{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XXCGVMBKEZ7WDTLVG4C57S6ATZ","short_pith_number":"pith:XXCGVMBK","schema_version":"1.0","canonical_sha256":"bdc46ab02a267f61cd753705dfcbc09e499e41b497917c01de22cb99ef4808a3","source":{"kind":"arxiv","id":"2505.15206","version":1},"attestation_state":"computed","paper":{"title":"EndoVLA: Dual-Phase Vision-Language-Action Model for Autonomous Tracking in Endoscopy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chenhan Jin, Chi Kit Ng, Guankun Wang, Hongliang Ren, Huxin Gao, Kun Yuan, Long Bai, Tieyong Zeng, Yupeng Wang","submitted_at":"2025-05-21T07:35:00Z","abstract_excerpt":"In endoscopic procedures, autonomous tracking of abnormal regions and following circumferential cutting markers can significantly reduce the cognitive burden on endoscopists. However, conventional model-based pipelines are fragile for each component (e.g., detection, motion planning) requires manual tuning and struggles to incorporate high-level endoscopic intent, leading to poor generalization across diverse scenes. Vision-Language-Action (VLA) models, which integrate visual perception, language grounding, and motion planning within an end-to-end framework, offer a promising alternative by se"},"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":"2505.15206","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-05-21T07:35:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4d9d2ae96790b6702022e666ff153375e19ad5fe2419c8c83ae5fef6eb6a0dc7","abstract_canon_sha256":"6efed5708359307edb497c8199377bf1495ceb4870d076ecb308208f52250140"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:19.705575Z","signature_b64":"cfLja91bEL3OMDUg5AEpxnPIQp2pD5JGNrsmwZ6wbfR/NXYJqpgQrHOlOWzpq0a0KfZRCkoy5XK2PDHs2NvnCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdc46ab02a267f61cd753705dfcbc09e499e41b497917c01de22cb99ef4808a3","last_reissued_at":"2026-07-05T11:56:19.705162Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:19.705162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EndoVLA: Dual-Phase Vision-Language-Action Model for Autonomous Tracking in Endoscopy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chenhan Jin, Chi Kit Ng, Guankun Wang, Hongliang Ren, Huxin Gao, Kun Yuan, Long Bai, Tieyong Zeng, Yupeng Wang","submitted_at":"2025-05-21T07:35:00Z","abstract_excerpt":"In endoscopic procedures, autonomous tracking of abnormal regions and following circumferential cutting markers can significantly reduce the cognitive burden on endoscopists. However, conventional model-based pipelines are fragile for each component (e.g., detection, motion planning) requires manual tuning and struggles to incorporate high-level endoscopic intent, leading to poor generalization across diverse scenes. Vision-Language-Action (VLA) models, which integrate visual perception, language grounding, and motion planning within an end-to-end framework, offer a promising alternative by se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15206","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/2505.15206/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":"2505.15206","created_at":"2026-07-05T11:56:19.705221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.15206v1","created_at":"2026-07-05T11:56:19.705221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15206","created_at":"2026-07-05T11:56:19.705221+00:00"},{"alias_kind":"pith_short_12","alias_value":"XXCGVMBKEZ7W","created_at":"2026-07-05T11:56:19.705221+00:00"},{"alias_kind":"pith_short_16","alias_value":"XXCGVMBKEZ7WDTLV","created_at":"2026-07-05T11:56:19.705221+00:00"},{"alias_kind":"pith_short_8","alias_value":"XXCGVMBK","created_at":"2026-07-05T11:56:19.705221+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20347","citing_title":"A Vision-Language-Action Model for Adaptive Ultrasound-Guided Needle Insertion and Needle Tracking","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XXCGVMBKEZ7WDTLVG4C57S6ATZ","json":"https://pith.science/pith/XXCGVMBKEZ7WDTLVG4C57S6ATZ.json","graph_json":"https://pith.science/api/pith-number/XXCGVMBKEZ7WDTLVG4C57S6ATZ/graph.json","events_json":"https://pith.science/api/pith-number/XXCGVMBKEZ7WDTLVG4C57S6ATZ/events.json","paper":"https://pith.science/paper/XXCGVMBK"},"agent_actions":{"view_html":"https://pith.science/pith/XXCGVMBKEZ7WDTLVG4C57S6ATZ","download_json":"https://pith.science/pith/XXCGVMBKEZ7WDTLVG4C57S6ATZ.json","view_paper":"https://pith.science/paper/XXCGVMBK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.15206&json=true","fetch_graph":"https://pith.science/api/pith-number/XXCGVMBKEZ7WDTLVG4C57S6ATZ/graph.json","fetch_events":"https://pith.science/api/pith-number/XXCGVMBKEZ7WDTLVG4C57S6ATZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XXCGVMBKEZ7WDTLVG4C57S6ATZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XXCGVMBKEZ7WDTLVG4C57S6ATZ/action/storage_attestation","attest_author":"https://pith.science/pith/XXCGVMBKEZ7WDTLVG4C57S6ATZ/action/author_attestation","sign_citation":"https://pith.science/pith/XXCGVMBKEZ7WDTLVG4C57S6ATZ/action/citation_signature","submit_replication":"https://pith.science/pith/XXCGVMBKEZ7WDTLVG4C57S6ATZ/action/replication_record"}},"created_at":"2026-07-05T11:56:19.705221+00:00","updated_at":"2026-07-05T11:56:19.705221+00:00"}