{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YDI27EI4TF6ASFAWT2DN4VQFQ6","short_pith_number":"pith:YDI27EI4","schema_version":"1.0","canonical_sha256":"c0d1af911c997c0914169e86de560587affdc587ad784f48dde208083def4c68","source":{"kind":"arxiv","id":"2605.17610","version":1},"attestation_state":"computed","paper":{"title":"SafeLens: Deliberate and Efficient Video Guardrails with Fast-and-Slow Screening","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Anshuman Chhabra, Hadi Askari, Muhao Chen, Shahriar Kabir Nahin","submitted_at":"2026-05-17T19:10:36Z","abstract_excerpt":"The rapid growth of online video platforms and AI-generated content has made reliable video guardrails a key challenge for safety and real-world deployment. While most videos can be screened through fast pattern recognition, a small subset requires deeper reasoning over temporally complex content and nuanced policy constraints. Existing approaches typically rely on large vision-language models applied uniformly across all inputs, resulting in high inference costs and inefficient allocation of computation. We propose SafeLens, a video guardrail framework that introduces a fast-and-slow inferenc"},"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":"2605.17610","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-17T19:10:36Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"1e334b4ee311616449b463ec80c40260cf35bb7f24e807e51e62314d41305a97","abstract_canon_sha256":"e1a7343c2ee29b222213ef9aa8bca889f11dcf119f118e12a1ae6370cf52e6c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:48.359404Z","signature_b64":"LQvs3ghGIom5DvqDzW11JZm06vLlgVATuunXVf21U3NW0K82US1Bob8WZ+/Nfq8fr1m7JivEZleuVTunxIe9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0d1af911c997c0914169e86de560587affdc587ad784f48dde208083def4c68","last_reissued_at":"2026-05-20T00:04:48.358539Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:48.358539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SafeLens: Deliberate and Efficient Video Guardrails with Fast-and-Slow Screening","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Anshuman Chhabra, Hadi Askari, Muhao Chen, Shahriar Kabir Nahin","submitted_at":"2026-05-17T19:10:36Z","abstract_excerpt":"The rapid growth of online video platforms and AI-generated content has made reliable video guardrails a key challenge for safety and real-world deployment. While most videos can be screened through fast pattern recognition, a small subset requires deeper reasoning over temporally complex content and nuanced policy constraints. Existing approaches typically rely on large vision-language models applied uniformly across all inputs, resulting in high inference costs and inefficient allocation of computation. We propose SafeLens, a video guardrail framework that introduces a fast-and-slow inferenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17610","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/2605.17610/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"cited_work_retraction","ran_at":"2026-05-19T22:53:08.911069Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.569491Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T21:21:57.497254Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"70635cd2091e00eb1937b7954520bfe4a2e6eca50dd1589802253c142ead3bf5"},"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":"2605.17610","created_at":"2026-05-20T00:04:48.358683+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17610v1","created_at":"2026-05-20T00:04:48.358683+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17610","created_at":"2026-05-20T00:04:48.358683+00:00"},{"alias_kind":"pith_short_12","alias_value":"YDI27EI4TF6A","created_at":"2026-05-20T00:04:48.358683+00:00"},{"alias_kind":"pith_short_16","alias_value":"YDI27EI4TF6ASFAW","created_at":"2026-05-20T00:04:48.358683+00:00"},{"alias_kind":"pith_short_8","alias_value":"YDI27EI4","created_at":"2026-05-20T00:04:48.358683+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/YDI27EI4TF6ASFAWT2DN4VQFQ6","json":"https://pith.science/pith/YDI27EI4TF6ASFAWT2DN4VQFQ6.json","graph_json":"https://pith.science/api/pith-number/YDI27EI4TF6ASFAWT2DN4VQFQ6/graph.json","events_json":"https://pith.science/api/pith-number/YDI27EI4TF6ASFAWT2DN4VQFQ6/events.json","paper":"https://pith.science/paper/YDI27EI4"},"agent_actions":{"view_html":"https://pith.science/pith/YDI27EI4TF6ASFAWT2DN4VQFQ6","download_json":"https://pith.science/pith/YDI27EI4TF6ASFAWT2DN4VQFQ6.json","view_paper":"https://pith.science/paper/YDI27EI4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17610&json=true","fetch_graph":"https://pith.science/api/pith-number/YDI27EI4TF6ASFAWT2DN4VQFQ6/graph.json","fetch_events":"https://pith.science/api/pith-number/YDI27EI4TF6ASFAWT2DN4VQFQ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YDI27EI4TF6ASFAWT2DN4VQFQ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YDI27EI4TF6ASFAWT2DN4VQFQ6/action/storage_attestation","attest_author":"https://pith.science/pith/YDI27EI4TF6ASFAWT2DN4VQFQ6/action/author_attestation","sign_citation":"https://pith.science/pith/YDI27EI4TF6ASFAWT2DN4VQFQ6/action/citation_signature","submit_replication":"https://pith.science/pith/YDI27EI4TF6ASFAWT2DN4VQFQ6/action/replication_record"}},"created_at":"2026-05-20T00:04:48.358683+00:00","updated_at":"2026-05-20T00:04:48.358683+00:00"}