{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DV7YFKW5VZQXB2EXPRJD2JJIWN","short_pith_number":"pith:DV7YFKW5","schema_version":"1.0","canonical_sha256":"1d7f82aaddae6170e8977c523d2528b36483897f1b9b0dc17257a81d6a23214d","source":{"kind":"arxiv","id":"2512.13660","version":3},"attestation_state":"computed","paper":{"title":"Towards Spatial Trace with Reasoning in Vision-Language Models for Robotics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Cheng Chi, Enshen Zhou, Huajie Tan, Jiawei He, Jiayuan Zhang, Jingkun An, Lu Sheng, Mengzhen Liu, Pengwei Wang, Shanghang Zhang, Shanyu Rong, Yibo Li, Yi Han, Yuheng Ji, Zhongyuan Wang","submitted_at":"2025-12-15T18:52:43Z","abstract_excerpt":"Spatial tracing, as a fundamental embodied interaction ability for robots, is inherently challenging as it requires multi-step metric-grounded reasoning compounded with complex spatial referring and real-world metric measurement. However, existing methods struggle with this compositional task. To this end, we propose RoboTracer, a 3D-aware VLM that first achieves both 3D spatial referring and measuring via a universal spatial encoder and a regression-supervised decoder to enhance scale awareness during supervised fine-tuning (SFT). Moreover, RoboTracer advances multi-step metric-grounded reaso"},"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":"2512.13660","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-12-15T18:52:43Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a9ab1ae1ccbf9fa56cf2729bc24b49762f494f3445db7db585862d08ef41d07a","abstract_canon_sha256":"64c00a881098753e4c7af7c6c899ec8fff0a39bb1d784485724f4547eb1ac4c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:30.966363Z","signature_b64":"4WU5SJ0flPl4ZsTTtgd1cWHtx6MQI2TUWCWuq5pkSR2TSfeVdAodALgOD/YK4m/JPDYdLO9fhxvp0C2C3qWDBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d7f82aaddae6170e8977c523d2528b36483897f1b9b0dc17257a81d6a23214d","last_reissued_at":"2026-06-30T01:17:30.965605Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:30.965605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Spatial Trace with Reasoning in Vision-Language Models for Robotics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Cheng Chi, Enshen Zhou, Huajie Tan, Jiawei He, Jiayuan Zhang, Jingkun An, Lu Sheng, Mengzhen Liu, Pengwei Wang, Shanghang Zhang, Shanyu Rong, Yibo Li, Yi Han, Yuheng Ji, Zhongyuan Wang","submitted_at":"2025-12-15T18:52:43Z","abstract_excerpt":"Spatial tracing, as a fundamental embodied interaction ability for robots, is inherently challenging as it requires multi-step metric-grounded reasoning compounded with complex spatial referring and real-world metric measurement. However, existing methods struggle with this compositional task. To this end, we propose RoboTracer, a 3D-aware VLM that first achieves both 3D spatial referring and measuring via a universal spatial encoder and a regression-supervised decoder to enhance scale awareness during supervised fine-tuning (SFT). Moreover, RoboTracer advances multi-step metric-grounded reaso"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.13660","kind":"arxiv","version":3},"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/2512.13660/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":"2512.13660","created_at":"2026-06-30T01:17:30.965724+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.13660v3","created_at":"2026-06-30T01:17:30.965724+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.13660","created_at":"2026-06-30T01:17:30.965724+00:00"},{"alias_kind":"pith_short_12","alias_value":"DV7YFKW5VZQX","created_at":"2026-06-30T01:17:30.965724+00:00"},{"alias_kind":"pith_short_16","alias_value":"DV7YFKW5VZQXB2EX","created_at":"2026-06-30T01:17:30.965724+00:00"},{"alias_kind":"pith_short_8","alias_value":"DV7YFKW5","created_at":"2026-06-30T01:17:30.965724+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.31329","citing_title":"3D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidance","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DV7YFKW5VZQXB2EXPRJD2JJIWN","json":"https://pith.science/pith/DV7YFKW5VZQXB2EXPRJD2JJIWN.json","graph_json":"https://pith.science/api/pith-number/DV7YFKW5VZQXB2EXPRJD2JJIWN/graph.json","events_json":"https://pith.science/api/pith-number/DV7YFKW5VZQXB2EXPRJD2JJIWN/events.json","paper":"https://pith.science/paper/DV7YFKW5"},"agent_actions":{"view_html":"https://pith.science/pith/DV7YFKW5VZQXB2EXPRJD2JJIWN","download_json":"https://pith.science/pith/DV7YFKW5VZQXB2EXPRJD2JJIWN.json","view_paper":"https://pith.science/paper/DV7YFKW5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.13660&json=true","fetch_graph":"https://pith.science/api/pith-number/DV7YFKW5VZQXB2EXPRJD2JJIWN/graph.json","fetch_events":"https://pith.science/api/pith-number/DV7YFKW5VZQXB2EXPRJD2JJIWN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DV7YFKW5VZQXB2EXPRJD2JJIWN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DV7YFKW5VZQXB2EXPRJD2JJIWN/action/storage_attestation","attest_author":"https://pith.science/pith/DV7YFKW5VZQXB2EXPRJD2JJIWN/action/author_attestation","sign_citation":"https://pith.science/pith/DV7YFKW5VZQXB2EXPRJD2JJIWN/action/citation_signature","submit_replication":"https://pith.science/pith/DV7YFKW5VZQXB2EXPRJD2JJIWN/action/replication_record"}},"created_at":"2026-06-30T01:17:30.965724+00:00","updated_at":"2026-06-30T01:17:30.965724+00:00"}