{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5L7PHXDKVR7H3HABAEXXSDT5V5","short_pith_number":"pith:5L7PHXDK","schema_version":"1.0","canonical_sha256":"eafef3dc6aac7e7d9c01012f790e7daf6cfb936326bb330dddebdbb4506f9f9d","source":{"kind":"arxiv","id":"2606.09746","version":1},"attestation_state":"computed","paper":{"title":"Hybrid Robustness Verification for Spatio-Temporal Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alessio Lomuscio, Matthew Wicker, Sherwin Varghese","submitted_at":"2026-06-08T17:06:51Z","abstract_excerpt":"With AI increasingly deployed in safety-critical systems, providing formal robustness guarantees for the underlying models is essential. Existing verification methods either rely on overly conservative approximations or incur prohibitive computational costs. For example, the use of lp-norm perturbations in video settings encodes the belief that the adversary can inject noise in every video frame. In practice, adversarial perturbations exhibit structured spatial and temporal correlations, constrained to lower-dimensional, semantically meaningful subspaces. In this work, we study robustness veri"},"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":"2606.09746","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-08T17:06:51Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6aeed3d7ad3b1312812646a00816c22bc60757031c5616ddd262e4a2ac7e989b","abstract_canon_sha256":"246b5abfa40d8c71e8b7115ec353b1171ea3bded5df438a93c9c43149a669660"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:09:07.331612Z","signature_b64":"JLPwdaNNLDtDERzk2C+GQmvFy94Nw6MdjZkSYB2fIkXt2Qyi2k4zmtYjp4CwTtXOI9p/mZ6z1KJm//Aay9GJAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eafef3dc6aac7e7d9c01012f790e7daf6cfb936326bb330dddebdbb4506f9f9d","last_reissued_at":"2026-06-09T02:09:07.330673Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:09:07.330673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hybrid Robustness Verification for Spatio-Temporal Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alessio Lomuscio, Matthew Wicker, Sherwin Varghese","submitted_at":"2026-06-08T17:06:51Z","abstract_excerpt":"With AI increasingly deployed in safety-critical systems, providing formal robustness guarantees for the underlying models is essential. Existing verification methods either rely on overly conservative approximations or incur prohibitive computational costs. For example, the use of lp-norm perturbations in video settings encodes the belief that the adversary can inject noise in every video frame. In practice, adversarial perturbations exhibit structured spatial and temporal correlations, constrained to lower-dimensional, semantically meaningful subspaces. In this work, we study robustness veri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09746","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/2606.09746/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":"2606.09746","created_at":"2026-06-09T02:09:07.330826+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09746v1","created_at":"2026-06-09T02:09:07.330826+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09746","created_at":"2026-06-09T02:09:07.330826+00:00"},{"alias_kind":"pith_short_12","alias_value":"5L7PHXDKVR7H","created_at":"2026-06-09T02:09:07.330826+00:00"},{"alias_kind":"pith_short_16","alias_value":"5L7PHXDKVR7H3HAB","created_at":"2026-06-09T02:09:07.330826+00:00"},{"alias_kind":"pith_short_8","alias_value":"5L7PHXDK","created_at":"2026-06-09T02:09:07.330826+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/5L7PHXDKVR7H3HABAEXXSDT5V5","json":"https://pith.science/pith/5L7PHXDKVR7H3HABAEXXSDT5V5.json","graph_json":"https://pith.science/api/pith-number/5L7PHXDKVR7H3HABAEXXSDT5V5/graph.json","events_json":"https://pith.science/api/pith-number/5L7PHXDKVR7H3HABAEXXSDT5V5/events.json","paper":"https://pith.science/paper/5L7PHXDK"},"agent_actions":{"view_html":"https://pith.science/pith/5L7PHXDKVR7H3HABAEXXSDT5V5","download_json":"https://pith.science/pith/5L7PHXDKVR7H3HABAEXXSDT5V5.json","view_paper":"https://pith.science/paper/5L7PHXDK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09746&json=true","fetch_graph":"https://pith.science/api/pith-number/5L7PHXDKVR7H3HABAEXXSDT5V5/graph.json","fetch_events":"https://pith.science/api/pith-number/5L7PHXDKVR7H3HABAEXXSDT5V5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5L7PHXDKVR7H3HABAEXXSDT5V5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5L7PHXDKVR7H3HABAEXXSDT5V5/action/storage_attestation","attest_author":"https://pith.science/pith/5L7PHXDKVR7H3HABAEXXSDT5V5/action/author_attestation","sign_citation":"https://pith.science/pith/5L7PHXDKVR7H3HABAEXXSDT5V5/action/citation_signature","submit_replication":"https://pith.science/pith/5L7PHXDKVR7H3HABAEXXSDT5V5/action/replication_record"}},"created_at":"2026-06-09T02:09:07.330826+00:00","updated_at":"2026-06-09T02:09:07.330826+00:00"}