{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3ORWK6A3MV7OO2IW5FYYON5HJH","short_pith_number":"pith:3ORWK6A3","schema_version":"1.0","canonical_sha256":"dba365781b657ee76916e9718737a749ede80095a6cd593815452eb0c3da119f","source":{"kind":"arxiv","id":"2506.02571","version":1},"attestation_state":"computed","paper":{"title":"Contrast & Compress: Learning Lightweight Embeddings for Short Trajectories","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhishek Vivekanandan, Christian Hubschneider, J. Marius Z\\\"ollner","submitted_at":"2025-06-03T07:53:04Z","abstract_excerpt":"The ability to retrieve semantically and directionally similar short-range trajectories with both accuracy and efficiency is foundational for downstream applications such as motion forecasting and autonomous navigation. However, prevailing approaches often depend on computationally intensive heuristics or latent anchor representations that lack interpretability and controllability. In this work, we propose a novel framework for learning fixed-dimensional embeddings for short trajectories by leveraging a Transformer encoder trained with a contrastive triplet loss that emphasize the importance o"},"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":"2506.02571","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-03T07:53:04Z","cross_cats_sorted":[],"title_canon_sha256":"24adc03b07397803a81304c738c4044ea9baf3773fe454193671a1c5006607aa","abstract_canon_sha256":"ecabd3559ccfc1364221cef188efe11ed81bd63b1af7d93f7273dad7e36c1911"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:04.434197Z","signature_b64":"NdrwCII7VYiWwjR1NdAY8nk9PbRILv7HxiJLVYO1xTdGgFCIGLiNvMi5LYsVddnslOdceWHGp0hQtvWu/ti5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dba365781b657ee76916e9718737a749ede80095a6cd593815452eb0c3da119f","last_reissued_at":"2026-07-05T11:15:04.433654Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:04.433654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrast & Compress: Learning Lightweight Embeddings for Short Trajectories","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhishek Vivekanandan, Christian Hubschneider, J. Marius Z\\\"ollner","submitted_at":"2025-06-03T07:53:04Z","abstract_excerpt":"The ability to retrieve semantically and directionally similar short-range trajectories with both accuracy and efficiency is foundational for downstream applications such as motion forecasting and autonomous navigation. However, prevailing approaches often depend on computationally intensive heuristics or latent anchor representations that lack interpretability and controllability. In this work, we propose a novel framework for learning fixed-dimensional embeddings for short trajectories by leveraging a Transformer encoder trained with a contrastive triplet loss that emphasize the importance o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02571","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/2506.02571/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":"2506.02571","created_at":"2026-07-05T11:15:04.433715+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02571v1","created_at":"2026-07-05T11:15:04.433715+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02571","created_at":"2026-07-05T11:15:04.433715+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ORWK6A3MV7O","created_at":"2026-07-05T11:15:04.433715+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ORWK6A3MV7OO2IW","created_at":"2026-07-05T11:15:04.433715+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ORWK6A3","created_at":"2026-07-05T11:15:04.433715+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21321","citing_title":"Objective-Behavior Alignment: Diagnostics for MORL Policy Selection","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01393","citing_title":"Recall to Predict: Grounding Motion Forecasting in Interpretable Motion Bank","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3ORWK6A3MV7OO2IW5FYYON5HJH","json":"https://pith.science/pith/3ORWK6A3MV7OO2IW5FYYON5HJH.json","graph_json":"https://pith.science/api/pith-number/3ORWK6A3MV7OO2IW5FYYON5HJH/graph.json","events_json":"https://pith.science/api/pith-number/3ORWK6A3MV7OO2IW5FYYON5HJH/events.json","paper":"https://pith.science/paper/3ORWK6A3"},"agent_actions":{"view_html":"https://pith.science/pith/3ORWK6A3MV7OO2IW5FYYON5HJH","download_json":"https://pith.science/pith/3ORWK6A3MV7OO2IW5FYYON5HJH.json","view_paper":"https://pith.science/paper/3ORWK6A3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02571&json=true","fetch_graph":"https://pith.science/api/pith-number/3ORWK6A3MV7OO2IW5FYYON5HJH/graph.json","fetch_events":"https://pith.science/api/pith-number/3ORWK6A3MV7OO2IW5FYYON5HJH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ORWK6A3MV7OO2IW5FYYON5HJH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ORWK6A3MV7OO2IW5FYYON5HJH/action/storage_attestation","attest_author":"https://pith.science/pith/3ORWK6A3MV7OO2IW5FYYON5HJH/action/author_attestation","sign_citation":"https://pith.science/pith/3ORWK6A3MV7OO2IW5FYYON5HJH/action/citation_signature","submit_replication":"https://pith.science/pith/3ORWK6A3MV7OO2IW5FYYON5HJH/action/replication_record"}},"created_at":"2026-07-05T11:15:04.433715+00:00","updated_at":"2026-07-05T11:15:04.433715+00:00"}