{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JVTTYY7JIISFWI5WA2GOTAXECN","short_pith_number":"pith:JVTTYY7J","schema_version":"1.0","canonical_sha256":"4d673c63e942245b23b6068ce982e4134c1ec9c989c4d33f8223d486f7e52763","source":{"kind":"arxiv","id":"2502.10156","version":4},"attestation_state":"computed","paper":{"title":"FusionForce: End-to-end Differentiable Neural-Symbolic Layer for Trajectory Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Karel Zimmermann, Ruslan Agishev","submitted_at":"2025-02-14T13:36:00Z","abstract_excerpt":"We propose end-to-end differentiable model that predicts robot trajectories on rough offroad terrain from camera images and/or lidar point clouds. The model integrates a learnable component that predicts robot-terrain interaction forces with a neural-symbolic layer that enforces the laws of classical mechanics and consequently improves generalization on out-of-distribution data. The neural-symbolic layer includes a differentiable physics engine that computes the robot's trajectory by querying these forces at the points of contact with the terrain. As the proposed architecture comprises substan"},"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":"2502.10156","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-02-14T13:36:00Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"f01648bacf2c9d902ce9eab18764dd44aacd75bc43660f022956f92fc6842060","abstract_canon_sha256":"fd6f770c18211ccf2df0c3d419120c055b2f9e307ee0d00f9cc21d05123100b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:26.102742Z","signature_b64":"S+/7oIMGZCMAvvl2YHTb3O8ctw1UIY/LoryU6Zw0lOotkX9ULPuqldSbq429orRjfScoRowHYEuCf8DQf0YHAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d673c63e942245b23b6068ce982e4134c1ec9c989c4d33f8223d486f7e52763","last_reissued_at":"2026-07-05T11:26:26.102288Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:26.102288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FusionForce: End-to-end Differentiable Neural-Symbolic Layer for Trajectory Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Karel Zimmermann, Ruslan Agishev","submitted_at":"2025-02-14T13:36:00Z","abstract_excerpt":"We propose end-to-end differentiable model that predicts robot trajectories on rough offroad terrain from camera images and/or lidar point clouds. The model integrates a learnable component that predicts robot-terrain interaction forces with a neural-symbolic layer that enforces the laws of classical mechanics and consequently improves generalization on out-of-distribution data. The neural-symbolic layer includes a differentiable physics engine that computes the robot's trajectory by querying these forces at the points of contact with the terrain. As the proposed architecture comprises substan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10156","kind":"arxiv","version":4},"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/2502.10156/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":"2502.10156","created_at":"2026-07-05T11:26:26.102349+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.10156v4","created_at":"2026-07-05T11:26:26.102349+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10156","created_at":"2026-07-05T11:26:26.102349+00:00"},{"alias_kind":"pith_short_12","alias_value":"JVTTYY7JIISF","created_at":"2026-07-05T11:26:26.102349+00:00"},{"alias_kind":"pith_short_16","alias_value":"JVTTYY7JIISFWI5W","created_at":"2026-07-05T11:26:26.102349+00:00"},{"alias_kind":"pith_short_8","alias_value":"JVTTYY7J","created_at":"2026-07-05T11:26:26.102349+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.01756","citing_title":"NeuroSymb-MRG: Differentiable Abductive Reasoning with Active Uncertainty Minimization for Radiology Report Generation","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JVTTYY7JIISFWI5WA2GOTAXECN","json":"https://pith.science/pith/JVTTYY7JIISFWI5WA2GOTAXECN.json","graph_json":"https://pith.science/api/pith-number/JVTTYY7JIISFWI5WA2GOTAXECN/graph.json","events_json":"https://pith.science/api/pith-number/JVTTYY7JIISFWI5WA2GOTAXECN/events.json","paper":"https://pith.science/paper/JVTTYY7J"},"agent_actions":{"view_html":"https://pith.science/pith/JVTTYY7JIISFWI5WA2GOTAXECN","download_json":"https://pith.science/pith/JVTTYY7JIISFWI5WA2GOTAXECN.json","view_paper":"https://pith.science/paper/JVTTYY7J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.10156&json=true","fetch_graph":"https://pith.science/api/pith-number/JVTTYY7JIISFWI5WA2GOTAXECN/graph.json","fetch_events":"https://pith.science/api/pith-number/JVTTYY7JIISFWI5WA2GOTAXECN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JVTTYY7JIISFWI5WA2GOTAXECN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JVTTYY7JIISFWI5WA2GOTAXECN/action/storage_attestation","attest_author":"https://pith.science/pith/JVTTYY7JIISFWI5WA2GOTAXECN/action/author_attestation","sign_citation":"https://pith.science/pith/JVTTYY7JIISFWI5WA2GOTAXECN/action/citation_signature","submit_replication":"https://pith.science/pith/JVTTYY7JIISFWI5WA2GOTAXECN/action/replication_record"}},"created_at":"2026-07-05T11:26:26.102349+00:00","updated_at":"2026-07-05T11:26:26.102349+00:00"}