{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FCWBTM2YARPLKXPICU2V4QWSM4","short_pith_number":"pith:FCWBTM2Y","schema_version":"1.0","canonical_sha256":"28ac19b358045eb55de815355e42d2671f82df32d97062a7e53f236344863c79","source":{"kind":"arxiv","id":"2605.23856","version":1},"attestation_state":"computed","paper":{"title":"Point Tracking Improves World Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Arno Solin, Jiarui Guan, Juho Kannala, Wenshuai Zhao, Yue Pei, Ziliang Chen","submitted_at":"2026-05-22T17:08:37Z","abstract_excerpt":"Robot policy learning benefits from world-action models that capture environment dynamics, but pixel-level prediction entangles dynamics with nuisance factors such as lighting and texture, making learned representations vulnerable to task-irrelevant visual variation. We propose JOPAT, a JOint Pixel-And-Track World-Action Model that predicts latent visual observations, 2D point tracks with visibility, and actions in a single denoising diffusion transformer. The key insight is that tracks provide an explicit representation of motion that captures long-horizon dynamics and remains robust under oc"},"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":"2605.23856","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-22T17:08:37Z","cross_cats_sorted":[],"title_canon_sha256":"4cb4c529e346b02936f85ba407da4575d77564a05ccfee9357d7aaf24b9aced9","abstract_canon_sha256":"dbb98f436671cb40b968d24f1afa4ef563bbad4ddadc59386ee0fdd9aed23629"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:02:36.194217Z","signature_b64":"vmXlQOvdA4Lo2hF1dW2p3PRyFNQ1U5rDS5Btnw4sfPaE0gbJ7ZzyvdWTekiKaZBx9G7Y283D/4WsUuDTz0MfCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28ac19b358045eb55de815355e42d2671f82df32d97062a7e53f236344863c79","last_reissued_at":"2026-05-25T02:02:36.193449Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:02:36.193449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Point Tracking Improves World Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Arno Solin, Jiarui Guan, Juho Kannala, Wenshuai Zhao, Yue Pei, Ziliang Chen","submitted_at":"2026-05-22T17:08:37Z","abstract_excerpt":"Robot policy learning benefits from world-action models that capture environment dynamics, but pixel-level prediction entangles dynamics with nuisance factors such as lighting and texture, making learned representations vulnerable to task-irrelevant visual variation. We propose JOPAT, a JOint Pixel-And-Track World-Action Model that predicts latent visual observations, 2D point tracks with visibility, and actions in a single denoising diffusion transformer. The key insight is that tracks provide an explicit representation of motion that captures long-horizon dynamics and remains robust under oc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23856","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/2605.23856/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":"2605.23856","created_at":"2026-05-25T02:02:36.193578+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.23856v1","created_at":"2026-05-25T02:02:36.193578+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23856","created_at":"2026-05-25T02:02:36.193578+00:00"},{"alias_kind":"pith_short_12","alias_value":"FCWBTM2YARPL","created_at":"2026-05-25T02:02:36.193578+00:00"},{"alias_kind":"pith_short_16","alias_value":"FCWBTM2YARPLKXPI","created_at":"2026-05-25T02:02:36.193578+00:00"},{"alias_kind":"pith_short_8","alias_value":"FCWBTM2Y","created_at":"2026-05-25T02:02:36.193578+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/FCWBTM2YARPLKXPICU2V4QWSM4","json":"https://pith.science/pith/FCWBTM2YARPLKXPICU2V4QWSM4.json","graph_json":"https://pith.science/api/pith-number/FCWBTM2YARPLKXPICU2V4QWSM4/graph.json","events_json":"https://pith.science/api/pith-number/FCWBTM2YARPLKXPICU2V4QWSM4/events.json","paper":"https://pith.science/paper/FCWBTM2Y"},"agent_actions":{"view_html":"https://pith.science/pith/FCWBTM2YARPLKXPICU2V4QWSM4","download_json":"https://pith.science/pith/FCWBTM2YARPLKXPICU2V4QWSM4.json","view_paper":"https://pith.science/paper/FCWBTM2Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.23856&json=true","fetch_graph":"https://pith.science/api/pith-number/FCWBTM2YARPLKXPICU2V4QWSM4/graph.json","fetch_events":"https://pith.science/api/pith-number/FCWBTM2YARPLKXPICU2V4QWSM4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FCWBTM2YARPLKXPICU2V4QWSM4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FCWBTM2YARPLKXPICU2V4QWSM4/action/storage_attestation","attest_author":"https://pith.science/pith/FCWBTM2YARPLKXPICU2V4QWSM4/action/author_attestation","sign_citation":"https://pith.science/pith/FCWBTM2YARPLKXPICU2V4QWSM4/action/citation_signature","submit_replication":"https://pith.science/pith/FCWBTM2YARPLKXPICU2V4QWSM4/action/replication_record"}},"created_at":"2026-05-25T02:02:36.193578+00:00","updated_at":"2026-05-25T02:02:36.193578+00:00"}