{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Y72K42YQRAOW6D3SGIMCTGSXZ2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b71050752ad5733a28828cf19ab19e478556b5bb702ad38144fd1cd3dc206e46","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-08T00:28:42Z","title_canon_sha256":"13417c4ccd331166ee1b7f9251ccd1966394503156052449c783c6731f15ec99"},"schema_version":"1.0","source":{"id":"2504.05579","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.05579","created_at":"2026-07-05T10:48:30Z"},{"alias_kind":"arxiv_version","alias_value":"2504.05579v2","created_at":"2026-07-05T10:48:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05579","created_at":"2026-07-05T10:48:30Z"},{"alias_kind":"pith_short_12","alias_value":"Y72K42YQRAOW","created_at":"2026-07-05T10:48:30Z"},{"alias_kind":"pith_short_16","alias_value":"Y72K42YQRAOW6D3S","created_at":"2026-07-05T10:48:30Z"},{"alias_kind":"pith_short_8","alias_value":"Y72K42YQ","created_at":"2026-07-05T10:48:30Z"}],"graph_snapshots":[{"event_id":"sha256:5daa5944ebceea2bc36eefcf9fd269e2215943f21e0019f086e341aef6180073","target":"graph","created_at":"2026-07-05T10:48:30Z","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/2504.05579/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tracking Any Point (TAP) in a video is a challenging computer vision problem with many demonstrated applications in robotics, video editing, and 3D reconstruction. Existing methods for TAP rely heavily on complex tracking-specific inductive biases and heuristics, limiting their generality and potential for scaling. To address these challenges, we present TAPNext, a new approach that casts TAP as sequential masked token decoding. Our model is causal, tracks in a purely online fashion, and removes tracking-specific inductive biases. This enables TAPNext to run with minimal latency, and removes t","authors_text":"Artem Zholus, Carl Doersch, Ignacio Rocco, Mehdi S. M. Sajjadi, Ross Goroshin, Sarath Chandar, Skanda Koppula, Viorica Patraucean, Xu Owen He, Yi Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-08T00:28:42Z","title":"TAPNext: Tracking Any Point (TAP) as Next Token Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05579","kind":"arxiv","version":2},"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:abeff039f75e529b1b2e2565be0a5b6c97559105206adf0ad589ff58a18acb16","target":"record","created_at":"2026-07-05T10:48:30Z","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":"b71050752ad5733a28828cf19ab19e478556b5bb702ad38144fd1cd3dc206e46","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-08T00:28:42Z","title_canon_sha256":"13417c4ccd331166ee1b7f9251ccd1966394503156052449c783c6731f15ec99"},"schema_version":"1.0","source":{"id":"2504.05579","kind":"arxiv","version":2}},"canonical_sha256":"c7f4ae6b10881d6f0f723218299a57ceae138457142f0ddcf1eeb256a1d819cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7f4ae6b10881d6f0f723218299a57ceae138457142f0ddcf1eeb256a1d819cd","first_computed_at":"2026-07-05T10:48:30.406231Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:48:30.406231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0n2r5z5QlavM9mN0K/loLVL4Z/Ms0Bc1M82WyUMIPH1XWSNJKrxknnlP8IKy8OvYwfCaMATbuKWSiy/fKWaPBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:48:30.406726Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.05579","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:abeff039f75e529b1b2e2565be0a5b6c97559105206adf0ad589ff58a18acb16","sha256:5daa5944ebceea2bc36eefcf9fd269e2215943f21e0019f086e341aef6180073"],"state_sha256":"779514daf9742ffd3009ee33037f7234255e3f46291d579fd0a0e1a01bcea9e5"}