{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:G3TBDHBUKWAHP5KNGH3F7ZVTA5","short_pith_number":"pith:G3TBDHBU","schema_version":"1.0","canonical_sha256":"36e6119c34558077f54d31f65fe6b3076590bfb2ef69003a0b7db5be7b9dcf41","source":{"kind":"arxiv","id":"2607.10984","version":1},"attestation_state":"computed","paper":{"title":"EquiFusion: Kinematics-Agnostic Human Motion Prediction via Equivariant Latent Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhishek Saroha, Cecilia Curreli, Daniel Cremers, Dominik Muhle, Florian Hofherr, Riccardo Marin","submitted_at":"2026-07-13T01:16:18Z","abstract_excerpt":"Existing Stochastic 3D Human Motion Prediction models are fundamentally constrained by hard-coding the skeleton kinematics, severely limiting generalization, preventing cross-dataset training, and requiring complex data retargeting. We introduce EquiFusion, the first kinematics-agnostic model to solve this bottleneck, implementing a latent diffusion model with a permutation equivariant architecture. EquiFusion treats the kinematics' connectivity as an explicit input parameter, ensuring its internal computations are inherently agnostic to joint ordering and graph structure. This novel design en"},"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":"2607.10984","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-13T01:16:18Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"title_canon_sha256":"57adc32bea09e7c2f4c4b8781d7c3d557c5b5bb4ee4918169c1bc97b3c2a9540","abstract_canon_sha256":"ea0aceef89975b4e2df360828ff6d0825137893fa7d1e82cad7a17d45bd432c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:21:50.854091Z","signature_b64":"g5jeVhAJjz27b9NdmcEehgF9tAhbEUhZVJtqE/J6ApBm4Fg7Ay2p3hLLZUTSqotaLYZVzdKxlPp54NmgCusBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36e6119c34558077f54d31f65fe6b3076590bfb2ef69003a0b7db5be7b9dcf41","last_reissued_at":"2026-07-14T01:21:50.853239Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:21:50.853239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EquiFusion: Kinematics-Agnostic Human Motion Prediction via Equivariant Latent Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhishek Saroha, Cecilia Curreli, Daniel Cremers, Dominik Muhle, Florian Hofherr, Riccardo Marin","submitted_at":"2026-07-13T01:16:18Z","abstract_excerpt":"Existing Stochastic 3D Human Motion Prediction models are fundamentally constrained by hard-coding the skeleton kinematics, severely limiting generalization, preventing cross-dataset training, and requiring complex data retargeting. We introduce EquiFusion, the first kinematics-agnostic model to solve this bottleneck, implementing a latent diffusion model with a permutation equivariant architecture. EquiFusion treats the kinematics' connectivity as an explicit input parameter, ensuring its internal computations are inherently agnostic to joint ordering and graph structure. This novel design en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10984","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/2607.10984/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":"2607.10984","created_at":"2026-07-14T01:21:50.853677+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.10984v1","created_at":"2026-07-14T01:21:50.853677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10984","created_at":"2026-07-14T01:21:50.853677+00:00"},{"alias_kind":"pith_short_12","alias_value":"G3TBDHBUKWAH","created_at":"2026-07-14T01:21:50.853677+00:00"},{"alias_kind":"pith_short_16","alias_value":"G3TBDHBUKWAHP5KN","created_at":"2026-07-14T01:21:50.853677+00:00"},{"alias_kind":"pith_short_8","alias_value":"G3TBDHBU","created_at":"2026-07-14T01:21:50.853677+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G3TBDHBUKWAHP5KNGH3F7ZVTA5","json":"https://pith.science/pith/G3TBDHBUKWAHP5KNGH3F7ZVTA5.json","graph_json":"https://pith.science/api/pith-number/G3TBDHBUKWAHP5KNGH3F7ZVTA5/graph.json","events_json":"https://pith.science/api/pith-number/G3TBDHBUKWAHP5KNGH3F7ZVTA5/events.json","paper":"https://pith.science/paper/G3TBDHBU"},"agent_actions":{"view_html":"https://pith.science/pith/G3TBDHBUKWAHP5KNGH3F7ZVTA5","download_json":"https://pith.science/pith/G3TBDHBUKWAHP5KNGH3F7ZVTA5.json","view_paper":"https://pith.science/paper/G3TBDHBU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.10984&json=true","fetch_graph":"https://pith.science/api/pith-number/G3TBDHBUKWAHP5KNGH3F7ZVTA5/graph.json","fetch_events":"https://pith.science/api/pith-number/G3TBDHBUKWAHP5KNGH3F7ZVTA5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G3TBDHBUKWAHP5KNGH3F7ZVTA5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G3TBDHBUKWAHP5KNGH3F7ZVTA5/action/storage_attestation","attest_author":"https://pith.science/pith/G3TBDHBUKWAHP5KNGH3F7ZVTA5/action/author_attestation","sign_citation":"https://pith.science/pith/G3TBDHBUKWAHP5KNGH3F7ZVTA5/action/citation_signature","submit_replication":"https://pith.science/pith/G3TBDHBUKWAHP5KNGH3F7ZVTA5/action/replication_record"}},"created_at":"2026-07-14T01:21:50.853677+00:00","updated_at":"2026-07-14T01:21:50.853677+00:00"}