{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QH6BLQLGC2AXD7PMDXT5QL25E4","short_pith_number":"pith:QH6BLQLG","schema_version":"1.0","canonical_sha256":"81fc15c166168171fdec1de7d82f5d273bd9ae9a0f4aad9e47d8878efcd4f66d","source":{"kind":"arxiv","id":"2606.26800","version":1},"attestation_state":"computed","paper":{"title":"SSI-Policy: Learning Structured Scene Interfaces for Vision-Language Robotic Manipulation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Haibo Lu, Jia Pan, Jinyi Hong, Kaijun Wang, Linfang Zheng, Wei Pan, Wei Zhang, Xuping Wu, Zikai Ouyang","submitted_at":"2026-06-25T09:38:05Z","abstract_excerpt":"Real-world robotic manipulation demands spatial grounding, task-aware reasoning, and precise control. Learning such capabilities becomes particularly challenging in the low-data regime. Prior methods often trade off scalable task-level reasoning and explicit physical structure: video-based approaches can drift geometrically over long horizons, 3D approaches often require depth sensing, and many flow/trajectory interfaces emphasize motion without an explicit RGB-only geometric representation. We introduce SSI-Policy, a modular framework built around a Structured Scene Interface (SSI) -- a unifi"},"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":"2606.26800","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-25T09:38:05Z","cross_cats_sorted":[],"title_canon_sha256":"08d04535b9d7408c7f40d78191c0e1da94cd826c5b1766f82d2ffc9a7c5679c6","abstract_canon_sha256":"0826a13f460dcd8100f380cbf2b3f9f648c3b789353d51f8f64ed6f6e042a433"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:16:00.112276Z","signature_b64":"ij0rCTcLJVKuffB1bF7RodGhIbB9o2+hMBqM4ZUEY8PXtb7JO7AQmcS+GrijoUZcUyv55gxtWJGkhx7e1Tc0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81fc15c166168171fdec1de7d82f5d273bd9ae9a0f4aad9e47d8878efcd4f66d","last_reissued_at":"2026-06-26T01:16:00.111898Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:16:00.111898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SSI-Policy: Learning Structured Scene Interfaces for Vision-Language Robotic Manipulation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Haibo Lu, Jia Pan, Jinyi Hong, Kaijun Wang, Linfang Zheng, Wei Pan, Wei Zhang, Xuping Wu, Zikai Ouyang","submitted_at":"2026-06-25T09:38:05Z","abstract_excerpt":"Real-world robotic manipulation demands spatial grounding, task-aware reasoning, and precise control. Learning such capabilities becomes particularly challenging in the low-data regime. Prior methods often trade off scalable task-level reasoning and explicit physical structure: video-based approaches can drift geometrically over long horizons, 3D approaches often require depth sensing, and many flow/trajectory interfaces emphasize motion without an explicit RGB-only geometric representation. We introduce SSI-Policy, a modular framework built around a Structured Scene Interface (SSI) -- a unifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26800","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/2606.26800/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":"2606.26800","created_at":"2026-06-26T01:16:00.111947+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.26800v1","created_at":"2026-06-26T01:16:00.111947+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26800","created_at":"2026-06-26T01:16:00.111947+00:00"},{"alias_kind":"pith_short_12","alias_value":"QH6BLQLGC2AX","created_at":"2026-06-26T01:16:00.111947+00:00"},{"alias_kind":"pith_short_16","alias_value":"QH6BLQLGC2AXD7PM","created_at":"2026-06-26T01:16:00.111947+00:00"},{"alias_kind":"pith_short_8","alias_value":"QH6BLQLG","created_at":"2026-06-26T01:16:00.111947+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/QH6BLQLGC2AXD7PMDXT5QL25E4","json":"https://pith.science/pith/QH6BLQLGC2AXD7PMDXT5QL25E4.json","graph_json":"https://pith.science/api/pith-number/QH6BLQLGC2AXD7PMDXT5QL25E4/graph.json","events_json":"https://pith.science/api/pith-number/QH6BLQLGC2AXD7PMDXT5QL25E4/events.json","paper":"https://pith.science/paper/QH6BLQLG"},"agent_actions":{"view_html":"https://pith.science/pith/QH6BLQLGC2AXD7PMDXT5QL25E4","download_json":"https://pith.science/pith/QH6BLQLGC2AXD7PMDXT5QL25E4.json","view_paper":"https://pith.science/paper/QH6BLQLG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.26800&json=true","fetch_graph":"https://pith.science/api/pith-number/QH6BLQLGC2AXD7PMDXT5QL25E4/graph.json","fetch_events":"https://pith.science/api/pith-number/QH6BLQLGC2AXD7PMDXT5QL25E4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QH6BLQLGC2AXD7PMDXT5QL25E4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QH6BLQLGC2AXD7PMDXT5QL25E4/action/storage_attestation","attest_author":"https://pith.science/pith/QH6BLQLGC2AXD7PMDXT5QL25E4/action/author_attestation","sign_citation":"https://pith.science/pith/QH6BLQLGC2AXD7PMDXT5QL25E4/action/citation_signature","submit_replication":"https://pith.science/pith/QH6BLQLGC2AXD7PMDXT5QL25E4/action/replication_record"}},"created_at":"2026-06-26T01:16:00.111947+00:00","updated_at":"2026-06-26T01:16:00.111947+00:00"}