{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XT75VE5SM46P2RQNRZLIM3G5BS","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":"3193fd5c8719d9ecd566989a0123a2d619336c80c12961ef246a656c4dc10317","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-12T15:53:45Z","title_canon_sha256":"f7c6db957c10e2bb8ed8c83bd7562a0f85584bbd0031dd083d11708d2fe1e715"},"schema_version":"1.0","source":{"id":"2508.09032","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.09032","created_at":"2026-07-05T11:52:38Z"},{"alias_kind":"arxiv_version","alias_value":"2508.09032v1","created_at":"2026-07-05T11:52:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09032","created_at":"2026-07-05T11:52:38Z"},{"alias_kind":"pith_short_12","alias_value":"XT75VE5SM46P","created_at":"2026-07-05T11:52:38Z"},{"alias_kind":"pith_short_16","alias_value":"XT75VE5SM46P2RQN","created_at":"2026-07-05T11:52:38Z"},{"alias_kind":"pith_short_8","alias_value":"XT75VE5S","created_at":"2026-07-05T11:52:38Z"}],"graph_snapshots":[{"event_id":"sha256:3f597f288360b6dc831c1abd60fd8041e62307ea80cac016a4f7fa4c46545d3a","target":"graph","created_at":"2026-07-05T11:52:38Z","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/2508.09032/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language-Action models have demonstrated remarkable capabilities in predicting agent movements within virtual environments and real-world scenarios based on visual observations and textual instructions. Although recent research has focused on enhancing spatial and temporal understanding independently, this paper presents a novel approach that integrates both aspects through visual prompting. We introduce a method that projects visual traces of key points from observations onto depth maps, enabling models to capture both spatial and temporal information simultaneously. The experiments in","authors_text":"Aleksandr I. Panov, Alexey K. Kovalev, Maxim A. Patratskiy","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-12T15:53:45Z","title":"Spatial Traces: Enhancing VLA Models with Spatial-Temporal Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09032","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:abc3a46dda64187bad8939894283ddda4096329627cb1b386482500cf208a4f6","target":"record","created_at":"2026-07-05T11:52:38Z","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":"3193fd5c8719d9ecd566989a0123a2d619336c80c12961ef246a656c4dc10317","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-12T15:53:45Z","title_canon_sha256":"f7c6db957c10e2bb8ed8c83bd7562a0f85584bbd0031dd083d11708d2fe1e715"},"schema_version":"1.0","source":{"id":"2508.09032","kind":"arxiv","version":1}},"canonical_sha256":"bcffda93b2673cfd460d8e56866cdd0ca2b43b5fce29b9b221bac324dd4ff63a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bcffda93b2673cfd460d8e56866cdd0ca2b43b5fce29b9b221bac324dd4ff63a","first_computed_at":"2026-07-05T11:52:38.598893Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:52:38.598893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xy96sf+t+kuOQQLPkj2RttISCcgn0oAv2wbjbdg+h1El8B6SJ/tRnm0Na0xVIPq6oU7p71xgMl7cRi/mYqdmDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:52:38.599390Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.09032","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:abc3a46dda64187bad8939894283ddda4096329627cb1b386482500cf208a4f6","sha256:3f597f288360b6dc831c1abd60fd8041e62307ea80cac016a4f7fa4c46545d3a"],"state_sha256":"f695b76e91b1663a063afe62c34a3322874d25d9b9391fdab9e43b1bfa5da30e"}