{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TCCEWMUCMOS3DL3L5MBZBLCZQZ","short_pith_number":"pith:TCCEWMUC","schema_version":"1.0","canonical_sha256":"98844b328263a5b1af6beb0390ac5986664ae24358db40ed9e90264f1ce737b0","source":{"kind":"arxiv","id":"2603.00461","version":3},"attestation_state":"computed","paper":{"title":"ReMoT: Reinforcement Learning with Motion Contrast Triplets","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cong Wan, Jiangyang Li, Lin Peng, SongLin Dong, Yifan Bai, Yihong Gong, Zeyu Guo, Zhiheng Ma","submitted_at":"2026-02-28T04:42:34Z","abstract_excerpt":"We present ReMoT, a unified training paradigm to systematically address the fundamental shortcomings of VLMs in spatio-temporal consistency -- a critical failure point in navigation, robotics, and autonomous driving. ReMoT integrates two core components: (1) A rule-based automatic framework that generates ReMoT-16K, a large-scale (16.5K triplets) motion-contrast dataset derived from video meta-annotations, surpassing costly manual or model-based generation. (2) Group Relative Policy Optimization, which we empirically validate yields optimal performance and data efficiency for learning this con"},"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":"2603.00461","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-28T04:42:34Z","cross_cats_sorted":[],"title_canon_sha256":"1e01acc9a394335f9770d8f509bc1603c0e60979504590c51778e410fb84de6b","abstract_canon_sha256":"19160a2d804af6fc7a76921f983a820897fb59c7c9aa47fa5832be58fa36f895"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:31.861212Z","signature_b64":"/aEVa4F7PLPFIsG5yPD8GKnRL83ehUyCMDCgWlvqWsuwyG4jab8aALWpiLzVx0zG+F2VPYZPawJUjAOXO6izBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98844b328263a5b1af6beb0390ac5986664ae24358db40ed9e90264f1ce737b0","last_reissued_at":"2026-06-11T01:09:31.860083Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:31.860083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReMoT: Reinforcement Learning with Motion Contrast Triplets","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cong Wan, Jiangyang Li, Lin Peng, SongLin Dong, Yifan Bai, Yihong Gong, Zeyu Guo, Zhiheng Ma","submitted_at":"2026-02-28T04:42:34Z","abstract_excerpt":"We present ReMoT, a unified training paradigm to systematically address the fundamental shortcomings of VLMs in spatio-temporal consistency -- a critical failure point in navigation, robotics, and autonomous driving. ReMoT integrates two core components: (1) A rule-based automatic framework that generates ReMoT-16K, a large-scale (16.5K triplets) motion-contrast dataset derived from video meta-annotations, surpassing costly manual or model-based generation. (2) Group Relative Policy Optimization, which we empirically validate yields optimal performance and data efficiency for learning this con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.00461","kind":"arxiv","version":3},"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/2603.00461/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":"2603.00461","created_at":"2026-06-11T01:09:31.860245+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.00461v3","created_at":"2026-06-11T01:09:31.860245+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.00461","created_at":"2026-06-11T01:09:31.860245+00:00"},{"alias_kind":"pith_short_12","alias_value":"TCCEWMUCMOS3","created_at":"2026-06-11T01:09:31.860245+00:00"},{"alias_kind":"pith_short_16","alias_value":"TCCEWMUCMOS3DL3L","created_at":"2026-06-11T01:09:31.860245+00:00"},{"alias_kind":"pith_short_8","alias_value":"TCCEWMUC","created_at":"2026-06-11T01:09:31.860245+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/TCCEWMUCMOS3DL3L5MBZBLCZQZ","json":"https://pith.science/pith/TCCEWMUCMOS3DL3L5MBZBLCZQZ.json","graph_json":"https://pith.science/api/pith-number/TCCEWMUCMOS3DL3L5MBZBLCZQZ/graph.json","events_json":"https://pith.science/api/pith-number/TCCEWMUCMOS3DL3L5MBZBLCZQZ/events.json","paper":"https://pith.science/paper/TCCEWMUC"},"agent_actions":{"view_html":"https://pith.science/pith/TCCEWMUCMOS3DL3L5MBZBLCZQZ","download_json":"https://pith.science/pith/TCCEWMUCMOS3DL3L5MBZBLCZQZ.json","view_paper":"https://pith.science/paper/TCCEWMUC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.00461&json=true","fetch_graph":"https://pith.science/api/pith-number/TCCEWMUCMOS3DL3L5MBZBLCZQZ/graph.json","fetch_events":"https://pith.science/api/pith-number/TCCEWMUCMOS3DL3L5MBZBLCZQZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TCCEWMUCMOS3DL3L5MBZBLCZQZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TCCEWMUCMOS3DL3L5MBZBLCZQZ/action/storage_attestation","attest_author":"https://pith.science/pith/TCCEWMUCMOS3DL3L5MBZBLCZQZ/action/author_attestation","sign_citation":"https://pith.science/pith/TCCEWMUCMOS3DL3L5MBZBLCZQZ/action/citation_signature","submit_replication":"https://pith.science/pith/TCCEWMUCMOS3DL3L5MBZBLCZQZ/action/replication_record"}},"created_at":"2026-06-11T01:09:31.860245+00:00","updated_at":"2026-06-11T01:09:31.860245+00:00"}