{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2JSE7OUA7CAVVX7XOKOZA2KOCK","short_pith_number":"pith:2JSE7OUA","schema_version":"1.0","canonical_sha256":"d2644fba80f8815adff7729d90694e12a25466deea0562e9c9cb142b04297e89","source":{"kind":"arxiv","id":"1901.07677","version":2},"attestation_state":"computed","paper":{"title":"Modeling Human Motion with Quaternion-based Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Christoph Feichtenhofer, Dario Pavllo, David Grangier, Michael Auli","submitted_at":"2019-01-21T23:56:54Z","abstract_excerpt":"Previous work on predicting or generating 3D human pose sequences regresses either joint rotations or joint positions. The former strategy is prone to error accumulation along the kinematic chain, as well as discontinuities when using Euler angles or exponential maps as parameterizations. The latter requires re-projection onto skeleton constraints to avoid bone stretching and invalid configurations. This work addresses both limitations. QuaterNet represents rotations with quaternions and our loss function performs forward kinematics on a skeleton to penalize absolute position errors instead of"},"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":"1901.07677","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-21T23:56:54Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"59ae82cc1549a5d82aa1953ac18eb899b7046b22743dfbfea70dce20a1c2438a","abstract_canon_sha256":"09e458d78675593163a2620162759180cf93a44ff8915e589ff9a906def8d7b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:15:02.446878Z","signature_b64":"HvlnxTglfn1tb/17s0KmzhT57BH9OSyKfNBh36ezBcDYRbf6/nHUGfU7jSbLE1uSLqpzArW3XtMvPwQ5FHtFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2644fba80f8815adff7729d90694e12a25466deea0562e9c9cb142b04297e89","last_reissued_at":"2026-07-05T00:15:02.446387Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:15:02.446387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modeling Human Motion with Quaternion-based Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Christoph Feichtenhofer, Dario Pavllo, David Grangier, Michael Auli","submitted_at":"2019-01-21T23:56:54Z","abstract_excerpt":"Previous work on predicting or generating 3D human pose sequences regresses either joint rotations or joint positions. The former strategy is prone to error accumulation along the kinematic chain, as well as discontinuities when using Euler angles or exponential maps as parameterizations. The latter requires re-projection onto skeleton constraints to avoid bone stretching and invalid configurations. This work addresses both limitations. QuaterNet represents rotations with quaternions and our loss function performs forward kinematics on a skeleton to penalize absolute position errors instead of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.07677","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/1901.07677/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":"1901.07677","created_at":"2026-07-05T00:15:02.446446+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.07677v2","created_at":"2026-07-05T00:15:02.446446+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.07677","created_at":"2026-07-05T00:15:02.446446+00:00"},{"alias_kind":"pith_short_12","alias_value":"2JSE7OUA7CAV","created_at":"2026-07-05T00:15:02.446446+00:00"},{"alias_kind":"pith_short_16","alias_value":"2JSE7OUA7CAVVX7X","created_at":"2026-07-05T00:15:02.446446+00:00"},{"alias_kind":"pith_short_8","alias_value":"2JSE7OUA","created_at":"2026-07-05T00:15:02.446446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.00733","citing_title":"Learning Variations in Human Motion via Mix-and-Match Perturbation","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2JSE7OUA7CAVVX7XOKOZA2KOCK","json":"https://pith.science/pith/2JSE7OUA7CAVVX7XOKOZA2KOCK.json","graph_json":"https://pith.science/api/pith-number/2JSE7OUA7CAVVX7XOKOZA2KOCK/graph.json","events_json":"https://pith.science/api/pith-number/2JSE7OUA7CAVVX7XOKOZA2KOCK/events.json","paper":"https://pith.science/paper/2JSE7OUA"},"agent_actions":{"view_html":"https://pith.science/pith/2JSE7OUA7CAVVX7XOKOZA2KOCK","download_json":"https://pith.science/pith/2JSE7OUA7CAVVX7XOKOZA2KOCK.json","view_paper":"https://pith.science/paper/2JSE7OUA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.07677&json=true","fetch_graph":"https://pith.science/api/pith-number/2JSE7OUA7CAVVX7XOKOZA2KOCK/graph.json","fetch_events":"https://pith.science/api/pith-number/2JSE7OUA7CAVVX7XOKOZA2KOCK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2JSE7OUA7CAVVX7XOKOZA2KOCK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2JSE7OUA7CAVVX7XOKOZA2KOCK/action/storage_attestation","attest_author":"https://pith.science/pith/2JSE7OUA7CAVVX7XOKOZA2KOCK/action/author_attestation","sign_citation":"https://pith.science/pith/2JSE7OUA7CAVVX7XOKOZA2KOCK/action/citation_signature","submit_replication":"https://pith.science/pith/2JSE7OUA7CAVVX7XOKOZA2KOCK/action/replication_record"}},"created_at":"2026-07-05T00:15:02.446446+00:00","updated_at":"2026-07-05T00:15:02.446446+00:00"}