{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZSSO2BHT5DMA6VIBFRQ5EQL7MV","short_pith_number":"pith:ZSSO2BHT","schema_version":"1.0","canonical_sha256":"cca4ed04f3e8d80f55012c61d2417f654ced0367b0ee1be3d91d3e92b60bbd3e","source":{"kind":"arxiv","id":"2507.23657","version":1},"attestation_state":"computed","paper":{"title":"OmniTraj: Pre-Training on Heterogeneous Data for Adaptive and Zero-Shot Human Trajectory Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandre Alahi, Kaouther Messaoud, Lan Feng, Po-Chien Luan, Yang Gao","submitted_at":"2025-07-31T15:37:09Z","abstract_excerpt":"While large-scale pre-training has advanced human trajectory prediction, a critical challenge remains: zero-shot transfer to unseen dataset with varying temporal dynamics. State-of-the-art pre-trained models often require fine-tuning to adapt to new datasets with different frame rates or observation horizons, limiting their scalability and practical utility. In this work, we systematically investigate this limitation and propose a robust solution. We first demonstrate that existing data-aware discrete models struggle when transferred to new scenarios with shifted temporal setups. We then isola"},"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":"2507.23657","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-31T15:37:09Z","cross_cats_sorted":[],"title_canon_sha256":"4236e19bd8275da9d1bb35be6010967e7cd4cc7c0ac14a55238c6098cce7c3ea","abstract_canon_sha256":"abb39307d10a4f7458f6aa5f31cdf508768aa4d5cfa8514576dd498a3fc72c05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:28.920813Z","signature_b64":"ek7/wPL23Ysc6BiGz9LnyzHZhDhP9fbDqXEwfcucPy2VjWdfw3C+Qduq8cwWhrQOJN+ZD/tJEIdojprhBaLcAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cca4ed04f3e8d80f55012c61d2417f654ced0367b0ee1be3d91d3e92b60bbd3e","last_reissued_at":"2026-07-05T11:46:28.920382Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:28.920382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniTraj: Pre-Training on Heterogeneous Data for Adaptive and Zero-Shot Human Trajectory Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandre Alahi, Kaouther Messaoud, Lan Feng, Po-Chien Luan, Yang Gao","submitted_at":"2025-07-31T15:37:09Z","abstract_excerpt":"While large-scale pre-training has advanced human trajectory prediction, a critical challenge remains: zero-shot transfer to unseen dataset with varying temporal dynamics. State-of-the-art pre-trained models often require fine-tuning to adapt to new datasets with different frame rates or observation horizons, limiting their scalability and practical utility. In this work, we systematically investigate this limitation and propose a robust solution. We first demonstrate that existing data-aware discrete models struggle when transferred to new scenarios with shifted temporal setups. We then isola"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23657","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/2507.23657/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":"2507.23657","created_at":"2026-07-05T11:46:28.920445+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.23657v1","created_at":"2026-07-05T11:46:28.920445+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23657","created_at":"2026-07-05T11:46:28.920445+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZSSO2BHT5DMA","created_at":"2026-07-05T11:46:28.920445+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZSSO2BHT5DMA6VIB","created_at":"2026-07-05T11:46:28.920445+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZSSO2BHT","created_at":"2026-07-05T11:46:28.920445+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28587","citing_title":"Deformable Gaussian Occupancy: Decoupling Rigid and Nonrigid Motion with Factorized Distillation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15424","citing_title":"Social-Mamba: Socially-Aware Trajectory Forecasting with State-Space Models","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07642","citing_title":"EggHand: A Multimodal Foundation Model for Egocentric Hand Pose Forecasting","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZSSO2BHT5DMA6VIBFRQ5EQL7MV","json":"https://pith.science/pith/ZSSO2BHT5DMA6VIBFRQ5EQL7MV.json","graph_json":"https://pith.science/api/pith-number/ZSSO2BHT5DMA6VIBFRQ5EQL7MV/graph.json","events_json":"https://pith.science/api/pith-number/ZSSO2BHT5DMA6VIBFRQ5EQL7MV/events.json","paper":"https://pith.science/paper/ZSSO2BHT"},"agent_actions":{"view_html":"https://pith.science/pith/ZSSO2BHT5DMA6VIBFRQ5EQL7MV","download_json":"https://pith.science/pith/ZSSO2BHT5DMA6VIBFRQ5EQL7MV.json","view_paper":"https://pith.science/paper/ZSSO2BHT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.23657&json=true","fetch_graph":"https://pith.science/api/pith-number/ZSSO2BHT5DMA6VIBFRQ5EQL7MV/graph.json","fetch_events":"https://pith.science/api/pith-number/ZSSO2BHT5DMA6VIBFRQ5EQL7MV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZSSO2BHT5DMA6VIBFRQ5EQL7MV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZSSO2BHT5DMA6VIBFRQ5EQL7MV/action/storage_attestation","attest_author":"https://pith.science/pith/ZSSO2BHT5DMA6VIBFRQ5EQL7MV/action/author_attestation","sign_citation":"https://pith.science/pith/ZSSO2BHT5DMA6VIBFRQ5EQL7MV/action/citation_signature","submit_replication":"https://pith.science/pith/ZSSO2BHT5DMA6VIBFRQ5EQL7MV/action/replication_record"}},"created_at":"2026-07-05T11:46:28.920445+00:00","updated_at":"2026-07-05T11:46:28.920445+00:00"}