{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JJFNVWUNLLAPOI2YZEGOB3J5QJ","short_pith_number":"pith:JJFNVWUN","schema_version":"1.0","canonical_sha256":"4a4adada8d5ac0f72358c90ce0ed3d8260536dd67f11423011cd1fc1ab7407d6","source":{"kind":"arxiv","id":"2605.14393","version":1},"attestation_state":"computed","paper":{"title":"Analogical Trajectory Transfer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Scenes are partitioned into object-centric clusters whose cross-scene mappings are predicted hierarchically from 3D foundation features and then assembled and refined to transfer trajectories while preserving semantics and avoiding clashes.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eun Sun Lee, Gwangtak Bae, Junho Kim, Seunggu Kang, Young Min Kim","submitted_at":"2026-05-14T05:14:59Z","abstract_excerpt":"We study analogical trajectory transfer, where the goal is to translate motion trajectories in one 3D environment to a semantically analogous location in another. Such a capacity would enable machines to perform analogical spatial reasoning, with applications in AR/VR co-presence, content creation, and robotics. However, even semantically similar scenes can still differ substantially in object placement, scale, and layout, so naively matching semantics leads to collisions or geometric distortions. Furthermore, finding where each trajectory point should transfer to has a large search space, as "},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.14393","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T05:14:59Z","cross_cats_sorted":[],"title_canon_sha256":"b3c68291306b9afd8f0fd2fa1626bd09fda01c0b10058bc0013c307dfc73faa4","abstract_canon_sha256":"7a882010299427928bca18a6c637778731d241cd60899ce741b6b07912b6385a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:07.593962Z","signature_b64":"1iDhGA0SMfxDBYnfIFkftai6MS0C8KQgXwmCoYDIbrSsklbK8fDsFCGAeCBnO0JqrPfq1vWAziL2VZDSVLI6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a4adada8d5ac0f72358c90ce0ed3d8260536dd67f11423011cd1fc1ab7407d6","last_reissued_at":"2026-05-17T23:39:07.593205Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:07.593205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analogical Trajectory Transfer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Scenes are partitioned into object-centric clusters whose cross-scene mappings are predicted hierarchically from 3D foundation features and then assembled and refined to transfer trajectories while preserving semantics and avoiding clashes.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eun Sun Lee, Gwangtak Bae, Junho Kim, Seunggu Kang, Young Min Kim","submitted_at":"2026-05-14T05:14:59Z","abstract_excerpt":"We study analogical trajectory transfer, where the goal is to translate motion trajectories in one 3D environment to a semantically analogous location in another. Such a capacity would enable machines to perform analogical spatial reasoning, with applications in AR/VR co-presence, content creation, and robotics. However, even semantically similar scenes can still differ substantially in object placement, scale, and layout, so naively matching semantics leads to collisions or geometric distortions. Furthermore, finding where each trajectory point should transfer to has a large search space, as "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We partition scenes into object-centric clusters and estimate cross-scene mappings via hierarchical smooth map prediction, using 3D foundation model features that encode contextual information from object and open-space arrangements. We then combinatorially assemble the per-cluster maps into an initial transfer and refine the result to remove collisions and distortions.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That 3D foundation model features provide sufficient contextual information to produce accurate cross-scene mappings that preserve both semantics and functionality without requiring scene-specific training or manual tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A method transfers trajectories across 3D scenes by clustering objects, predicting hierarchical smooth maps from foundation model features, assembling them combinatorially, and refining for coherence.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Scenes are partitioned into object-centric clusters whose cross-scene mappings are predicted hierarchically from 3D foundation features and then assembled and refined to transfer trajectories while preserving semantics and avoiding clashes.