{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TS7NID7T7ZRV35WJ6WZ7TH4TPJ","short_pith_number":"pith:TS7NID7T","canonical_record":{"source":{"id":"2506.11261","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-12T20:04:31Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"63868733ea65a02c0e12bf9399b76baab8360c084ff49e932f0973e1dc0a7647","abstract_canon_sha256":"b8736eb89b85417d2eaadf97f8be14042d2995dc08bd487efb94eb0b1004c442"},"schema_version":"1.0"},"canonical_sha256":"9cbed40ff3fe635df6c9f5b3f99f937a49eebe981741dbbc893bab1b1263f5fc","source":{"kind":"arxiv","id":"2506.11261","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11261","created_at":"2026-07-05T11:21:01Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11261v1","created_at":"2026-07-05T11:21:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11261","created_at":"2026-07-05T11:21:01Z"},{"alias_kind":"pith_short_12","alias_value":"TS7NID7T7ZRV","created_at":"2026-07-05T11:21:01Z"},{"alias_kind":"pith_short_16","alias_value":"TS7NID7T7ZRV35WJ","created_at":"2026-07-05T11:21:01Z"},{"alias_kind":"pith_short_8","alias_value":"TS7NID7T","created_at":"2026-07-05T11:21:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TS7NID7T7ZRV35WJ6WZ7TH4TPJ","target":"record","payload":{"canonical_record":{"source":{"id":"2506.11261","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-12T20:04:31Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"63868733ea65a02c0e12bf9399b76baab8360c084ff49e932f0973e1dc0a7647","abstract_canon_sha256":"b8736eb89b85417d2eaadf97f8be14042d2995dc08bd487efb94eb0b1004c442"},"schema_version":"1.0"},"canonical_sha256":"9cbed40ff3fe635df6c9f5b3f99f937a49eebe981741dbbc893bab1b1263f5fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:01.814001Z","signature_b64":"Ium9W3+J/IZ7z4Ssiv1MmRkbOD068d/wl3wxjdkuwFYQW3fHGeeHxiJYJ0KIkPWUV984mIpiK32OAmwlqxUlDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cbed40ff3fe635df6c9f5b3f99f937a49eebe981741dbbc893bab1b1263f5fc","last_reissued_at":"2026-07-05T11:21:01.813509Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:01.813509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.11261","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:21:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lTDRxj9Eifj4ixNX+uvZjFv9he+ntFQXUT7GkPC81etCpVKfxCPHNnDUg+2II+JR+auGNW4FYKX4KZ0BofMqAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:12:16.837416Z"},"content_sha256":"9660e33ec71ec4bc9ffed1f58a32a69dc907569c6f74a1d7da2a20f51a926c35","schema_version":"1.0","event_id":"sha256:9660e33ec71ec4bc9ffed1f58a32a69dc907569c6f74a1d7da2a20f51a926c35"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TS7NID7T7ZRV35WJ6WZ7TH4TPJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Gondola: Grounded Vision Language Planning for Generalizable Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Cordelia Schmid, Paul Pacaud, Ricardo Garcia, Shizhe Chen","submitted_at":"2025-06-12T20:04:31Z","abstract_excerpt":"Robotic manipulation faces a significant challenge in generalizing across unseen objects, environments and tasks specified by diverse language instructions. To improve generalization capabilities, recent research has incorporated large language models (LLMs) for planning and action execution. While promising, these methods often fall short in generating grounded plans in visual environments. Although efforts have been made to perform visual instructional tuning on LLMs for robotic manipulation, existing methods are typically constrained by single-view image input and struggle with precise obje"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11261","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/2506.11261/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:21:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G6ZxO0LaH+0yoiYqB/MlIIUseNklmztOJ/pzHeFQlTAT94G7/eyTpMQeWCMilemecddOrypnwqXwxu/hc4p/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:12:16.838385Z"},"content_sha256":"a306a93aa431a6a4980af8519bbebe8458a325f200a5f5b92b1dbe7ae25198fb","schema_version":"1.0","event_id":"sha256:a306a93aa431a6a4980af8519bbebe8458a325f200a5f5b92b1dbe7ae25198fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TS7NID7T7ZRV35WJ6WZ7TH4TPJ/bundle.json","state_url":"https://