{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UVYTC2F7EJ6ZGTWZL2STJ4NJPU","short_pith_number":"pith:UVYTC2F7","schema_version":"1.0","canonical_sha256":"a5713168bf227d934ed95ea534f1a97d09953fa477d64eb9a6621d0450915ab9","source":{"kind":"arxiv","id":"2502.01896","version":1},"attestation_state":"computed","paper":{"title":"INTACT: Inducing Noise Tolerance through Adversarial Curriculum Training for LiDAR-based Safety-Critical Perception and Autonomy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Amit Ranjan Trivedi, Divake Kumar, Nastaran Darabi, Sina Tayebati","submitted_at":"2025-02-04T00:02:16Z","abstract_excerpt":"In this work, we present INTACT, a novel two-phase framework designed to enhance the robustness of deep neural networks (DNNs) against noisy LiDAR data in safety-critical perception tasks. INTACT combines meta-learning with adversarial curriculum training (ACT) to systematically address challenges posed by data corruption and sparsity in 3D point clouds. The meta-learning phase equips a teacher network with task-agnostic priors, enabling it to generate robust saliency maps that identify critical data regions. The ACT phase leverages these saliency maps to progressively expose a student network"},"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":"2502.01896","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-04T00:02:16Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"39090c07453c625781ad06181e2cd8c2e9ede1e0614e7e9829d36b75d36c1b6a","abstract_canon_sha256":"168ab946a80c5baf71a5f854ba25161151dfd81fb9e18384f70ea4454331de6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:20.813488Z","signature_b64":"s3hwquUiVqCNygWyWUFpbSBdGCKCwQSQ0dRtVUzgpPH1JGiqb9Ao4Et4OasCEXDpdZBYosf6jy8pZ8Lb625RBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5713168bf227d934ed95ea534f1a97d09953fa477d64eb9a6621d0450915ab9","last_reissued_at":"2026-07-05T10:09:20.812983Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:20.812983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"INTACT: Inducing Noise Tolerance through Adversarial Curriculum Training for LiDAR-based Safety-Critical Perception and Autonomy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Amit Ranjan Trivedi, Divake Kumar, Nastaran Darabi, Sina Tayebati","submitted_at":"2025-02-04T00:02:16Z","abstract_excerpt":"In this work, we present INTACT, a novel two-phase framework designed to enhance the robustness of deep neural networks (DNNs) against noisy LiDAR data in safety-critical perception tasks. INTACT combines meta-learning with adversarial curriculum training (ACT) to systematically address challenges posed by data corruption and sparsity in 3D point clouds. The meta-learning phase equips a teacher network with task-agnostic priors, enabling it to generate robust saliency maps that identify critical data regions. The ACT phase leverages these saliency maps to progressively expose a student network"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01896","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/2502.01896/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":"2502.01896","created_at":"2026-07-05T10:09:20.813045+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.01896v1","created_at":"2026-07-05T10:09:20.813045+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01896","created_at":"2026-07-05T10:09:20.813045+00:00"},{"alias_kind":"pith_short_12","alias_value":"UVYTC2F7EJ6Z","created_at":"2026-07-05T10:09:20.813045+00:00"},{"alias_kind":"pith_short_16","alias_value":"UVYTC2F7EJ6ZGTWZ","created_at":"2026-07-05T10:09:20.813045+00:00"},{"alias_kind":"pith_short_8","alias_value":"UVYTC2F7","created_at":"2026-07-05T10:09:20.813045+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.25235","citing_title":"VLM Judges Can Rank but Cannot Score: Task-Dependent Uncertainty in Multimodal Evaluation","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UVYTC2F7EJ6ZGTWZL2STJ4NJPU","json":"https://pith.science/pith/UVYTC2F7EJ6ZGTWZL2STJ4NJPU.json","graph_json":"https://pith.science/api/pith-number/UVYTC2F7EJ6ZGTWZL2STJ4NJPU/graph.json","events_json":"https://pith.science/api/pith-number/UVYTC2F7EJ6ZGTWZL2STJ4NJPU/events.json","paper":"https://pith.science/paper/UVYTC2F7"},"agent_actions":{"view_html":"https://pith.science/pith/UVYTC2F7EJ6ZGTWZL2STJ4NJPU","download_json":"https://pith.science/pith/UVYTC2F7EJ6ZGTWZL2STJ4NJPU.json","view_paper":"https://pith.science/paper/UVYTC2F7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.01896&json=true","fetch_graph":"https://pith.science/api/pith-number/UVYTC2F7EJ6ZGTWZL2STJ4NJPU/graph.json","fetch_events":"https://pith.science/api/pith-number/UVYTC2F7EJ6ZGTWZL2STJ4NJPU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UVYTC2F7EJ6ZGTWZL2STJ4NJPU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UVYTC2F7EJ6ZGTWZL2STJ4NJPU/action/storage_attestation","attest_author":"https://pith.science/pith/UVYTC2F7EJ6ZGTWZL2STJ4NJPU/action/author_attestation","sign_citation":"https://pith.science/pith/UVYTC2F7EJ6ZGTWZL2STJ4NJPU/action/citation_signature","submit_replication":"https://pith.science/pith/UVYTC2F7EJ6ZGTWZL2STJ4NJPU/action/replication_record"}},"created_at":"2026-07-05T10:09:20.813045+00:00","updated_at":"2026-07-05T10:09:20.813045+00:00"}