{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LQLXX7HUPKMK2IE5RQGVFHK5RR","short_pith_number":"pith:LQLXX7HU","schema_version":"1.0","canonical_sha256":"5c177bfcf47a98ad209d8c0d529d5d8c7d11fa830c9a084abee944d62bb2d6c7","source":{"kind":"arxiv","id":"2412.05675","version":2},"attestation_state":"computed","paper":{"title":"M$^3$PC: Test-time Model Predictive Control for Pretrained Masked Trajectory Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Kehan Wen, Lei Ke, Yao Mu, Yutong Hu","submitted_at":"2024-12-07T14:44:22Z","abstract_excerpt":"Recent work in Offline Reinforcement Learning (RL) has shown that a unified Transformer trained under a masked auto-encoding objective can effectively capture the relationships between different modalities (e.g., states, actions, rewards) within given trajectory datasets. However, this information has not been fully exploited during the inference phase, where the agent needs to generate an optimal policy instead of just reconstructing masked components from unmasked ones. Given that a pretrained trajectory model can act as both a Policy Model and a World Model with appropriate mask patterns, w"},"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":"2412.05675","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-07T14:44:22Z","cross_cats_sorted":["cs.RO","cs.SY","eess.SY"],"title_canon_sha256":"c1a094117ca4394b56b1fcfc3493c67418e33af7cef455edc16fb11ce9c43231","abstract_canon_sha256":"2316a6f1eed173b7695242519616f9e43b22fab0a0b31b0bb95a6dd65833e099"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:29.254232Z","signature_b64":"NhAmh2s3KLmkZliwWdjGA4s2wD/GArTLHAuEoYXbEimNx+RuEolOD6anBk8bI88XvgyQcc78jzk7VLZIkha9Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c177bfcf47a98ad209d8c0d529d5d8c7d11fa830c9a084abee944d62bb2d6c7","last_reissued_at":"2026-07-05T10:10:29.253760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:29.253760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M$^3$PC: Test-time Model Predictive Control for Pretrained Masked Trajectory Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Kehan Wen, Lei Ke, Yao Mu, Yutong Hu","submitted_at":"2024-12-07T14:44:22Z","abstract_excerpt":"Recent work in Offline Reinforcement Learning (RL) has shown that a unified Transformer trained under a masked auto-encoding objective can effectively capture the relationships between different modalities (e.g., states, actions, rewards) within given trajectory datasets. However, this information has not been fully exploited during the inference phase, where the agent needs to generate an optimal policy instead of just reconstructing masked components from unmasked ones. Given that a pretrained trajectory model can act as both a Policy Model and a World Model with appropriate mask patterns, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05675","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/2412.05675/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":"2412.05675","created_at":"2026-07-05T10:10:29.253817+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05675v2","created_at":"2026-07-05T10:10:29.253817+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05675","created_at":"2026-07-05T10:10:29.253817+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQLXX7HUPKMK","created_at":"2026-07-05T10:10:29.253817+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQLXX7HUPKMK2IE5","created_at":"2026-07-05T10:10:29.253817+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQLXX7HU","created_at":"2026-07-05T10:10:29.253817+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00113","citing_title":"World Models for Robotic Manipulation: A Survey","ref_index":95,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LQLXX7HUPKMK2IE5RQGVFHK5RR","json":"https://pith.science/pith/LQLXX7HUPKMK2IE5RQGVFHK5RR.json","graph_json":"https://pith.science/api/pith-number/LQLXX7HUPKMK2IE5RQGVFHK5RR/graph.json","events_json":"https://pith.science/api/pith-number/LQLXX7HUPKMK2IE5RQGVFHK5RR/events.json","paper":"https://pith.science/paper/LQLXX7HU"},"agent_actions":{"view_html":"https://pith.science/pith/LQLXX7HUPKMK2IE5RQGVFHK5RR","download_json":"https://pith.science/pith/LQLXX7HUPKMK2IE5RQGVFHK5RR.json","view_paper":"https://pith.science/paper/LQLXX7HU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05675&json=true","fetch_graph":"https://pith.science/api/pith-number/LQLXX7HUPKMK2IE5RQGVFHK5RR/graph.json","fetch_events":"https://pith.science/api/pith-number/LQLXX7HUPKMK2IE5RQGVFHK5RR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQLXX7HUPKMK2IE5RQGVFHK5RR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQLXX7HUPKMK2IE5RQGVFHK5RR/action/storage_attestation","attest_author":"https://pith.science/pith/LQLXX7HUPKMK2IE5RQGVFHK5RR/action/author_attestation","sign_citation":"https://pith.science/pith/LQLXX7HUPKMK2IE5RQGVFHK5RR/action/citation_signature","submit_replication":"https://pith.science/pith/LQLXX7HUPKMK2IE5RQGVFHK5RR/action/replication_record"}},"created_at":"2026-07-05T10:10:29.253817+00:00","updated_at":"2026-07-05T10:10:29.253817+00:00"}