pith.science/pith/TS7NID7T7ZRV35WJ6WZ7TH4TPJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TS7NID7T7ZRV35WJ6WZ7TH4TPJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T11:12:16Z","links":{"resolver":"https://pith.science/pith/TS7NID7T7ZRV35WJ6WZ7TH4TPJ","bundle":"https://pith.science/pith/TS7NID7T7ZRV35WJ6WZ7TH4TPJ/bundle.json","state":"https://pith.science/pith/TS7NID7T7ZRV35WJ6WZ7TH4TPJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TS7NID7T7ZRV35WJ6WZ7TH4TPJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TS7NID7T7ZRV35WJ6WZ7TH4TPJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b8736eb89b85417d2eaadf97f8be14042d2995dc08bd487efb94eb0b1004c442","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-12T20:04:31Z","title_canon_sha256":"63868733ea65a02c0e12bf9399b76baab8360c084ff49e932f0973e1dc0a7647"},"schema_version":"1.0","source":{"id":"2506.11261","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11261","created_at":"2026-07-05T11:21:01Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11261v1","created_at":"2026-07-05T11:21:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11261","created_at":"2026-07-05T11:21:01Z"},{"alias_kind":"pith_short_12","alias_value":"TS7NID7T7ZRV","created_at":"2026-07-05T11:21:01Z"},{"alias_kind":"pith_short_16","alias_value":"TS7NID7T7ZRV35WJ","created_at":"2026-07-05T11:21:01Z"},{"alias_kind":"pith_short_8","alias_value":"TS7NID7T","created_at":"2026-07-05T11:21:01Z"}],"graph_snapshots":[{"event_id":"sha256:a306a93aa431a6a4980af8519bbebe8458a325f200a5f5b92b1dbe7ae25198fb","target":"graph","created_at":"2026-07-05T11:21:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.11261/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Robotic manipulation faces a significant challenge in generalizing across unseen objects, environments and tasks specified by diverse language instructions. To improve generalization capabilities, recent research has incorporated large language models (LLMs) for planning and action execution. While promising, these methods often fall short in generating grounded plans in visual environments. Although efforts have been made to perform visual instructional tuning on LLMs for robotic manipulation, existing methods are typically constrained by single-view image input and struggle with precise obje","authors_text":"Cordelia Schmid, Paul Pacaud, Ricardo Garcia, Shizhe Chen","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-12T20:04:31Z","title":"Gondola: Grounded Vision Language Planning for Generalizable Robotic Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11261","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9660e33ec71ec4bc9ffed1f58a32a69dc907569c6f74a1d7da2a20f51a926c35","target":"record","created_at":"2026-07-05T11:21:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b8736eb89b85417d2eaadf97f8be14042d2995dc08bd487efb94eb0b1004c442","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-12T20:04:31Z","title_canon_sha256":"63868733ea65a02c0e12bf9399b76baab8360c084ff49e932f0973e1dc0a7647"},"schema_version":"1.0","source":{"id":"2506.11261","kind":"arxiv","version":1}},"canonical_sha256":"9cbed40ff3fe635df6c9f5b3f99f937a49eebe981741dbbc893bab1b1263f5fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9cbed40ff3fe635df6c9f5b3f99f937a49eebe981741dbbc893bab1b1263f5fc","first_computed_at":"2026-07-05T11:21:01.813509Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:01.813509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ium9W3+J/IZ7z4Ssiv1MmRkbOD068d/wl3wxjdkuwFYQW3fHGeeHxiJYJ0KIkPWUV984mIpiK32OAmwlqxUlDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:01.814001Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.11261","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9660e33ec71ec4bc9ffed1f58a32a69dc907569c6f74a1d7da2a20f51a926c35","sha256:a306a93aa431a6a4980af8519bbebe8458a325f200a5f5b92b1dbe7ae25198fb"],"state_sha256":"e2b62e2784af2a4d871658f3372cdf75527ecf779ce9eaf361e4d26cf8eb5dd9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fe8fKZdDHTkTGeOSjDm5h/NZpOrnWNOP0V1yGVDqRe4KA09Tdf4uDY6aAOOV6/8AcLIyRa727yR0YttmBSG9BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:12:16.857073Z","bundle_sha256":"2b450d3b3761ebb96ce63770353b5c8d70e76f1abe46a208c925e9bd3173757a"}}