{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3XPJRERIILFH7RZKHWEUZHQJAL","short_pith_number":"pith:3XPJRERI","schema_version":"1.0","canonical_sha256":"ddde98922842ca7fc72a3d894c9e0902e8497b8175f2a3379fe824e71acd0e5d","source":{"kind":"arxiv","id":"2411.15096","version":2},"attestation_state":"computed","paper":{"title":"RED: Effective Trajectory Representation Learning with Comprehensive Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Christian S. Jensen, Lisi Chen, Panos Kalnis, Shuo Shang, Silin Zhou","submitted_at":"2024-11-22T17:51:21Z","abstract_excerpt":"Trajectory representation learning (TRL) maps trajectories to vectors that can then be used for various downstream tasks, including trajectory similarity computation, trajectory classification, and travel-time estimation. However, existing TRL methods often produce vectors that, when used in downstream tasks, yield insufficiently accurate results. A key reason is that they fail to utilize the comprehensive information encompassed by trajectories. We propose a self-supervised TRL framework, called RED, which effectively exploits multiple types of trajectory information. Overall, RED adopts 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":"2411.15096","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T17:51:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f0dbca33efc19f43b697b29ab9f26bbe3feff43d674fab678fd47e2ecdab9f4f","abstract_canon_sha256":"ff18f724753eca0119db450341e495ae1189f24ea9ad6a64f3bc27137ebe0b72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:46.448849Z","signature_b64":"mulh04rn8ZqfZiKlf39N0XcW5WymKH2+Rj8WSsFA00lfS0hYjkrzCDAk+Z41tTn544Dg6h9ZwPHMYGBBAb4mCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddde98922842ca7fc72a3d894c9e0902e8497b8175f2a3379fe824e71acd0e5d","last_reissued_at":"2026-07-05T09:41:46.448310Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:46.448310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RED: Effective Trajectory Representation Learning with Comprehensive Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Christian S. Jensen, Lisi Chen, Panos Kalnis, Shuo Shang, Silin Zhou","submitted_at":"2024-11-22T17:51:21Z","abstract_excerpt":"Trajectory representation learning (TRL) maps trajectories to vectors that can then be used for various downstream tasks, including trajectory similarity computation, trajectory classification, and travel-time estimation. However, existing TRL methods often produce vectors that, when used in downstream tasks, yield insufficiently accurate results. A key reason is that they fail to utilize the comprehensive information encompassed by trajectories. We propose a self-supervised TRL framework, called RED, which effectively exploits multiple types of trajectory information. Overall, RED adopts the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15096","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/2411.15096/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":"2411.15096","created_at":"2026-07-05T09:41:46.448378+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.15096v2","created_at":"2026-07-05T09:41:46.448378+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15096","created_at":"2026-07-05T09:41:46.448378+00:00"},{"alias_kind":"pith_short_12","alias_value":"3XPJRERIILFH","created_at":"2026-07-05T09:41:46.448378+00:00"},{"alias_kind":"pith_short_16","alias_value":"3XPJRERIILFH7RZK","created_at":"2026-07-05T09:41:46.448378+00:00"},{"alias_kind":"pith_short_8","alias_value":"3XPJRERI","created_at":"2026-07-05T09:41:46.448378+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08273","citing_title":"Efficient Prompt Learning for Traffic Forecasting","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3XPJRERIILFH7RZKHWEUZHQJAL","json":"https://pith.science/pith/3XPJRERIILFH7RZKHWEUZHQJAL.json","graph_json":"https://pith.science/api/pith-number/3XPJRERIILFH7RZKHWEUZHQJAL/graph.json","events_json":"https://pith.science/api/pith-number/3XPJRERIILFH7RZKHWEUZHQJAL/events.json","paper":"https://pith.science/paper/3XPJRERI"},"agent_actions":{"view_html":"https://pith.science/pith/3XPJRERIILFH7RZKHWEUZHQJAL","download_json":"https://pith.science/pith/3XPJRERIILFH7RZKHWEUZHQJAL.json","view_paper":"https://pith.science/paper/3XPJRERI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.15096&json=true","fetch_graph":"https://pith.science/api/pith-number/3XPJRERIILFH7RZKHWEUZHQJAL/graph.json","fetch_events":"https://pith.science/api/pith-number/3XPJRERIILFH7RZKHWEUZHQJAL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3XPJRERIILFH7RZKHWEUZHQJAL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3XPJRERIILFH7RZKHWEUZHQJAL/action/storage_attestation","attest_author":"https://pith.science/pith/3XPJRERIILFH7RZKHWEUZHQJAL/action/author_attestation","sign_citation":"https://pith.science/pith/3XPJRERIILFH7RZKHWEUZHQJAL/action/citation_signature","submit_replication":"https://pith.science/pith/3XPJRERIILFH7RZKHWEUZHQJAL/action/replication_record"}},"created_at":"2026-07-05T09:41:46.448378+00:00","updated_at":"2026-07-05T09:41:46.448378+00:00"}