{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:J3EPCJYJJWNXHCDNS2EWFVBEAG","short_pith_number":"pith:J3EPCJYJ","schema_version":"1.0","canonical_sha256":"4ec8f127094d9b73886d968962d4240184e884aba993d3c6467d508d5e1114b4","source":{"kind":"arxiv","id":"2405.04909","version":1},"attestation_state":"computed","paper":{"title":"Traj-LLM: A New Exploration for Empowering Trajectory Prediction with Pre-trained Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Fan, Hongbo Li, Lingshan Liu, Yilong Ren, Yisheng Lv, Zhengxing Lan, Zhiyong Cui","submitted_at":"2024-05-08T09:28:04Z","abstract_excerpt":"Predicting the future trajectories of dynamic traffic actors is a cornerstone task in autonomous driving. Though existing notable efforts have resulted in impressive performance improvements, a gap persists in scene cognitive and understanding of the complex traffic semantics. This paper proposes Traj-LLM, the first to investigate the potential of using Large Language Models (LLMs) without explicit prompt engineering to generate future motion from agents' past/observed trajectories and scene semantics. Traj-LLM starts with sparse context joint coding to dissect the agent and scene features int"},"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":"2405.04909","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-08T09:28:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"85c2b1315c8aa4310b1ec0772557e1d15adad49ea31049752f8e2937217fe844","abstract_canon_sha256":"3c4205c1161da7ef7af98c011d07b158021482a3c04663c96f5df825f89f186e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:55.968966Z","signature_b64":"7HGjhCL7ikbf7+yFQynCe7xDrinKDS+pap9tYsf0Aune1GmdwH7zEVKWqPdgz2IxrbR+eFLinPdFtcFg0bPYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ec8f127094d9b73886d968962d4240184e884aba993d3c6467d508d5e1114b4","last_reissued_at":"2026-07-05T08:16:55.968464Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:55.968464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Traj-LLM: A New Exploration for Empowering Trajectory Prediction with Pre-trained Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Fan, Hongbo Li, Lingshan Liu, Yilong Ren, Yisheng Lv, Zhengxing Lan, Zhiyong Cui","submitted_at":"2024-05-08T09:28:04Z","abstract_excerpt":"Predicting the future trajectories of dynamic traffic actors is a cornerstone task in autonomous driving. Though existing notable efforts have resulted in impressive performance improvements, a gap persists in scene cognitive and understanding of the complex traffic semantics. This paper proposes Traj-LLM, the first to investigate the potential of using Large Language Models (LLMs) without explicit prompt engineering to generate future motion from agents' past/observed trajectories and scene semantics. Traj-LLM starts with sparse context joint coding to dissect the agent and scene features int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04909","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/2405.04909/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":"2405.04909","created_at":"2026-07-05T08:16:55.968517+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.04909v1","created_at":"2026-07-05T08:16:55.968517+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04909","created_at":"2026-07-05T08:16:55.968517+00:00"},{"alias_kind":"pith_short_12","alias_value":"J3EPCJYJJWNX","created_at":"2026-07-05T08:16:55.968517+00:00"},{"alias_kind":"pith_short_16","alias_value":"J3EPCJYJJWNXHCDN","created_at":"2026-07-05T08:16:55.968517+00:00"},{"alias_kind":"pith_short_8","alias_value":"J3EPCJYJ","created_at":"2026-07-05T08:16:55.968517+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.03715","citing_title":"PathletRL++: Optimizing Trajectory Pathlet Extraction and Dictionary Formation via Reinforcement Learning","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J3EPCJYJJWNXHCDNS2EWFVBEAG","json":"https://pith.science/pith/J3EPCJYJJWNXHCDNS2EWFVBEAG.json","graph_json":"https://pith.science/api/pith-number/J3EPCJYJJWNXHCDNS2EWFVBEAG/graph.json","events_json":"https://pith.science/api/pith-number/J3EPCJYJJWNXHCDNS2EWFVBEAG/events.json","paper":"https://pith.science/paper/J3EPCJYJ"},"agent_actions":{"view_html":"https://pith.science/pith/J3EPCJYJJWNXHCDNS2EWFVBEAG","download_json":"https://pith.science/pith/J3EPCJYJJWNXHCDNS2EWFVBEAG.json","view_paper":"https://pith.science/paper/J3EPCJYJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.04909&json=true","fetch_graph":"https://pith.science/api/pith-number/J3EPCJYJJWNXHCDNS2EWFVBEAG/graph.json","fetch_events":"https://pith.science/api/pith-number/J3EPCJYJJWNXHCDNS2EWFVBEAG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J3EPCJYJJWNXHCDNS2EWFVBEAG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J3EPCJYJJWNXHCDNS2EWFVBEAG/action/storage_attestation","attest_author":"https://pith.science/pith/J3EPCJYJJWNXHCDNS2EWFVBEAG/action/author_attestation","sign_citation":"https://pith.science/pith/J3EPCJYJJWNXHCDNS2EWFVBEAG/action/citation_signature","submit_replication":"https://pith.science/pith/J3EPCJYJJWNXHCDNS2EWFVBEAG/action/replication_record"}},"created_at":"2026-07-05T08:16:55.968517+00:00","updated_at":"2026-07-05T08:16:55.968517+00:00"}