{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BI5BEGIZEEBGBZUOF3WMA5DAD2","short_pith_number":"pith:BI5BEGIZ","canonical_record":{"source":{"id":"2606.03954","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T17:42:17Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"8e89bb5780e438982b3e9e6812545b51bdaa71d57eb62336d348e33b0f570fc8","abstract_canon_sha256":"a3786bf39a41a28acaed662b832c8a9d69deaa6b6d5e48b272fe72cc4af56000"},"schema_version":"1.0"},"canonical_sha256":"0a3a121919210260e68e2eecc074601e883d630671d993d607b60099611b7e4d","source":{"kind":"arxiv","id":"2606.03954","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03954","created_at":"2026-06-03T02:06:07Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03954v1","created_at":"2026-06-03T02:06:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03954","created_at":"2026-06-03T02:06:07Z"},{"alias_kind":"pith_short_12","alias_value":"BI5BEGIZEEBG","created_at":"2026-06-03T02:06:07Z"},{"alias_kind":"pith_short_16","alias_value":"BI5BEGIZEEBGBZUO","created_at":"2026-06-03T02:06:07Z"},{"alias_kind":"pith_short_8","alias_value":"BI5BEGIZ","created_at":"2026-06-03T02:06:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BI5BEGIZEEBGBZUOF3WMA5DAD2","target":"record","payload":{"canonical_record":{"source":{"id":"2606.03954","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T17:42:17Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"8e89bb5780e438982b3e9e6812545b51bdaa71d57eb62336d348e33b0f570fc8","abstract_canon_sha256":"a3786bf39a41a28acaed662b832c8a9d69deaa6b6d5e48b272fe72cc4af56000"},"schema_version":"1.0"},"canonical_sha256":"0a3a121919210260e68e2eecc074601e883d630671d993d607b60099611b7e4d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T02:06:07.885273Z","signature_b64":"kOdbjcV9pugBo1wMcuXwi7izvYMiNpLQlGUd+ES1kBYmZGibShC8VfKyLzn/oq8QEUh66p5oHDwVq3B1GGlFDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a3a121919210260e68e2eecc074601e883d630671d993d607b60099611b7e4d","last_reissued_at":"2026-06-03T02:06:07.884873Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T02:06:07.884873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.03954","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":"2026-06-03T02:06:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xys72WBWHph+wNp/Vp5/afiQk1FANv9GpfDLBKLYotWHmTvwacdw1vlCqhpydrELEPai2LgUyJJgPah86dfyAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T11:00:26.179183Z"},"content_sha256":"8b9acb7693f06c9de2c79197a61619e87c298230cf5550dde67d8d314f520263","schema_version":"1.0","event_id":"sha256:8b9acb7693f06c9de2c79197a61619e87c298230cf5550dde67d8d314f520263"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BI5BEGIZEEBGBZUOF3WMA5DAD2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VLESA: Vision-Language Embodied Safety Agent for Human Activity Monitoring","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Alexander Robey, Changliu Liu, Hanjiang Hu, Jiaxing Li, Na Li, Xusheng Luo, Yebin Wang, Yiyuan Pan","submitted_at":"2026-06-02T17:42:17Z","abstract_excerpt":"As AI systems increasingly assist humans in physical tasks, ensuring safety becomes paramount -- physical actions carry immediate and irreversible consequences that digital errors do not. We introduce the Vision-Language Embodied Safety Agent (VLESA), a framework that monitors human activities from egocentric video and triggers real-time safety interventions when dangerous actions are predicted. VLESA addresses intent-dependent safety where identical actions can be safe or dangerous depending on context. A dataset pairing egocentric frames with goal-conditioned safety annotations is introduced"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03954","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/2606.03954/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":"2026-06-03T02:06:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YOj7BjPg4uvS5cZcughufAfJX+vvZpjt4409u80vs2dFTM+1IlMCG9lm0jYxV9yBlp1Hae8LCE7hb6WeSv5/Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T11:00:26.179591Z"},"content_sha256":"8de1f7228afb21c6eedf594eeecb65454c84540d8417cf3a71577480a60514dc","schema_version":"1.0","event_id":"sha256:8de1f7228afb21c6eedf594eeecb65454c84540d8417cf3a71577480a60514dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BI5BEGIZEEBGBZUOF3WMA5DAD2/bundle.json","state_url":"https://pith.science/