{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XP3DHG33N5ZGJPKT2CALUFVTSK","short_pith_number":"pith:XP3DHG33","schema_version":"1.0","canonical_sha256":"bbf6339b7b6f7264bd53d080ba16b3928f7332f26a39057b8720bb74b313dbfb","source":{"kind":"arxiv","id":"2505.13131","version":1},"attestation_state":"computed","paper":{"title":"Constraint-Aware Diffusion Guidance for Robotics: Real-Time Obstacle Avoidance for Autonomous Racing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Andrea Carron, Hao Ma, Melanie Zeilinger, Michael Muehlebach, Sabrina Bodmer","submitted_at":"2025-05-19T14:00:17Z","abstract_excerpt":"Diffusion models hold great potential in robotics due to their ability to capture complex, high-dimensional data distributions. However, their lack of constraint-awareness limits their deployment in safety-critical applications. We propose Constraint-Aware Diffusion Guidance (CoDiG), a data-efficient and general-purpose framework that integrates barrier functions into the denoising process, guiding diffusion sampling toward constraint-satisfying outputs. CoDiG enables constraint satisfaction even with limited training data and generalizes across tasks. We evaluate our framework in the challeng"},"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":"2505.13131","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-05-19T14:00:17Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"8fb369374dff0cf4cd600ac90904c5b27c0004c4f14cf9d0865e7281dc0598f1","abstract_canon_sha256":"2c4e1162e136935a0644e6ff0127df72758e0411896526c77cbc8dd45c683dbe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:25.631137Z","signature_b64":"r67FNjO+C7eoOuRzAAQGQ3iRS555/64yk+Q3+i4687KITk9cHhwUbKlHP9y0gZaRkERTkOAjn/srHyVLtxN6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbf6339b7b6f7264bd53d080ba16b3928f7332f26a39057b8720bb74b313dbfb","last_reissued_at":"2026-07-05T11:05:25.630652Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:25.630652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Constraint-Aware Diffusion Guidance for Robotics: Real-Time Obstacle Avoidance for Autonomous Racing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Andrea Carron, Hao Ma, Melanie Zeilinger, Michael Muehlebach, Sabrina Bodmer","submitted_at":"2025-05-19T14:00:17Z","abstract_excerpt":"Diffusion models hold great potential in robotics due to their ability to capture complex, high-dimensional data distributions. However, their lack of constraint-awareness limits their deployment in safety-critical applications. We propose Constraint-Aware Diffusion Guidance (CoDiG), a data-efficient and general-purpose framework that integrates barrier functions into the denoising process, guiding diffusion sampling toward constraint-satisfying outputs. CoDiG enables constraint satisfaction even with limited training data and generalizes across tasks. We evaluate our framework in the challeng"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13131","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/2505.13131/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":"2505.13131","created_at":"2026-07-05T11:05:25.630712+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.13131v1","created_at":"2026-07-05T11:05:25.630712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13131","created_at":"2026-07-05T11:05:25.630712+00:00"},{"alias_kind":"pith_short_12","alias_value":"XP3DHG33N5ZG","created_at":"2026-07-05T11:05:25.630712+00:00"},{"alias_kind":"pith_short_16","alias_value":"XP3DHG33N5ZGJPKT","created_at":"2026-07-05T11:05:25.630712+00:00"},{"alias_kind":"pith_short_8","alias_value":"XP3DHG33","created_at":"2026-07-05T11:05:25.630712+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12965","citing_title":"EmbodiSteer: Steering Embodiment-Agnostic Visuomotor Policies with Joint-Space Guidance for Zero-Shot Cross-Embodiment Deployment","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28726","citing_title":"How VLAs Fail Differently: Black-Box Action Monitoring Reveals Architecture-Specific Failure Signatures","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02777","citing_title":"Decoupled Guidance Diffusion for Adaptive Offline Safe Reinforcement Learning","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XP3DHG33N5ZGJPKT2CALUFVTSK","json":"https://pith.science/pith/XP3DHG33N5ZGJPKT2CALUFVTSK.json","graph_json":"https://pith.science/api/pith-number/XP3DHG33N5ZGJPKT2CALUFVTSK/graph.json","events_json":"https://pith.science/api/pith-number/XP3DHG33N5ZGJPKT2CALUFVTSK/events.json","paper":"https://pith.science/paper/XP3DHG33"},"agent_actions":{"view_html":"https://pith.science/pith/XP3DHG33N5ZGJPKT2CALUFVTSK","download_json":"https://pith.science/pith/XP3DHG33N5ZGJPKT2CALUFVTSK.json","view_paper":"https://pith.science/paper/XP3DHG33","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.13131&json=true","fetch_graph":"https://pith.science/api/pith-number/XP3DHG33N5ZGJPKT2CALUFVTSK/graph.json","fetch_events":"https://pith.science/api/pith-number/XP3DHG33N5ZGJPKT2CALUFVTSK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XP3DHG33N5ZGJPKT2CALUFVTSK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XP3DHG33N5ZGJPKT2CALUFVTSK/action/storage_attestation","attest_author":"https://pith.science/pith/XP3DHG33N5ZGJPKT2CALUFVTSK/action/author_attestation","sign_citation":"https://pith.science/pith/XP3DHG33N5ZGJPKT2CALUFVTSK/action/citation_signature","submit_replication":"https://pith.science/pith/XP3DHG33N5ZGJPKT2CALUFVTSK/action/replication_record"}},"created_at":"2026-07-05T11:05:25.630712+00:00","updated_at":"2026-07-05T11:05:25.630712+00:00"}