{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:P3CEOT4ATWRYLMD2E3DPHUF7L4","short_pith_number":"pith:P3CEOT4A","schema_version":"1.0","canonical_sha256":"7ec4474f809da385b07a26c6f3d0bf5f3a097e6083e2c650cea6bb8f972d0c5a","source":{"kind":"arxiv","id":"2605.20134","version":1},"attestation_state":"computed","paper":{"title":"TrajTok: Adaptive Spatial Tokenization for Trajectory Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cyrus Shahabi, Shang-Ling Hsu, Zhen Xiong","submitted_at":"2026-05-19T17:18:32Z","abstract_excerpt":"Learning generalizable trajectory representations from raw GPS traces remains difficult because the data is continuous, noisy, and irregularly sampled. Spatial tokenization is also challenging: fine grids yield sparse cells with weak embeddings, while coarse grids merge heterogeneous movement patterns into the same token. We present TrajTok, a trajectory encoder with a simple pretraining recipe for transferable trajectory embeddings. TrajTok first learns a multi-resolution hexagonal cell partition from the spatial distribution of GPS points, converting noisy GPS sequences into discrete cell to"},"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":"2605.20134","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T17:18:32Z","cross_cats_sorted":[],"title_canon_sha256":"739382011c7dfec5e0cfd02b54255bb09f152f43c266eca507bcfb1a23452e20","abstract_canon_sha256":"6d071c91e42f1f38faad0c3c7a61fe19bc84c009266e37d0244213df1c1ffc50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T02:06:03.606684Z","signature_b64":"7PDAtFDk745jN25novcZAr9qtrZrlxxX/z5Er7SMQ4BH2uMYovTFHjJeDcJWpF1IL4nTMvV/Dt7NXg3FHrDlAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ec4474f809da385b07a26c6f3d0bf5f3a097e6083e2c650cea6bb8f972d0c5a","last_reissued_at":"2026-05-20T02:06:03.606079Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T02:06:03.606079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TrajTok: Adaptive Spatial Tokenization for Trajectory Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cyrus Shahabi, Shang-Ling Hsu, Zhen Xiong","submitted_at":"2026-05-19T17:18:32Z","abstract_excerpt":"Learning generalizable trajectory representations from raw GPS traces remains difficult because the data is continuous, noisy, and irregularly sampled. Spatial tokenization is also challenging: fine grids yield sparse cells with weak embeddings, while coarse grids merge heterogeneous movement patterns into the same token. We present TrajTok, a trajectory encoder with a simple pretraining recipe for transferable trajectory embeddings. TrajTok first learns a multi-resolution hexagonal cell partition from the spatial distribution of GPS points, converting noisy GPS sequences into discrete cell to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20134","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/2605.20134/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":"2605.20134","created_at":"2026-05-20T02:06:03.606169+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20134v1","created_at":"2026-05-20T02:06:03.606169+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20134","created_at":"2026-05-20T02:06:03.606169+00:00"},{"alias_kind":"pith_short_12","alias_value":"P3CEOT4ATWRY","created_at":"2026-05-20T02:06:03.606169+00:00"},{"alias_kind":"pith_short_16","alias_value":"P3CEOT4ATWRYLMD2","created_at":"2026-05-20T02:06:03.606169+00:00"},{"alias_kind":"pith_short_8","alias_value":"P3CEOT4A","created_at":"2026-05-20T02:06:03.606169+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/P3CEOT4ATWRYLMD2E3DPHUF7L4","json":"https://pith.science/pith/P3CEOT4ATWRYLMD2E3DPHUF7L4.json","graph_json":"https://pith.science/api/pith-number/P3CEOT4ATWRYLMD2E3DPHUF7L4/graph.json","events_json":"https://pith.science/api/pith-number/P3CEOT4ATWRYLMD2E3DPHUF7L4/events.json","paper":"https://pith.science/paper/P3CEOT4A"},"agent_actions":{"view_html":"https://pith.science/pith/P3CEOT4ATWRYLMD2E3DPHUF7L4","download_json":"https://pith.science/pith/P3CEOT4ATWRYLMD2E3DPHUF7L4.json","view_paper":"https://pith.science/paper/P3CEOT4A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20134&json=true","fetch_graph":"https://pith.science/api/pith-number/P3CEOT4ATWRYLMD2E3DPHUF7L4/graph.json","fetch_events":"https://pith.science/api/pith-number/P3CEOT4ATWRYLMD2E3DPHUF7L4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P3CEOT4ATWRYLMD2E3DPHUF7L4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P3CEOT4ATWRYLMD2E3DPHUF7L4/action/storage_attestation","attest_author":"https://pith.science/pith/P3CEOT4ATWRYLMD2E3DPHUF7L4/action/author_attestation","sign_citation":"https://pith.science/pith/P3CEOT4ATWRYLMD2E3DPHUF7L4/action/citation_signature","submit_replication":"https://pith.science/pith/P3CEOT4ATWRYLMD2E3DPHUF7L4/action/replication_record"}},"created_at":"2026-05-20T02:06:03.606169+00:00","updated_at":"2026-05-20T02:06:03.606169+00:00"}