{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3BS4ZQTCZ4QU4RYJKPGPZ4EFQ3","short_pith_number":"pith:3BS4ZQTC","schema_version":"1.0","canonical_sha256":"d865ccc262cf214e470953ccfcf08586fead62c2444cd3bd683beb8199f5712b","source":{"kind":"arxiv","id":"2607.00218","version":1},"attestation_state":"computed","paper":{"title":"EgoSafetyBench: A Diagnostic Egocentric Video Benchmark for Evaluating Embodied VLMs as Runtime Safety Guards","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Arth Singh, Chaeyun Kim, Dasol Choi, Haon Park, Mijin Koo, Siddhant Panpatil","submitted_at":"2026-06-30T21:50:49Z","abstract_excerpt":"Vision-language models (VLMs) are now proposed as runtime safety guards for embodied agents in homes and factories. A deployable guard must catch genuinely unsafe situations while avoiding unnecessary intervention on routine but superficially alarming activity, a distinction that binary safety benchmarks obscure. We introduce EgoSafetyBench, an egocentric video benchmark of 1,200 robot-view scenarios annotated at half-second granularity, to evaluate VLMs as streaming guards across two tracks. The situational track (800 scenarios) spans four families, from routine and safe-but-suspicious scenes"},"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":"2607.00218","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T21:50:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"670dbce44a3641e7ae0536b244f26c3615874c40c3d98ab636e192b76757f823","abstract_canon_sha256":"5b1f6b80bb1a198df2a389e79a89f62e0ac3807a41a6d7c109041147bb969844"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T00:18:39.668858Z","signature_b64":"1M7TeFdf/rPgXhw647yvcsnuE9UXCjN4NTHo7TBe3Fdy9BOuuUHxyOLp1SZAc2cV0Cz62ePr2i9JPsZeJdrlBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d865ccc262cf214e470953ccfcf08586fead62c2444cd3bd683beb8199f5712b","last_reissued_at":"2026-07-02T00:18:39.667957Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T00:18:39.667957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EgoSafetyBench: A Diagnostic Egocentric Video Benchmark for Evaluating Embodied VLMs as Runtime Safety Guards","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Arth Singh, Chaeyun Kim, Dasol Choi, Haon Park, Mijin Koo, Siddhant Panpatil","submitted_at":"2026-06-30T21:50:49Z","abstract_excerpt":"Vision-language models (VLMs) are now proposed as runtime safety guards for embodied agents in homes and factories. A deployable guard must catch genuinely unsafe situations while avoiding unnecessary intervention on routine but superficially alarming activity, a distinction that binary safety benchmarks obscure. We introduce EgoSafetyBench, an egocentric video benchmark of 1,200 robot-view scenarios annotated at half-second granularity, to evaluate VLMs as streaming guards across two tracks. The situational track (800 scenarios) spans four families, from routine and safe-but-suspicious scenes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00218","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/2607.00218/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":"2607.00218","created_at":"2026-07-02T00:18:39.668058+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00218v1","created_at":"2026-07-02T00:18:39.668058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00218","created_at":"2026-07-02T00:18:39.668058+00:00"},{"alias_kind":"pith_short_12","alias_value":"3BS4ZQTCZ4QU","created_at":"2026-07-02T00:18:39.668058+00:00"},{"alias_kind":"pith_short_16","alias_value":"3BS4ZQTCZ4QU4RYJ","created_at":"2026-07-02T00:18:39.668058+00:00"},{"alias_kind":"pith_short_8","alias_value":"3BS4ZQTC","created_at":"2026-07-02T00:18:39.668058+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/3BS4ZQTCZ4QU4RYJKPGPZ4EFQ3","json":"https://pith.science/pith/3BS4ZQTCZ4QU4RYJKPGPZ4EFQ3.json","graph_json":"https://pith.science/api/pith-number/3BS4ZQTCZ4QU4RYJKPGPZ4EFQ3/graph.json","events_json":"https://pith.science/api/pith-number/3BS4ZQTCZ4QU4RYJKPGPZ4EFQ3/events.json","paper":"https://pith.science/paper/3BS4ZQTC"},"agent_actions":{"view_html":"https://pith.science/pith/3BS4ZQTCZ4QU4RYJKPGPZ4EFQ3","download_json":"https://pith.science/pith/3BS4ZQTCZ4QU4RYJKPGPZ4EFQ3.json","view_paper":"https://pith.science/paper/3BS4ZQTC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00218&json=true","fetch_graph":"https://pith.science/api/pith-number/3BS4ZQTCZ4QU4RYJKPGPZ4EFQ3/graph.json","fetch_events":"https://pith.science/api/pith-number/3BS4ZQTCZ4QU4RYJKPGPZ4EFQ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3BS4ZQTCZ4QU4RYJKPGPZ4EFQ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3BS4ZQTCZ4QU4RYJKPGPZ4EFQ3/action/storage_attestation","attest_author":"https://pith.science/pith/3BS4ZQTCZ4QU4RYJKPGPZ4EFQ3/action/author_attestation","sign_citation":"https://pith.science/pith/3BS4ZQTCZ4QU4RYJKPGPZ4EFQ3/action/citation_signature","submit_replication":"https://pith.science/pith/3BS4ZQTCZ4QU4RYJKPGPZ4EFQ3/action/replication_record"}},"created_at":"2026-07-02T00:18:39.668058+00:00","updated_at":"2026-07-02T00:18:39.668058+00:00"}