{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LWY2BP6UWURWV2VH2BVMDM2Z43","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":"6bda4390a62b3dcb19689d10f918a7aeee2f1b97c6f90879a9e25690734f1ab8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T16:35:50Z","title_canon_sha256":"9b61a8c5369849bf6cfe4659d3781b1f53e955d52008b021b186021ee9bbf4b4"},"schema_version":"1.0","source":{"id":"2605.13755","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13755","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13755v1","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13755","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"pith_short_12","alias_value":"LWY2BP6UWURW","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"LWY2BP6UWURWV2VH","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"LWY2BP6U","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:ed72994e2e355c63be9a4450a553845876be69fb4359a7884afdfaf6b3c8dd9b","target":"graph","created_at":"2026-05-18T02:44:16Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our findings demonstrate that controlled synthetic diversification improves robustness in 2D detection while revealing the sensitivity of 3D perception models to geometric domain gaps."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That automatically mapping StyleGAN2-generated textures onto 3D meshes produces appearance variations that are realistic enough to improve robustness without introducing mapping artifacts or distribution shifts that undermine the detection gains."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Generative texture synthesis from StyleGAN2 diversifies 3D pedestrian assets from a single base model, improving robustness in 2D object detection while exposing 3D perception models' sensitivity to geometric domain gaps."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Synthesizing diverse facial textures on one 3D pedestrian base asset improves 2D detection robustness but exposes geometric sensitivities in 3D point-cloud models."}],"snapshot_sha256":"59b54de15a3e58d0264a3c14d1f379f1421bc06de610017688dc3987ea6a9d45"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"In recent years, autonomous driving has significantly in creased the demand for high-quality data to train 2D and 3D perception models for safety-critical scenarios. Real world datasets struggle to meet this demand as require ments continuously evolve and large-scale annotated data collection remains costly and time-consuming making syn thetic data a scalable, practical and controllable alterna tive. Pedestrian detection is among the most safety-critical tasks in autonomous driving. In this paper, we propose a simple yet effective method for scaling variability in 3D pedestrian assets for synt","authors_text":"Ahmed Abdullah, Arka Bhowmick, Enes Ozeren, Oliver Wasenmuller","cross_cats":[],"headline":"Synthesizing diverse facial textures on one 3D pedestrian base asset improves 2D detection robustness but exposes geometric sensitivities in 3D point-cloud models.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T16:35:50Z","title":"Generative Texture Diversification of 3D Pedestrians for Robust Autonomous Driving Perception"},"references":{"count":26,"internal_anchors":2,"resolved_work":26,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Boosting few-shot detection with large language models and layout-to-image synthesis","work_id":"9a31abb6-b769-4afa-9f76-d5de5b4e15ff","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Ffhq-uv: Normalized facial uv-texture dataset for 3d face reconstruction, 2023","work_id":"3ecbd10b-5b67-451f-8ac5-8e2de420be4b","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Vir- tual kitti 2, 2020","work_id":"552b577f-3178-4a91-9394-ca9226c6815c","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Data augmentation for object detec- tion via controllable diffusion models","work_id":"a9648b9d-a7e9-4da6-9687-f6617ee43b92","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Virtual worlds as proxy for multi-object tracking anal- ysis, 2016","work_id":"328f0cc1-6e52-47f6-bdf5-c43a0cffbe38","year":2016}],"snapshot_sha256":"b37c88ca1ad47d5ec2cd340e36134ef6ec5f6b23415fe701b1a804930baa9ba4"},"source":{"id":"2605.13755","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:37:36.458101Z","id":"7d359241-dd10-4671-99b1-83bd11162beb","model_set":{"reader":"grok-4.3"},"one_line_summary":"Generative texture synthesis from StyleGAN2 diversifies 3D pedestrian assets from a single base model, improving robustness in 2D object detection while exposing 3D perception models' sensitivity to geometric domain gaps.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Synthesizing diverse facial textures on one 3D pedestrian base asset improves 2D detection robustness but exposes geometric sensitivities in 3D point-cloud models.","strongest_claim":"Our findings demonstrate that controlled synthetic diversification improves robustness in 2D detection while revealing the sensitivity of 3D perception models to geometric domain gaps.","weakest_assumption":"That automatically mapping StyleGAN2-generated textures onto 3D meshes produces appearance variations that are realistic enough to improve robustness without introducing mapping artifacts or distribution shifts that undermine the detection gains."}},"verdict_id":"7d359241-dd10-4671-99b1-83bd11162beb"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:37e7af22c30ce4913e024cc4e47e3b01b9c26b424af25fad5846cfe8034de3ac","target":"record","created_at":"2026-05-18T02:44:16Z","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":"6bda4390a62b3dcb19689d10f918a7aeee2f1b97c6f90879a9e25690734f1ab8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T16:35:50Z","title_canon_sha256":"9b61a8c5369849bf6cfe4659d3781b1f53e955d52008b021b186021ee9bbf4b4"},"schema_version":"1.0","source":{"id":"2605.13755","kind":"arxiv","version":1}},"canonical_sha256":"5db1a0bfd4b5236aeaa7d06ac1b359e6f93c8692fa64519b4d638fa4a89ef43a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5db1a0bfd4b5236aeaa7d06ac1b359e6f93c8692fa64519b4d638fa4a89ef43a","first_computed_at":"2026-05-18T02:44:16.345625Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:16.345625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J3j4xlZ3ivtS+0ZpSl0tgrYsPFmvIoTBqxxezW2llu7rke6ojou3P/SvQk9Dt+XxR22O0XdAmZWVW9Ivnp2uAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:16.346096Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13755","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37e7af22c30ce4913e024cc4e47e3b01b9c26b424af25fad5846cfe8034de3ac","sha256:ed72994e2e355c63be9a4450a553845876be69fb4359a7884afdfaf6b3c8dd9b"],"state_sha256":"521a248c69954543f2107100d529f0fafa8034876392858852ea90a2cb9ab472"}