{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HBYWHNRU6PPYCGQKNTYRN3GAMV","short_pith_number":"pith:HBYWHNRU","schema_version":"1.0","canonical_sha256":"387163b634f3df811a0a6cf116ecc06568a92bfeca5856cc0c8fc8e18ad1c08a","source":{"kind":"arxiv","id":"2506.06196","version":1},"attestation_state":"computed","paper":{"title":"Bridging Perception and Action: Spatially-Grounded Mid-Level Representations for Robot Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chuyuan Kelly Fu, Dhruv Shah, Dorsa Sadigh, Fei Xia, Jonathan Yang, Tingnan Zhang","submitted_at":"2025-06-06T15:57:48Z","abstract_excerpt":"In this work, we investigate how spatially grounded auxiliary representations can provide both broad, high-level grounding as well as direct, actionable information to improve policy learning performance and generalization for dexterous tasks. We study these mid-level representations across three critical dimensions: object-centricity, pose-awareness, and depth-awareness. We use these interpretable mid-level representations to train specialist encoders via supervised learning, then feed them as inputs to a diffusion policy to solve dexterous bimanual manipulation tasks in the real world. We pr"},"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":"2506.06196","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-06T15:57:48Z","cross_cats_sorted":[],"title_canon_sha256":"49bfdf2a0be26de5a370dcf8af8d2cd9ae2af3f18cfae6dcfc43296155a660ec","abstract_canon_sha256":"a1fd140dc17e8cd2b2799298430364c3a08e9e84c41e4f429d821e56e8c10a19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:27.350395Z","signature_b64":"ZkueNr2xyps8EP+MDgBobxGKO9Efib8nDfN8OWnsakMmhoJ2Kcs9xMFb51AtUD8H+8GvWhnbnq6bFeCTTeWUCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"387163b634f3df811a0a6cf116ecc06568a92bfeca5856cc0c8fc8e18ad1c08a","last_reissued_at":"2026-07-05T11:17:27.349819Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:27.349819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging Perception and Action: Spatially-Grounded Mid-Level Representations for Robot Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chuyuan Kelly Fu, Dhruv Shah, Dorsa Sadigh, Fei Xia, Jonathan Yang, Tingnan Zhang","submitted_at":"2025-06-06T15:57:48Z","abstract_excerpt":"In this work, we investigate how spatially grounded auxiliary representations can provide both broad, high-level grounding as well as direct, actionable information to improve policy learning performance and generalization for dexterous tasks. We study these mid-level representations across three critical dimensions: object-centricity, pose-awareness, and depth-awareness. We use these interpretable mid-level representations to train specialist encoders via supervised learning, then feed them as inputs to a diffusion policy to solve dexterous bimanual manipulation tasks in the real world. We pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06196","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/2506.06196/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":"2506.06196","created_at":"2026-07-05T11:17:27.349881+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.06196v1","created_at":"2026-07-05T11:17:27.349881+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06196","created_at":"2026-07-05T11:17:27.349881+00:00"},{"alias_kind":"pith_short_12","alias_value":"HBYWHNRU6PPY","created_at":"2026-07-05T11:17:27.349881+00:00"},{"alias_kind":"pith_short_16","alias_value":"HBYWHNRU6PPYCGQK","created_at":"2026-07-05T11:17:27.349881+00:00"},{"alias_kind":"pith_short_8","alias_value":"HBYWHNRU","created_at":"2026-07-05T11:17:27.349881+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.18085","citing_title":"Continually Evolving Skill Knowledge in Vision Language Action Model","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HBYWHNRU6PPYCGQKNTYRN3GAMV","json":"https://pith.science/pith/HBYWHNRU6PPYCGQKNTYRN3GAMV.json","graph_json":"https://pith.science/api/pith-number/HBYWHNRU6PPYCGQKNTYRN3GAMV/graph.json","events_json":"https://pith.science/api/pith-number/HBYWHNRU6PPYCGQKNTYRN3GAMV/events.json","paper":"https://pith.science/paper/HBYWHNRU"},"agent_actions":{"view_html":"https://pith.science/pith/HBYWHNRU6PPYCGQKNTYRN3GAMV","download_json":"https://pith.science/pith/HBYWHNRU6PPYCGQKNTYRN3GAMV.json","view_paper":"https://pith.science/paper/HBYWHNRU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.06196&json=true","fetch_graph":"https://pith.science/api/pith-number/HBYWHNRU6PPYCGQKNTYRN3GAMV/graph.json","fetch_events":"https://pith.science/api/pith-number/HBYWHNRU6PPYCGQKNTYRN3GAMV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HBYWHNRU6PPYCGQKNTYRN3GAMV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HBYWHNRU6PPYCGQKNTYRN3GAMV/action/storage_attestation","attest_author":"https://pith.science/pith/HBYWHNRU6PPYCGQKNTYRN3GAMV/action/author_attestation","sign_citation":"https://pith.science/pith/HBYWHNRU6PPYCGQKNTYRN3GAMV/action/citation_signature","submit_replication":"https://pith.science/pith/HBYWHNRU6PPYCGQKNTYRN3GAMV/action/replication_record"}},"created_at":"2026-07-05T11:17:27.349881+00:00","updated_at":"2026-07-05T11:17:27.349881+00:00"}