{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AAPGKNC2WTWU52PZLW75SPXX46","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":"a7c5cf66b9bc1aa7da1169cf4cd111ef8ded47b41421d6b58e8e016fc9d0c5c6","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-26T17:59:14Z","title_canon_sha256":"1e82796679b63cec0420a92f86337d5f38dc042bfa88b25f21ab375257b96709"},"schema_version":"1.0","source":{"id":"2506.21547","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21547","created_at":"2026-07-05T11:27:47Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21547v1","created_at":"2026-07-05T11:27:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21547","created_at":"2026-07-05T11:27:47Z"},{"alias_kind":"pith_short_12","alias_value":"AAPGKNC2WTWU","created_at":"2026-07-05T11:27:47Z"},{"alias_kind":"pith_short_16","alias_value":"AAPGKNC2WTWU52PZ","created_at":"2026-07-05T11:27:47Z"},{"alias_kind":"pith_short_8","alias_value":"AAPGKNC2","created_at":"2026-07-05T11:27:47Z"}],"graph_snapshots":[{"event_id":"sha256:c9e580746436e3fc9379264fea49b99a3712dc70a616d428d666ebbc65903ccf","target":"graph","created_at":"2026-07-05T11:27:47Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.21547/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present SAM4D, a multi-modal and temporal foundation model designed for promptable segmentation across camera and LiDAR streams. Unified Multi-modal Positional Encoding (UMPE) is introduced to align camera and LiDAR features in a shared 3D space, enabling seamless cross-modal prompting and interaction. Additionally, we propose Motion-aware Cross-modal Memory Attention (MCMA), which leverages ego-motion compensation to enhance temporal consistency and long-horizon feature retrieval, ensuring robust segmentation across dynamically changing autonomous driving scenes. To avoid annotation bottle","authors_text":"Chunyong Hu, Jianke Zhu, Jianyun Xu, Qiang Li, Sheng Yang, Song Wang, Ziqian Ni","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-26T17:59:14Z","title":"SAM4D: Segment Anything in Camera and LiDAR Streams"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21547","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:db444627ae910111023f570fdc8014ad453eef0f02d406d051c4acfa179be152","target":"record","created_at":"2026-07-05T11:27:47Z","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":"a7c5cf66b9bc1aa7da1169cf4cd111ef8ded47b41421d6b58e8e016fc9d0c5c6","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-26T17:59:14Z","title_canon_sha256":"1e82796679b63cec0420a92f86337d5f38dc042bfa88b25f21ab375257b96709"},"schema_version":"1.0","source":{"id":"2506.21547","kind":"arxiv","version":1}},"canonical_sha256":"001e65345ab4ed4ee9f95dbfd93ef7e7b1aee60300c497f72c81c3ba4d5acf06","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"001e65345ab4ed4ee9f95dbfd93ef7e7b1aee60300c497f72c81c3ba4d5acf06","first_computed_at":"2026-07-05T11:27:47.622726Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:47.622726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jOUiekwZqyxumGQkH0r2D8oGxcuav3g0mD+V/lWOaHavRxUZY7aPkgrUYPmIgpp2CZrOkX7fuywUV9dcs4g9Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:47.623268Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.21547","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db444627ae910111023f570fdc8014ad453eef0f02d406d051c4acfa179be152","sha256:c9e580746436e3fc9379264fea49b99a3712dc70a616d428d666ebbc65903ccf"],"state_sha256":"a14e440225e3adbdb34a94350d95cd2346cac47cb0bf79f22fc998bc99241bc0"}