{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FCWBTM2YARPLKXPICU2V4QWSM4","merge_version":"pith-open-graph-merge-v1","event_count":6,"valid_event_count":6,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"dbb98f436671cb40b968d24f1afa4ef563bbad4ddadc59386ee0fdd9aed23629","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-22T17:08:37Z","title_canon_sha256":"4cb4c529e346b02936f85ba407da4575d77564a05ccfee9357d7aaf24b9aced9"},"schema_version":"1.0","source":{"id":"2605.23856","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23856","created_at":"2026-05-25T02:02:36Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23856v1","created_at":"2026-05-25T02:02:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23856","created_at":"2026-05-25T02:02:36Z"},{"alias_kind":"pith_short_12","alias_value":"FCWBTM2YARPL","created_at":"2026-05-25T02:02:36Z"},{"alias_kind":"pith_short_16","alias_value":"FCWBTM2YARPLKXPI","created_at":"2026-05-25T02:02:36Z"},{"alias_kind":"pith_short_8","alias_value":"FCWBTM2Y","created_at":"2026-05-25T02:02:36Z"}],"graph_snapshots":[{"event_id":"sha256:d33ceea7e71608b227991f34257896cf896142c4832e6dbe68d09d9f2ffc150b","target":"graph","created_at":"2026-05-25T02:02:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.23856/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Arno Solin, Jiarui Guan, Juho Kannala, Wenshuai Zhao, Yue Pei, Ziliang Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-22T17:08:37Z","title":"Point Tracking Improves World Action Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23856","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:be2eb6eb29276234c5ec65bbb26cd46dd53751ab153c2e9457e8749970b9c3ed","target":"record","created_at":"2026-05-25T02:02:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"dbb98f436671cb40b968d24f1afa4ef563bbad4ddadc59386ee0fdd9aed23629","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-22T17:08:37Z","title_canon_sha256":"4cb4c529e346b02936f85ba407da4575d77564a05ccfee9357d7aaf24b9aced9"},"schema_version":"1.0","source":{"id":"2605.23856","kind":"arxiv","version":1}},"canonical_sha256":"28ac19b358045eb55de815355e42d2671f82df32d97062a7e53f236344863c79","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28ac19b358045eb55de815355e42d2671f82df32d97062a7e53f236344863c79","first_computed_at":"2026-05-25T02:02:36.193449Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:02:36.193449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vmXlQOvdA4Lo2hF1dW2p3PRyFNQ1U5rDS5Btnw4sfPaE0gbJ7ZzyvdWTekiKaZBx9G7Y283D/4WsUuDTz0MfCQ==","signature_status":"signed_v1","signed_at":"2026-05-25T02:02:36.194217Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.23856","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:3b587669398384919073a2d97273b35b6eea53fd6554e67d2ff8d47d674237f3","sha256:6c508a0a502e38627da848462a2d9e3e68c7e6b016571e7a215d946c649b53b8","sha256:d2f21b3041997f61546e3c55d18ee3a2981a4da3aa6a06066e5279c9734bfb72","sha256:dfd6c29b534daaf7c828ce39c8b172e63badef65d1e1af31ad3622c6f6b12830"]}],"invalid_events":[],"applied_event_ids":["sha256:be2eb6eb29276234c5ec65bbb26cd46dd53751ab153c2e9457e8749970b9c3ed","sha256:d33ceea7e71608b227991f34257896cf896142c4832e6dbe68d09d9f2ffc150b"],"state_sha256":"d3ddc643e65b3eb63fd278473ae1200387736af814295efd0bc1dc523a1dcd7b"}