{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7ORHXWLPV4T5GETYRBKJ32CDUX","short_pith_number":"pith:7ORHXWLP","canonical_record":{"source":{"id":"2410.15863","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-21T10:43:49Z","cross_cats_sorted":[],"title_canon_sha256":"6ae2e2b78e68e0cd9dd081a5c968a402a37f4616fa80f8a227e25f757653e15c","abstract_canon_sha256":"55840b5f8bb3e57da93ec6b0eb04f7819986217d373fb671683946920d3619ad"},"schema_version":"1.0"},"canonical_sha256":"fba27bd96faf27d3127888549de843a5c4b1d33f668343f59f8be109f5c89303","source":{"kind":"arxiv","id":"2410.15863","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.15863","created_at":"2026-07-05T11:05:35Z"},{"alias_kind":"arxiv_version","alias_value":"2410.15863v2","created_at":"2026-07-05T11:05:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15863","created_at":"2026-07-05T11:05:35Z"},{"alias_kind":"pith_short_12","alias_value":"7ORHXWLPV4T5","created_at":"2026-07-05T11:05:35Z"},{"alias_kind":"pith_short_16","alias_value":"7ORHXWLPV4T5GETY","created_at":"2026-07-05T11:05:35Z"},{"alias_kind":"pith_short_8","alias_value":"7ORHXWLP","created_at":"2026-07-05T11:05:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7ORHXWLPV4T5GETYRBKJ32CDUX","target":"record","payload":{"canonical_record":{"source":{"id":"2410.15863","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-21T10:43:49Z","cross_cats_sorted":[],"title_canon_sha256":"6ae2e2b78e68e0cd9dd081a5c968a402a37f4616fa80f8a227e25f757653e15c","abstract_canon_sha256":"55840b5f8bb3e57da93ec6b0eb04f7819986217d373fb671683946920d3619ad"},"schema_version":"1.0"},"canonical_sha256":"fba27bd96faf27d3127888549de843a5c4b1d33f668343f59f8be109f5c89303","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:35.877933Z","signature_b64":"oQ6FVmyZeoEYfuxmFOCXlJEP4KrRdOAm0+d8gt1yZWVuXhYfXwKIfE2B87GDyxO+QXB42cKHNdsCVVoie73YAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fba27bd96faf27d3127888549de843a5c4b1d33f668343f59f8be109f5c89303","last_reissued_at":"2026-07-05T11:05:35.877470Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:35.877470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.15863","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:05:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lOwMZ2fW+D2YpsC6h9w6MyJz6QS2iv422AlKVk/8Fxjz96F8AblJQtyyaY8ggZ8LVfGc964rIR2t21CHecDaDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:58:59.514214Z"},"content_sha256":"23edd1088a7ab60620d7faa607a9193b86dbad8b1364f4d2669d1374ec20ee3a","schema_version":"1.0","event_id":"sha256:23edd1088a7ab60620d7faa607a9193b86dbad8b1364f4d2669d1374ec20ee3a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7ORHXWLPV4T5GETYRBKJ32CDUX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Task-oriented Robotic Manipulation with Vision Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Hanchi Ren, Jingjing Deng, Nurhan Bulus Guran, Xianghua Xie","submitted_at":"2024-10-21T10:43:49Z","abstract_excerpt":"Vision Language Models (VLMs) play a crucial role in robotic manipulation by enabling robots to understand and interpret the visual properties of objects and their surroundings, allowing them to perform manipulation based on this multimodal understanding. Accurately understanding spatial relationships remains a non-trivial challenge, yet it is essential for effective robotic manipulation. In this work, we introduce a novel framework that integrates VLMs with a structured spatial reasoning pipeline to perform object manipulation based on high-level, task-oriented input. Our approach is the tran"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15863","kind":"arxiv","version":2},"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/2410.15863/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":"2026-07-05T11:05:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oNomSl2BKKGF/g2SE8xQydB9WtCUEy07Qq5kR4c2Q6lA0cCX6/nQnrIUvnaZ8KqcZ/EI7+IIW6i530RaDQA2BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:58:59.515153Z"},"content_sha256":"e8e45db8e19117b38e5f1ab9985dda0f2938784b2e2fae753796fa0dc6d62daf","schema_version":"1.0","event_id":"sha256:e8e45db8e19117b38e5f1ab9985dda0f2938784b2e2fae753796fa0dc6d62daf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7ORHXWLPV4T5GETYRBKJ32CDUX/bundle.json","state_url":"https://pith.science