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9b8a0228e31067ab6e5649ae501a60f5d584fa0e857c9ec8324c0865a0f9ac24"},"source":{"id":"2605.14393","kind":"arxiv","version":1},"verdict":{"id":"39b53288-555d-4ce8-889d-467eab1a259e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T01:41:07.075818Z","strongest_claim":"We partition scenes into object-centric clusters and estimate cross-scene mappings via hierarchical smooth map prediction, using 3D foundation model features that encode contextual information from object and open-space arrangements. We then combinatorially assemble the per-cluster maps into an initial transfer and refine the result to remove collisions and distortions.","one_line_summary":"A method transfers trajectories across 3D scenes by clustering objects, predicting hierarchical smooth maps from foundation model features, assembling them combinatorially, and refining for coherence.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That 3D foundation model features provide sufficient contextual information to produce accurate cross-scene mappings that preserve both semantics and functionality without requiring scene-specific training or manual tuning.","pith_extraction_headline":"Scenes are partitioned into object-centric clusters whose cross-scene mappings are predicted hierarchically from 3D foundation features and then assembled and refined to transfer trajectories while preserving semantics and avoiding clashes."},"references":{"count":192,"sample":[{"doi":"","year":2021,"title":"Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) , month =","work_id":"9079fdd2-f257-4408-b578-af685897a1bf","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"The Farthest Point Strategy for Progressive Image Sampling , volume =","work_id":"2e8eaf52-a725-4cdf-84c7-8b260e5e1d0f","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1145/355759.355766","year":1977,"title":"Eddy, William F. , title =. 1977 , issue_date =. doi:10.1145/355759.355766 , journal =","work_id":"f70a18f7-0dfe-490c-95ca-26e9caeb3b47","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) , year=","work_id":"c15e9d09-443e-40cd-854b-62066b4faf00","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"International Journal of Computer Vision (IJCV) , pages=","work_id":"77d0fa20-9954-41ca-8239-6db820731636","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":192,"snapshot_sha256":"b6ec68bdf2955fcdb761e1b43ae225429bd1b7ce4aefa27bc831b17434a47eb3","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"b4e383461b5e7f860941f1dbc65fd3353cf9567140ea1bfa59bd6c420e4595a1"},"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":"2605.14393","created_at":"2026-05-17T23:39:07.593334+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14393v1","created_at":"2026-05-17T23:39:07.593334+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14393","created_at":"2026-05-17T23:39:07.593334+00:00"},{"alias_kind":"pith_short_12","alias_value":"JJFNVWUNLLAP","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"JJFNVWUNLLAPOI2Y","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"JJFNVWUN","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JJFNVWUNLLAPOI2YZEGOB3J5QJ","json":"https://pith.science/pith/JJFNVWUNLLAPOI2YZEGOB3J5QJ.json","graph_json":"https://pith.science/api/pith-number/JJFNVWUNLLAPOI2YZEGOB3J5QJ/graph.json","events_json":"https://pith.science/api/pith-number/JJFNVWUNLLAPOI2YZEGOB3J5QJ/events.json","paper":"https://pith.science/paper/JJFNVWUN"},"agent_actions":{"view_html":"https://pith.science/pith/JJFNVWUNLLAPOI2YZEGOB3J5QJ","download_json":"https://pith.science/pith/JJFNVWUNLLAPOI2YZEGOB3J5QJ.json","view_paper":"https://pith.science/paper/JJFNVWUN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14393&json=true","fetch_graph":"https://pith.science/api/pith-number/JJFNVWUNLLAPOI2YZEGOB3J5QJ/graph.json","fetch_events":"https://pith.science/api/pith-number/JJFNVWUNLLAPOI2YZEGOB3J5QJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JJFNVWUNLLAPOI2YZEGOB3J5QJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JJFNVWUNLLAPOI2YZEGOB3J5QJ/action/storage_attestation","attest_author":"https://pith.science/pith/JJFNVWUNLLAPOI2YZEGOB3J5QJ/action/author_attestation","sign_citation":"https://pith.science/pith/JJFNVWUNLLAPOI2YZEGOB3J5QJ/action/citation_signature","submit_replication":"https://pith.science/pith/JJFNVWUNLLAPOI2YZEGOB3J5QJ/action/replication_record"}},"created_at":"2026-05-17T23:39:07.593334+00:00","updated_at":"2026-05-17T23:39:07.593334+00:00"}