{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:53RGTONYEJGKHWMVR3RYSJI6ZL","short_pith_number":"pith:53RGTONY","schema_version":"1.0","canonical_sha256":"eee269b9b8224ca3d9958ee389251ecaf5e2d9dd9faa9d4db2b8d979e6b72f9e","source":{"kind":"arxiv","id":"2501.15842","version":1},"attestation_state":"computed","paper":{"title":"Beyond In-Distribution Performance: A Cross-Dataset Study of Trajectory Prediction Robustness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Goehring, Joerg Reichardt, Yue Yao","submitted_at":"2025-01-27T08:08:17Z","abstract_excerpt":"We study the Out-of-Distribution (OoD) generalization ability of three SotA trajectory prediction models with comparable In-Distribution (ID) performance but different model designs. We investigate the influence of inductive bias, size of training data and data augmentation strategy by training the models on Argoverse 2 (A2) and testing on Waymo Open Motion (WO) and vice versa. We find that the smallest model with highest inductive bias exhibits the best OoD generalization across different augmentation strategies when trained on the smaller A2 dataset and tested on the large WO dataset. In the"},"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":"2501.15842","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-27T08:08:17Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"12567b5266e20391cace1fd740dd16f2c4f082114cd144430366c607d78dabb0","abstract_canon_sha256":"df167634bb0d3de13a1385712198295f1889f03f4425662dc8bbe64a48cf7a59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:51.191649Z","signature_b64":"UDCArfoMimZ10eUPhgyK8iFHpfweTxpWXCoxf4AEFumnufD8feKptSOUd/KxSk9w3LKCh6bWHKfJyar4VjxlDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eee269b9b8224ca3d9958ee389251ecaf5e2d9dd9faa9d4db2b8d979e6b72f9e","last_reissued_at":"2026-07-05T10:05:51.191216Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:51.191216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond In-Distribution Performance: A Cross-Dataset Study of Trajectory Prediction Robustness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Goehring, Joerg Reichardt, Yue Yao","submitted_at":"2025-01-27T08:08:17Z","abstract_excerpt":"We study the Out-of-Distribution (OoD) generalization ability of three SotA trajectory prediction models with comparable In-Distribution (ID) performance but different model designs. We investigate the influence of inductive bias, size of training data and data augmentation strategy by training the models on Argoverse 2 (A2) and testing on Waymo Open Motion (WO) and vice versa. We find that the smallest model with highest inductive bias exhibits the best OoD generalization across different augmentation strategies when trained on the smaller A2 dataset and tested on the large WO dataset. In the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15842","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/2501.15842/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":"2501.15842","created_at":"2026-07-05T10:05:51.191276+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.15842v1","created_at":"2026-07-05T10:05:51.191276+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15842","created_at":"2026-07-05T10:05:51.191276+00:00"},{"alias_kind":"pith_short_12","alias_value":"53RGTONYEJGK","created_at":"2026-07-05T10:05:51.191276+00:00"},{"alias_kind":"pith_short_16","alias_value":"53RGTONYEJGKHWMV","created_at":"2026-07-05T10:05:51.191276+00:00"},{"alias_kind":"pith_short_8","alias_value":"53RGTONY","created_at":"2026-07-05T10:05:51.191276+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/53RGTONYEJGKHWMVR3RYSJI6ZL","json":"https://pith.science/pith/53RGTONYEJGKHWMVR3RYSJI6ZL.json","graph_json":"https://pith.science/api/pith-number/53RGTONYEJGKHWMVR3RYSJI6ZL/graph.json","events_json":"https://pith.science/api/pith-number/53RGTONYEJGKHWMVR3RYSJI6ZL/events.json","paper":"https://pith.science/paper/53RGTONY"},"agent_actions":{"view_html":"https://pith.science/pith/53RGTONYEJGKHWMVR3RYSJI6ZL","download_json":"https://pith.science/pith/53RGTONYEJGKHWMVR3RYSJI6ZL.json","view_paper":"https://pith.science/paper/53RGTONY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.15842&json=true","fetch_graph":"https://pith.science/api/pith-number/53RGTONYEJGKHWMVR3RYSJI6ZL/graph.json","fetch_events":"https://pith.science/api/pith-number/53RGTONYEJGKHWMVR3RYSJI6ZL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/53RGTONYEJGKHWMVR3RYSJI6ZL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/53RGTONYEJGKHWMVR3RYSJI6ZL/action/storage_attestation","attest_author":"https://pith.science/pith/53RGTONYEJGKHWMVR3RYSJI6ZL/action/author_attestation","sign_citation":"https://pith.science/pith/53RGTONYEJGKHWMVR3RYSJI6ZL/action/citation_signature","submit_replication":"https://pith.science/pith/53RGTONYEJGKHWMVR3RYSJI6ZL/action/replication_record"}},"created_at":"2026-07-05T10:05:51.191276+00:00","updated_at":"2026-07-05T10:05:51.191276+00:00"}