{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DT75QUVFHXCJUAUORIQZ4OOZ55","short_pith_number":"pith:DT75QUVF","schema_version":"1.0","canonical_sha256":"1cffd852a53dc49a028e8a219e39d9ef71d1bedd18e007a73987315519ecfb9a","source":{"kind":"arxiv","id":"2608.13489","version":1},"attestation_state":"computed","paper":{"title":"DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Datao Tang, DreamX Team, Geng Li, Jifan Li, Jing Tang, Jun Wang, Pengfei Zhang, Qingfeng Shi, Rui Chen, Xiangxiang Chu","submitted_at":"2026-08-13T17:18:09Z","abstract_excerpt":"We present \\textbf{DreamX-Phi 1.0}, an action-conditioned video world model for robotic manipulation that, given an observed frame, a language instruction, and a prescribed action sequence comprising end-effector poses and gripper states, predicts the resulting future observations. Yet realism alone does not guarantee faithfulness: a convincing rollout can still move the wrong arm or lose the manipulated object. To ensure the prediction respects each arm's commanded path, we inject per-arm $\\mathrm{SE}(3)$ transformations into attention via \\textbf{PRoPE-style geometric encoding}, preserving a"},"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":"2608.13489","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-13T17:18:09Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"07326a825d5c442f9918a8fa2aada1f469f3000806598d5caac5043e85e0a4d3","abstract_canon_sha256":"5590ada59962f2a551bfe993e6cc3785bb3484e44fa6456ab29255d423f5a07f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T01:24:51.589009Z","signature_b64":"uRdzSV50BHx3gZ78ioG4Q28VD++6CT27h9NdPL3fnPV3/yH41nsJ9ZaXzwsw8qEgGksCygVNzZZxTpuh/pIEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cffd852a53dc49a028e8a219e39d9ef71d1bedd18e007a73987315519ecfb9a","last_reissued_at":"2026-08-14T01:24:51.586697Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T01:24:51.586697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Datao Tang, DreamX Team, Geng Li, Jifan Li, Jing Tang, Jun Wang, Pengfei Zhang, Qingfeng Shi, Rui Chen, Xiangxiang Chu","submitted_at":"2026-08-13T17:18:09Z","abstract_excerpt":"We present \\textbf{DreamX-Phi 1.0}, an action-conditioned video world model for robotic manipulation that, given an observed frame, a language instruction, and a prescribed action sequence comprising end-effector poses and gripper states, predicts the resulting future observations. Yet realism alone does not guarantee faithfulness: a convincing rollout can still move the wrong arm or lose the manipulated object. To ensure the prediction respects each arm's commanded path, we inject per-arm $\\mathrm{SE}(3)$ transformations into attention via \\textbf{PRoPE-style geometric encoding}, preserving a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.13489","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/2608.13489/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":"2608.13489","created_at":"2026-08-14T01:24:51.588277+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.13489v1","created_at":"2026-08-14T01:24:51.588277+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.13489","created_at":"2026-08-14T01:24:51.588277+00:00"},{"alias_kind":"pith_short_12","alias_value":"DT75QUVFHXCJ","created_at":"2026-08-14T01:24:51.588277+00:00"},{"alias_kind":"pith_short_16","alias_value":"DT75QUVFHXCJUAUO","created_at":"2026-08-14T01:24:51.588277+00:00"},{"alias_kind":"pith_short_8","alias_value":"DT75QUVF","created_at":"2026-08-14T01:24:51.588277+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/DT75QUVFHXCJUAUORIQZ4OOZ55","json":"https://pith.science/pith/DT75QUVFHXCJUAUORIQZ4OOZ55.json","graph_json":"https://pith.science/api/pith-number/DT75QUVFHXCJUAUORIQZ4OOZ55/graph.json","events_json":"https://pith.science/api/pith-number/DT75QUVFHXCJUAUORIQZ4OOZ55/events.json","paper":"https://pith.science/paper/DT75QUVF"},"agent_actions":{"view_html":"https://pith.science/pith/DT75QUVFHXCJUAUORIQZ4OOZ55","download_json":"https://pith.science/pith/DT75QUVFHXCJUAUORIQZ4OOZ55.json","view_paper":"https://pith.science/paper/DT75QUVF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.13489&json=true","fetch_graph":"https://pith.science/api/pith-number/DT75QUVFHXCJUAUORIQZ4OOZ55/graph.json","fetch_events":"https://pith.science/api/pith-number/DT75QUVFHXCJUAUORIQZ4OOZ55/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DT75QUVFHXCJUAUORIQZ4OOZ55/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DT75QUVFHXCJUAUORIQZ4OOZ55/action/storage_attestation","attest_author":"https://pith.science/pith/DT75QUVFHXCJUAUORIQZ4OOZ55/action/author_attestation","sign_citation":"https://pith.science/pith/DT75QUVFHXCJUAUORIQZ4OOZ55/action/citation_signature","submit_replication":"https://pith.science/pith/DT75QUVFHXCJUAUORIQZ4OOZ55/action/replication_record"}},"created_at":"2026-08-14T01:24:51.588277+00:00","updated_at":"2026-08-14T01:24:51.588277+00:00"}