{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XT75VE5SM46P2RQNRZLIM3G5BS","short_pith_number":"pith:XT75VE5S","schema_version":"1.0","canonical_sha256":"bcffda93b2673cfd460d8e56866cdd0ca2b43b5fce29b9b221bac324dd4ff63a","source":{"kind":"arxiv","id":"2508.09032","version":1},"attestation_state":"computed","paper":{"title":"Spatial Traces: Enhancing VLA Models with Spatial-Temporal Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Aleksandr I. Panov, Alexey K. Kovalev, Maxim A. Patratskiy","submitted_at":"2025-08-12T15:53:45Z","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"},"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":"2508.09032","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-12T15:53:45Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"f7c6db957c10e2bb8ed8c83bd7562a0f85584bbd0031dd083d11708d2fe1e715","abstract_canon_sha256":"3193fd5c8719d9ecd566989a0123a2d619336c80c12961ef246a656c4dc10317"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:38.599390Z","signature_b64":"xy96sf+t+kuOQQLPkj2RttISCcgn0oAv2wbjbdg+h1El8B6SJ/tRnm0Na0xVIPq6oU7p71xgMl7cRi/mYqdmDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcffda93b2673cfd460d8e56866cdd0ca2b43b5fce29b9b221bac324dd4ff63a","last_reissued_at":"2026-07-05T11:52:38.598893Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:38.598893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spatial Traces: Enhancing VLA Models with Spatial-Temporal Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Aleksandr I. Panov, Alexey K. Kovalev, Maxim A. Patratskiy","submitted_at":"2025-08-12T15:53:45Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09032","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/2508.09032/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":"2508.09032","created_at":"2026-07-05T11:52:38.598951+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.09032v1","created_at":"2026-07-05T11:52:38.598951+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09032","created_at":"2026-07-05T11:52:38.598951+00:00"},{"alias_kind":"pith_short_12","alias_value":"XT75VE5SM46P","created_at":"2026-07-05T11:52:38.598951+00:00"},{"alias_kind":"pith_short_16","alias_value":"XT75VE5SM46P2RQN","created_at":"2026-07-05T11:52:38.598951+00:00"},{"alias_kind":"pith_short_8","alias_value":"XT75VE5S","created_at":"2026-07-05T11:52:38.598951+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17598","citing_title":"MuseVLA: An Adaptive Multimodal Sensing Vision-Language-Action Model for Robotic Manipulation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2508.13073","citing_title":"Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey","ref_index":110,"is_internal_anchor":false},{"citing_arxiv_id":"2602.20231","citing_title":"UniLACT: Depth-Aware RGB Latent Action Learning for Vision-Language-Action Models","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XT75VE5SM46P2RQNRZLIM3G5BS","json":"https://pith.science/pith/XT75VE5SM46P2RQNRZLIM3G5BS.json","graph_json":"https://pith.science/api/pith-number/XT75VE5SM46P2RQNRZLIM3G5BS/graph.json","events_json":"https://pith.science/api/pith-number/XT75VE5SM46P2RQNRZLIM3G5BS/events.json","paper":"https://pith.science/paper/XT75VE5S"},"agent_actions":{"view_html":"https://pith.science/pith/XT75VE5SM46P2RQNRZLIM3G5BS","download_json":"https://pith.science/pith/XT75VE5SM46P2RQNRZLIM3G5BS.json","view_paper":"https://pith.science/paper/XT75VE5S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.09032&json=true","fetch_graph":"https://pith.science/api/pith-number/XT75VE5SM46P2RQNRZLIM3G5BS/graph.json","fetch_events":"https://pith.science/api/pith-number/XT75VE5SM46P2RQNRZLIM3G5BS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XT75VE5SM46P2RQNRZLIM3G5BS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XT75VE5SM46P2RQNRZLIM3G5BS/action/storage_attestation","attest_author":"https://pith.science/pith/XT75VE5SM46P2RQNRZLIM3G5BS/action/author_attestation","sign_citation":"https://pith.science/pith/XT75VE5SM46P2RQNRZLIM3G5BS/action/citation_signature","submit_replication":"https://pith.science/pith/XT75VE5SM46P2RQNRZLIM3G5BS/action/replication_record"}},"created_at":"2026-07-05T11:52:38.598951+00:00","updated_at":"2026-07-05T11:52:38.598951+00:00"}