{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AUMW64YFEQAJT2SX4BHBKGWUML","short_pith_number":"pith:AUMW64YF","schema_version":"1.0","canonical_sha256":"05196f7305240099ea57e04e151ad462f4e8149942d8969eac2da149d6d8e86d","source":{"kind":"arxiv","id":"2506.03605","version":1},"attestation_state":"computed","paper":{"title":"Generating 6DoF Object Manipulation Trajectories from Action Description in Egocentric Vision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shinsuke Mori, Shuhei Kurita, Taichi Nishimura, Tomoya Yoshida","submitted_at":"2025-06-04T06:28:16Z","abstract_excerpt":"Learning to use tools or objects in common scenes, particularly handling them in various ways as instructed, is a key challenge for developing interactive robots. Training models to generate such manipulation trajectories requires a large and diverse collection of detailed manipulation demonstrations for various objects, which is nearly unfeasible to gather at scale. In this paper, we propose a framework that leverages large-scale ego- and exo-centric video datasets -- constructed globally with substantial effort -- of Exo-Ego4D to extract diverse manipulation trajectories at scale. From these"},"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":"2506.03605","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-04T06:28:16Z","cross_cats_sorted":[],"title_canon_sha256":"7f6958ebe3abea18b7e110a6f6175c4c494e99d3337382815dc852fd833ae551","abstract_canon_sha256":"b4b704866de52961fb3ad76a1c64264855cb317082871cf2c487311900db5e87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:48.613431Z","signature_b64":"zLV9b3XpM0tIZoOKrWVpHDCBb3TAV8OydPTsUvPqVA28NOb7wT8TW9y4sZDc32U1VDWzEajVk6E4S40hHlcHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05196f7305240099ea57e04e151ad462f4e8149942d8969eac2da149d6d8e86d","last_reissued_at":"2026-07-05T11:15:48.612728Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:48.612728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating 6DoF Object Manipulation Trajectories from Action Description in Egocentric Vision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shinsuke Mori, Shuhei Kurita, Taichi Nishimura, Tomoya Yoshida","submitted_at":"2025-06-04T06:28:16Z","abstract_excerpt":"Learning to use tools or objects in common scenes, particularly handling them in various ways as instructed, is a key challenge for developing interactive robots. Training models to generate such manipulation trajectories requires a large and diverse collection of detailed manipulation demonstrations for various objects, which is nearly unfeasible to gather at scale. In this paper, we propose a framework that leverages large-scale ego- and exo-centric video datasets -- constructed globally with substantial effort -- of Exo-Ego4D to extract diverse manipulation trajectories at scale. From these"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03605","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/2506.03605/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":"2506.03605","created_at":"2026-07-05T11:15:48.612803+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.03605v1","created_at":"2026-07-05T11:15:48.612803+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03605","created_at":"2026-07-05T11:15:48.612803+00:00"},{"alias_kind":"pith_short_12","alias_value":"AUMW64YFEQAJ","created_at":"2026-07-05T11:15:48.612803+00:00"},{"alias_kind":"pith_short_16","alias_value":"AUMW64YFEQAJT2SX","created_at":"2026-07-05T11:15:48.612803+00:00"},{"alias_kind":"pith_short_8","alias_value":"AUMW64YF","created_at":"2026-07-05T11:15:48.612803+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.16192","citing_title":"MotionForesight: Re-purposing Video Models for Future 3D Scene-Flow Prediction","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AUMW64YFEQAJT2SX4BHBKGWUML","json":"https://pith.science/pith/AUMW64YFEQAJT2SX4BHBKGWUML.json","graph_json":"https://pith.science/api/pith-number/AUMW64YFEQAJT2SX4BHBKGWUML/graph.json","events_json":"https://pith.science/api/pith-number/AUMW64YFEQAJT2SX4BHBKGWUML/events.json","paper":"https://pith.science/paper/AUMW64YF"},"agent_actions":{"view_html":"https://pith.science/pith/AUMW64YFEQAJT2SX4BHBKGWUML","download_json":"https://pith.science/pith/AUMW64YFEQAJT2SX4BHBKGWUML.json","view_paper":"https://pith.science/paper/AUMW64YF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.03605&json=true","fetch_graph":"https://pith.science/api/pith-number/AUMW64YFEQAJT2SX4BHBKGWUML/graph.json","fetch_events":"https://pith.science/api/pith-number/AUMW64YFEQAJT2SX4BHBKGWUML/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AUMW64YFEQAJT2SX4BHBKGWUML/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AUMW64YFEQAJT2SX4BHBKGWUML/action/storage_attestation","attest_author":"https://pith.science/pith/AUMW64YFEQAJT2SX4BHBKGWUML/action/author_attestation","sign_citation":"https://pith.science/pith/AUMW64YFEQAJT2SX4BHBKGWUML/action/citation_signature","submit_replication":"https://pith.science/pith/AUMW64YFEQAJT2SX4BHBKGWUML/action/replication_record"}},"created_at":"2026-07-05T11:15:48.612803+00:00","updated_at":"2026-07-05T11:15:48.612803+00:00"}