{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QMYAQVIL7SLP5FPRB6AR5Y2M6K","short_pith_number":"pith:QMYAQVIL","schema_version":"1.0","canonical_sha256":"833008550bfc96fe95f10f811ee34cf2b2d8d62d0a2e90397fc8a0c5334849ec","source":{"kind":"arxiv","id":"2607.26518","version":1},"attestation_state":"computed","paper":{"title":"EgoSafe: A First-Person Mobile-Captured Benchmark for Visual Safety Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cen Chen, Hao Peng, Huiping Zhuang, Tianao Li, Tianquan Feng, Yuyun Chen, Ziqian Zeng","submitted_at":"2026-07-29T06:33:11Z","abstract_excerpt":"Reliable visual safety understanding in real-world scenarios demands more than just object recognition; it requires causal reasoning under epistemic uncertainty. While Large Vision-Language Models (LVLMs) demonstrate impressive semantic alignment on standard benchmarks, they often struggle to distinguish between superficial correlation and genuine forensic logic when grounded in the dynamic, partially observable nature of first-person experiences. Existing evaluations, dominated by third-person surveillance footage and binary classification metrics, fail to expose this cognitive gap. To addres"},"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":"2607.26518","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-29T06:33:11Z","cross_cats_sorted":[],"title_canon_sha256":"4563a239fb8e42ae88b3ec87e27d299713459bddab900ca81b36cdd7e70af4d9","abstract_canon_sha256":"93c09b14bbc433a34b1e061dd462cdf267b790fe6bd207d45d24eff4342b7d6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"833008550bfc96fe95f10f811ee34cf2b2d8d62d0a2e90397fc8a0c5334849ec","last_reissued_at":"2026-07-30T01:20:46.067248Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:20:46.067248Z"},"graph_snapshot":{"paper":{"title":"EgoSafe: A First-Person Mobile-Captured Benchmark for Visual Safety Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cen Chen, Hao Peng, Huiping Zhuang, Tianao Li, Tianquan Feng, Yuyun Chen, Ziqian Zeng","submitted_at":"2026-07-29T06:33:11Z","abstract_excerpt":"Reliable visual safety understanding in real-world scenarios demands more than just object recognition; it requires causal reasoning under epistemic uncertainty. While Large Vision-Language Models (LVLMs) demonstrate impressive semantic alignment on standard benchmarks, they often struggle to distinguish between superficial correlation and genuine forensic logic when grounded in the dynamic, partially observable nature of first-person experiences. Existing evaluations, dominated by third-person surveillance footage and binary classification metrics, fail to expose this cognitive gap. To addres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26518","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/2607.26518/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":"2607.26518","created_at":"2026-07-30T01:20:46.072573+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.26518v1","created_at":"2026-07-30T01:20:46.072573+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26518","created_at":"2026-07-30T01:20:46.072573+00:00"},{"alias_kind":"pith_short_12","alias_value":"QMYAQVIL7SLP","created_at":"2026-07-30T01:20:46.072573+00:00"},{"alias_kind":"pith_short_16","alias_value":"QMYAQVIL7SLP5FPR","created_at":"2026-07-30T01:20:46.072573+00:00"},{"alias_kind":"pith_short_8","alias_value":"QMYAQVIL","created_at":"2026-07-30T01:20:46.072573+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/QMYAQVIL7SLP5FPRB6AR5Y2M6K","json":"https://pith.science/pith/QMYAQVIL7SLP5FPRB6AR5Y2M6K.json","graph_json":"https://pith.science/api/pith-number/QMYAQVIL7SLP5FPRB6AR5Y2M6K/graph.json","events_json":"https://pith.science/api/pith-number/QMYAQVIL7SLP5FPRB6AR5Y2M6K/events.json","paper":"https://pith.science/paper/QMYAQVIL"},"agent_actions":{"view_html":"https://pith.science/pith/QMYAQVIL7SLP5FPRB6AR5Y2M6K","download_json":"https://pith.science/pith/QMYAQVIL7SLP5FPRB6AR5Y2M6K.json","view_paper":"https://pith.science/paper/QMYAQVIL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.26518&json=true","fetch_graph":"https://pith.science/api/pith-number/QMYAQVIL7SLP5FPRB6AR5Y2M6K/graph.json","fetch_events":"https://pith.science/api/pith-number/QMYAQVIL7SLP5FPRB6AR5Y2M6K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QMYAQVIL7SLP5FPRB6AR5Y2M6K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QMYAQVIL7SLP5FPRB6AR5Y2M6K/action/storage_attestation","attest_author":"https://pith.science/pith/QMYAQVIL7SLP5FPRB6AR5Y2M6K/action/author_attestation","sign_citation":"https://pith.science/pith/QMYAQVIL7SLP5FPRB6AR5Y2M6K/action/citation_signature","submit_replication":"https://pith.science/pith/QMYAQVIL7SLP5FPRB6AR5Y2M6K/action/replication_record"}},"created_at":"2026-07-30T01:20:46.072573+00:00","updated_at":"2026-07-30T01:20:46.072573+00:00"}