{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RJDWOSC5KU4TBD3RQDVRXEGBV4","short_pith_number":"pith:RJDWOSC5","schema_version":"1.0","canonical_sha256":"8a4767485d5539308f7180eb1b90c1af18c282e5b7642fceaccca4dc214527c4","source":{"kind":"arxiv","id":"2603.06480","version":2},"attestation_state":"computed","paper":{"title":"History-Conditioned Spatio-Temporal Visual Token Pruning for Efficient Vision-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Christopher Rasmussen, Ming Li, Qitong Wang, Tianyi Zhou, Yijun Liang","submitted_at":"2026-03-06T17:03:16Z","abstract_excerpt":"Vision-Language Navigation (VLN) enables robots to follow natural-language instructions in visually grounded environments, serving as a key capability for embodied robotic systems. Recent Vision-Language-Action (VLA) models have demonstrated strong navigation performance, but their high computational cost introduces latency that limits real-time deployment. We propose a training-free spatio-temporal vision token pruning framework tailored to VLA-based VLN. We apply spatial token selection to the current view, alongside spatio-temporal compression for historical memories, enabling efficient lon"},"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":"2603.06480","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-03-06T17:03:16Z","cross_cats_sorted":[],"title_canon_sha256":"4e43545de30773ca3817026c9e1565479676ae5420f64d8c219a5e40a29006e4","abstract_canon_sha256":"bbcd24de29350c0be4c3d28fc871281ba1df2b9794e55b41da167b9e6734323b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:15:50.353701Z","signature_b64":"/Jop1ynAw0HxG0DNJUXDAGvCY1y5xmp5J3AlQBM01X1ZEWlNihUYIGw5BwB5LRAfwVSvOe7HUjrcsIvirAreBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a4767485d5539308f7180eb1b90c1af18c282e5b7642fceaccca4dc214527c4","last_reissued_at":"2026-06-26T01:15:50.353240Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:15:50.353240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"History-Conditioned Spatio-Temporal Visual Token Pruning for Efficient Vision-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Christopher Rasmussen, Ming Li, Qitong Wang, Tianyi Zhou, Yijun Liang","submitted_at":"2026-03-06T17:03:16Z","abstract_excerpt":"Vision-Language Navigation (VLN) enables robots to follow natural-language instructions in visually grounded environments, serving as a key capability for embodied robotic systems. Recent Vision-Language-Action (VLA) models have demonstrated strong navigation performance, but their high computational cost introduces latency that limits real-time deployment. We propose a training-free spatio-temporal vision token pruning framework tailored to VLA-based VLN. We apply spatial token selection to the current view, alongside spatio-temporal compression for historical memories, enabling efficient lon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.06480","kind":"arxiv","version":2},"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/2603.06480/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":"2603.06480","created_at":"2026-06-26T01:15:50.353293+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.06480v2","created_at":"2026-06-26T01:15:50.353293+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.06480","created_at":"2026-06-26T01:15:50.353293+00:00"},{"alias_kind":"pith_short_12","alias_value":"RJDWOSC5KU4T","created_at":"2026-06-26T01:15:50.353293+00:00"},{"alias_kind":"pith_short_16","alias_value":"RJDWOSC5KU4TBD3R","created_at":"2026-06-26T01:15:50.353293+00:00"},{"alias_kind":"pith_short_8","alias_value":"RJDWOSC5","created_at":"2026-06-26T01:15:50.353293+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RJDWOSC5KU4TBD3RQDVRXEGBV4","json":"https://pith.science/pith/RJDWOSC5KU4TBD3RQDVRXEGBV4.json","graph_json":"https://pith.science/api/pith-number/RJDWOSC5KU4TBD3RQDVRXEGBV4/graph.json","events_json":"https://pith.science/api/pith-number/RJDWOSC5KU4TBD3RQDVRXEGBV4/events.json","paper":"https://pith.science/paper/RJDWOSC5"},"agent_actions":{"view_html":"https://pith.science/pith/RJDWOSC5KU4TBD3RQDVRXEGBV4","download_json":"https://pith.science/pith/RJDWOSC5KU4TBD3RQDVRXEGBV4.json","view_paper":"https://pith.science/paper/RJDWOSC5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.06480&json=true","fetch_graph":"https://pith.science/api/pith-number/RJDWOSC5KU4TBD3RQDVRXEGBV4/graph.json","fetch_events":"https://pith.science/api/pith-number/RJDWOSC5KU4TBD3RQDVRXEGBV4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RJDWOSC5KU4TBD3RQDVRXEGBV4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RJDWOSC5KU4TBD3RQDVRXEGBV4/action/storage_attestation","attest_author":"https://pith.science/pith/RJDWOSC5KU4TBD3RQDVRXEGBV4/action/author_attestation","sign_citation":"https://pith.science/pith/RJDWOSC5KU4TBD3RQDVRXEGBV4/action/citation_signature","submit_replication":"https://pith.science/pith/RJDWOSC5KU4TBD3RQDVRXEGBV4/action/replication_record"}},"created_at":"2026-06-26T01:15:50.353293+00:00","updated_at":"2026-06-26T01:15:50.353293+00:00"}