/pith/7ORHXWLPV4T5GETYRBKJ32CDUX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7ORHXWLPV4T5GETYRBKJ32CDUX/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":"2026-08-08T19:58:59Z","links":{"resolver":"https://pith.science/pith/7ORHXWLPV4T5GETYRBKJ32CDUX","bundle":"https://pith.science/pith/7ORHXWLPV4T5GETYRBKJ32CDUX/bundle.json","state":"https://pith.science/pith/7ORHXWLPV4T5GETYRBKJ32CDUX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7ORHXWLPV4T5GETYRBKJ32CDUX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7ORHXWLPV4T5GETYRBKJ32CDUX","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":"55840b5f8bb3e57da93ec6b0eb04f7819986217d373fb671683946920d3619ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-21T10:43:49Z","title_canon_sha256":"6ae2e2b78e68e0cd9dd081a5c968a402a37f4616fa80f8a227e25f757653e15c"},"schema_version":"1.0","source":{"id":"2410.15863","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.15863","created_at":"2026-07-05T11:05:35Z"},{"alias_kind":"arxiv_version","alias_value":"2410.15863v2","created_at":"2026-07-05T11:05:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15863","created_at":"2026-07-05T11:05:35Z"},{"alias_kind":"pith_short_12","alias_value":"7ORHXWLPV4T5","created_at":"2026-07-05T11:05:35Z"},{"alias_kind":"pith_short_16","alias_value":"7ORHXWLPV4T5GETY","created_at":"2026-07-05T11:05:35Z"},{"alias_kind":"pith_short_8","alias_value":"7ORHXWLP","created_at":"2026-07-05T11:05:35Z"}],"graph_snapshots":[{"event_id":"sha256:e8e45db8e19117b38e5f1ab9985dda0f2938784b2e2fae753796fa0dc6d62daf","target":"graph","created_at":"2026-07-05T11:05:35Z","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/2410.15863/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Language Models (VLMs) play a crucial role in robotic manipulation by enabling robots to understand and interpret the visual properties of objects and their surroundings, allowing them to perform manipulation based on this multimodal understanding. Accurately understanding spatial relationships remains a non-trivial challenge, yet it is essential for effective robotic manipulation. In this work, we introduce a novel framework that integrates VLMs with a structured spatial reasoning pipeline to perform object manipulation based on high-level, task-oriented input. Our approach is the tran","authors_text":"Hanchi Ren, Jingjing Deng, Nurhan Bulus Guran, Xianghua Xie","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-21T10:43:49Z","title":"Task-oriented Robotic Manipulation with Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15863","kind":"arxiv","version":2},"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":"sha256:23edd1088a7ab60620d7faa607a9193b86dbad8b1364f4d2669d1374ec20ee3a","target":"record","created_at":"2026-07-05T11:05:35Z","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":"55840b5f8bb3e57da93ec6b0eb04f7819986217d373fb671683946920d3619ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-21T10:43:49Z","title_canon_sha256":"6ae2e2b78e68e0cd9dd081a5c968a402a37f4616fa80f8a227e25f757653e15c"},"schema_version":"1.0","source":{"id":"2410.15863","kind":"arxiv","version":2}},"canonical_sha256":"fba27bd96faf27d3127888549de843a5c4b1d33f668343f59f8be109f5c89303","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fba27bd96faf27d3127888549de843a5c4b1d33f668343f59f8be109f5c89303","first_computed_at":"2026-07-05T11:05:35.877470Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:35.877470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oQ6FVmyZeoEYfuxmFOCXlJEP4KrRdOAm0+d8gt1yZWVuXhYfXwKIfE2B87GDyxO+QXB42cKHNdsCVVoie73YAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:35.877933Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.15863","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23edd1088a7ab60620d7faa607a9193b86dbad8b1364f4d2669d1374ec20ee3a","sha256:e8e45db8e19117b38e5f1ab9985dda0f2938784b2e2fae753796fa0dc6d62daf"],"state_sha256":"db16e1222e6f9ce22b1a5e81df41cf0fdb7c082385777b0762806be74dbe5470"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/S2fwEbCSHFfwdyO8MedFfUbDkelHu7M+2Jp4mYMBZACiuS59YNNtk3UqeFvfda+mMxF481yWHsNY6SqiTlzCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:58:59.520937Z","bundle_sha256":"5f183ccbbbf3cb03cafc50856a2a4e090138dc17c7d260b48a82a1aea8b49a53"}}