pith/BI5BEGIZEEBGBZUOF3WMA5DAD2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BI5BEGIZEEBGBZUOF3WMA5DAD2/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":"2026-06-05T11:00:26Z","links":{"resolver":"https://pith.science/pith/BI5BEGIZEEBGBZUOF3WMA5DAD2","bundle":"https://pith.science/pith/BI5BEGIZEEBGBZUOF3WMA5DAD2/bundle.json","state":"https://pith.science/pith/BI5BEGIZEEBGBZUOF3WMA5DAD2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BI5BEGIZEEBGBZUOF3WMA5DAD2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BI5BEGIZEEBGBZUOF3WMA5DAD2","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":"a3786bf39a41a28acaed662b832c8a9d69deaa6b6d5e48b272fe72cc4af56000","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T17:42:17Z","title_canon_sha256":"8e89bb5780e438982b3e9e6812545b51bdaa71d57eb62336d348e33b0f570fc8"},"schema_version":"1.0","source":{"id":"2606.03954","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03954","created_at":"2026-06-03T02:06:07Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03954v1","created_at":"2026-06-03T02:06:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03954","created_at":"2026-06-03T02:06:07Z"},{"alias_kind":"pith_short_12","alias_value":"BI5BEGIZEEBG","created_at":"2026-06-03T02:06:07Z"},{"alias_kind":"pith_short_16","alias_value":"BI5BEGIZEEBGBZUO","created_at":"2026-06-03T02:06:07Z"},{"alias_kind":"pith_short_8","alias_value":"BI5BEGIZ","created_at":"2026-06-03T02:06:07Z"}],"graph_snapshots":[{"event_id":"sha256:8de1f7228afb21c6eedf594eeecb65454c84540d8417cf3a71577480a60514dc","target":"graph","created_at":"2026-06-03T02:06:07Z","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/2606.03954/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As AI systems increasingly assist humans in physical tasks, ensuring safety becomes paramount -- physical actions carry immediate and irreversible consequences that digital errors do not. We introduce the Vision-Language Embodied Safety Agent (VLESA), a framework that monitors human activities from egocentric video and triggers real-time safety interventions when dangerous actions are predicted. VLESA addresses intent-dependent safety where identical actions can be safe or dangerous depending on context. A dataset pairing egocentric frames with goal-conditioned safety annotations is introduced","authors_text":"Alexander Robey, Changliu Liu, Hanjiang Hu, Jiaxing Li, Na Li, Xusheng Luo, Yebin Wang, Yiyuan Pan","cross_cats":["cs.LG","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T17:42:17Z","title":"VLESA: Vision-Language Embodied Safety Agent for Human Activity Monitoring"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03954","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":"sha256:8b9acb7693f06c9de2c79197a61619e87c298230cf5550dde67d8d314f520263","target":"record","created_at":"2026-06-03T02:06:07Z","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":"a3786bf39a41a28acaed662b832c8a9d69deaa6b6d5e48b272fe72cc4af56000","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T17:42:17Z","title_canon_sha256":"8e89bb5780e438982b3e9e6812545b51bdaa71d57eb62336d348e33b0f570fc8"},"schema_version":"1.0","source":{"id":"2606.03954","kind":"arxiv","version":1}},"canonical_sha256":"0a3a121919210260e68e2eecc074601e883d630671d993d607b60099611b7e4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a3a121919210260e68e2eecc074601e883d630671d993d607b60099611b7e4d","first_computed_at":"2026-06-03T02:06:07.884873Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T02:06:07.884873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kOdbjcV9pugBo1wMcuXwi7izvYMiNpLQlGUd+ES1kBYmZGibShC8VfKyLzn/oq8QEUh66p5oHDwVq3B1GGlFDg==","signature_status":"signed_v1","signed_at":"2026-06-03T02:06:07.885273Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03954","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b9acb7693f06c9de2c79197a61619e87c298230cf5550dde67d8d314f520263","sha256:8de1f7228afb21c6eedf594eeecb65454c84540d8417cf3a71577480a60514dc"],"state_sha256":"74c4f4823acd39722642c4628a91c8ad9b26ce35f826d4468f6ccd0090e96a6a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oXUi95edLi7UA6y6AQ4x4ZmuXukE8VNBNH1PQj8eCS91zxVNerpNsc/p7q7+bkIYAG9JyCGr7xaMyns94tVJBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T11:00:26.181777Z","bundle_sha256":"2d7ecb84e7cba9f4f5f281f9e55665bfc19e73119a054d506f4d6d8b7c9cc605"}}