{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PVLQVQKYLTYAHGYKHWY5NHPZ5N","short_pith_number":"pith:PVLQVQKY","schema_version":"1.0","canonical_sha256":"7d570ac1585cf0039b0a3db1d69df9eb74439af5e1c911c9feaaeabb33529f16","source":{"kind":"arxiv","id":"2412.04455","version":3},"attestation_state":"computed","paper":{"title":"Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Cheng Chi, Enshen Zhou, He Wang, Lu Sheng, Qi Su, Tiejun Huang, Zhizheng Zhang, Zhongyuan Wang","submitted_at":"2024-12-05T18:58:27Z","abstract_excerpt":"Automatic detection and prevention of open-set failures are crucial in closed-loop robotic systems. Recent studies often struggle to simultaneously identify unexpected failures reactively after they occur and prevent foreseeable ones proactively. To this end, we propose Code-as-Monitor (CaM), a novel paradigm leveraging the vision-language model (VLM) for both open-set reactive and proactive failure detection. The core of our method is to formulate both tasks as a unified set of spatio-temporal constraint satisfaction problems and use VLM-generated code to evaluate them for real-time monitorin"},"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":"2412.04455","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-05T18:58:27Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"10a4b4f4386c04a677e29b6b511d52a635cd9590336f17af45852b9e94e1340d","abstract_canon_sha256":"903d879d116b676474291d6382f611177d5af31c465da74a9201277ba8a3edb8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:32.474407Z","signature_b64":"6lz6gquq2w9uy3Ds4PVsN6ODbT3GsDbNfFTF88Tc5cUrKNBL9g2+/eaDWFiJYJVhEG/0N2Pl5qtn8i013BRuAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d570ac1585cf0039b0a3db1d69df9eb74439af5e1c911c9feaaeabb33529f16","last_reissued_at":"2026-07-05T10:36:32.473473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:32.473473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Cheng Chi, Enshen Zhou, He Wang, Lu Sheng, Qi Su, Tiejun Huang, Zhizheng Zhang, Zhongyuan Wang","submitted_at":"2024-12-05T18:58:27Z","abstract_excerpt":"Automatic detection and prevention of open-set failures are crucial in closed-loop robotic systems. Recent studies often struggle to simultaneously identify unexpected failures reactively after they occur and prevent foreseeable ones proactively. To this end, we propose Code-as-Monitor (CaM), a novel paradigm leveraging the vision-language model (VLM) for both open-set reactive and proactive failure detection. The core of our method is to formulate both tasks as a unified set of spatio-temporal constraint satisfaction problems and use VLM-generated code to evaluate them for real-time monitorin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04455","kind":"arxiv","version":3},"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/2412.04455/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":"2412.04455","created_at":"2026-07-05T10:36:32.473585+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04455v3","created_at":"2026-07-05T10:36:32.473585+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04455","created_at":"2026-07-05T10:36:32.473585+00:00"},{"alias_kind":"pith_short_12","alias_value":"PVLQVQKYLTYA","created_at":"2026-07-05T10:36:32.473585+00:00"},{"alias_kind":"pith_short_16","alias_value":"PVLQVQKYLTYAHGYK","created_at":"2026-07-05T10:36:32.473585+00:00"},{"alias_kind":"pith_short_8","alias_value":"PVLQVQKY","created_at":"2026-07-05T10:36:32.473585+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23085","citing_title":"Foresight: Failure Detection for Long-Horizon Robotic Manipulation with Action-Conditioned World Model Latents","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PVLQVQKYLTYAHGYKHWY5NHPZ5N","json":"https://pith.science/pith/PVLQVQKYLTYAHGYKHWY5NHPZ5N.json","graph_json":"https://pith.science/api/pith-number/PVLQVQKYLTYAHGYKHWY5NHPZ5N/graph.json","events_json":"https://pith.science/api/pith-number/PVLQVQKYLTYAHGYKHWY5NHPZ5N/events.json","paper":"https://pith.science/paper/PVLQVQKY"},"agent_actions":{"view_html":"https://pith.science/pith/PVLQVQKYLTYAHGYKHWY5NHPZ5N","download_json":"https://pith.science/pith/PVLQVQKYLTYAHGYKHWY5NHPZ5N.json","view_paper":"https://pith.science/paper/PVLQVQKY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04455&json=true","fetch_graph":"https://pith.science/api/pith-number/PVLQVQKYLTYAHGYKHWY5NHPZ5N/graph.json","fetch_events":"https://pith.science/api/pith-number/PVLQVQKYLTYAHGYKHWY5NHPZ5N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PVLQVQKYLTYAHGYKHWY5NHPZ5N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PVLQVQKYLTYAHGYKHWY5NHPZ5N/action/storage_attestation","attest_author":"https://pith.science/pith/PVLQVQKYLTYAHGYKHWY5NHPZ5N/action/author_attestation","sign_citation":"https://pith.science/pith/PVLQVQKYLTYAHGYKHWY5NHPZ5N/action/citation_signature","submit_replication":"https://pith.science/pith/PVLQVQKYLTYAHGYKHWY5NHPZ5N/action/replication_record"}},"created_at":"2026-07-05T10:36:32.473585+00:00","updated_at":"2026-07-05T10:36:32.473585+00:00"}