","sha256:91edc8d9b44170518ab0e84b625283341c022216f3165748bf5fe3a5b7bff604"],"state_sha256":"9cc4687d5190fc3436ce6f8a4e3cab20b604e099d2cf6946ed67ecbe90657ea5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TIT1sy2gpERVzkzFpsiEfRLFJKFxumMK8yVpFtbz62u/Y01AgnYejPihmgMbZD3hv8fRrEQwPZjDrq8Bwoo+DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T21:22:26.192227Z","bundle_sha256":"89264cbc02612edb75b2ac47f11e30a8f93f06031875f8ed61e574641bab1b3d"}}