{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MYAGO4V57XHZ2EU7XNST3KN2K4","short_pith_number":"pith:MYAGO4V5","schema_version":"1.0","canonical_sha256":"66006772bdfdcf9d129fbb653da9ba572619e091a4525787800583aca60195d1","source":{"kind":"arxiv","id":"2501.13976","version":1},"attestation_state":"computed","paper":{"title":"Towards Safer Social Media Platforms: Scalable and Performant Few-Shot Harmful Content Moderation Using Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.SI"],"primary_cat":"cs.CL","authors_text":"Akash Bonagiri, Anshuman Chhabra, Lucen Li, Magdalena Wojcieszak, Rajvardhan Oak, Zeerak Babar","submitted_at":"2025-01-23T00:19:14Z","abstract_excerpt":"The prevalence of harmful content on social media platforms poses significant risks to users and society, necessitating more effective and scalable content moderation strategies. Current approaches rely on human moderators, supervised classifiers, and large volumes of training data, and often struggle with scalability, subjectivity, and the dynamic nature of harmful content (e.g., violent content, dangerous challenge trends, etc.). To bridge these gaps, we utilize Large Language Models (LLMs) to undertake few-shot dynamic content moderation via in-context learning. Through extensive experiment"},"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":"2501.13976","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-23T00:19:14Z","cross_cats_sorted":["cs.AI","cs.CY","cs.SI"],"title_canon_sha256":"ba171f81c66ead3768583bd8e7150aaf78c153460685df74efc840c081d82ce7","abstract_canon_sha256":"178277f2c27481b23c00e7eaa1cfb10accdf5c7de3610ea8cd5ba5e6d798c602"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:43.340727Z","signature_b64":"/lbQEONjTC/WIc+o6Tww7C+Um2tN8K40nDb6g53ICd83eng78fTjt8JQKwjcSzjYAde9UzDhabbApMhBcCRgDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66006772bdfdcf9d129fbb653da9ba572619e091a4525787800583aca60195d1","last_reissued_at":"2026-07-05T10:04:43.340280Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:43.340280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Safer Social Media Platforms: Scalable and Performant Few-Shot Harmful Content Moderation Using Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.SI"],"primary_cat":"cs.CL","authors_text":"Akash Bonagiri, Anshuman Chhabra, Lucen Li, Magdalena Wojcieszak, Rajvardhan Oak, Zeerak Babar","submitted_at":"2025-01-23T00:19:14Z","abstract_excerpt":"The prevalence of harmful content on social media platforms poses significant risks to users and society, necessitating more effective and scalable content moderation strategies. Current approaches rely on human moderators, supervised classifiers, and large volumes of training data, and often struggle with scalability, subjectivity, and the dynamic nature of harmful content (e.g., violent content, dangerous challenge trends, etc.). To bridge these gaps, we utilize Large Language Models (LLMs) to undertake few-shot dynamic content moderation via in-context learning. Through extensive experiment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13976","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/2501.13976/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":"2501.13976","created_at":"2026-07-05T10:04:43.340356+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.13976v1","created_at":"2026-07-05T10:04:43.340356+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13976","created_at":"2026-07-05T10:04:43.340356+00:00"},{"alias_kind":"pith_short_12","alias_value":"MYAGO4V57XHZ","created_at":"2026-07-05T10:04:43.340356+00:00"},{"alias_kind":"pith_short_16","alias_value":"MYAGO4V57XHZ2EU7","created_at":"2026-07-05T10:04:43.340356+00:00"},{"alias_kind":"pith_short_8","alias_value":"MYAGO4V5","created_at":"2026-07-05T10:04:43.340356+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02122","citing_title":"STABLEVAL: Disagreement-Aware and Stable Evaluation of AI Systems","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17610","citing_title":"SafeLens: Deliberate and Efficient Video Guardrails with Fast-and-Slow Screening","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MYAGO4V57XHZ2EU7XNST3KN2K4","json":"https://pith.science/pith/MYAGO4V57XHZ2EU7XNST3KN2K4.json","graph_json":"https://pith.science/api/pith-number/MYAGO4V57XHZ2EU7XNST3KN2K4/graph.json","events_json":"https://pith.science/api/pith-number/MYAGO4V57XHZ2EU7XNST3KN2K4/events.json","paper":"https://pith.science/paper/MYAGO4V5"},"agent_actions":{"view_html":"https://pith.science/pith/MYAGO4V57XHZ2EU7XNST3KN2K4","download_json":"https://pith.science/pith/MYAGO4V57XHZ2EU7XNST3KN2K4.json","view_paper":"https://pith.science/paper/MYAGO4V5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.13976&json=true","fetch_graph":"https://pith.science/api/pith-number/MYAGO4V57XHZ2EU7XNST3KN2K4/graph.json","fetch_events":"https://pith.science/api/pith-number/MYAGO4V57XHZ2EU7XNST3KN2K4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MYAGO4V57XHZ2EU7XNST3KN2K4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MYAGO4V57XHZ2EU7XNST3KN2K4/action/storage_attestation","attest_author":"https://pith.science/pith/MYAGO4V57XHZ2EU7XNST3KN2K4/action/author_attestation","sign_citation":"https://pith.science/pith/MYAGO4V57XHZ2EU7XNST3KN2K4/action/citation_signature","submit_replication":"https://pith.science/pith/MYAGO4V57XHZ2EU7XNST3KN2K4/action/replication_record"}},"created_at":"2026-07-05T10:04:43.340356+00:00","updated_at":"2026-07-05T10:04:43.340356+00:00"}