{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KLP2RQ4B5XFPHKCUUSR4DDZ4AL","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":"4a6804214bdddaac914311b072a3302a228977bbeacab739c3b7b34ffcfb4698","cross_cats_sorted":["cs.AI","cs.GR","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-22T17:55:13Z","title_canon_sha256":"ccbc359fc601dc916e1317549f5addd2d9c7be63361b2e77396eef62ee1d1036"},"schema_version":"1.0","source":{"id":"2605.23892","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23892","created_at":"2026-05-25T02:02:38Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23892v1","created_at":"2026-05-25T02:02:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23892","created_at":"2026-05-25T02:02:38Z"},{"alias_kind":"pith_short_12","alias_value":"KLP2RQ4B5XFP","created_at":"2026-05-25T02:02:38Z"},{"alias_kind":"pith_short_16","alias_value":"KLP2RQ4B5XFPHKCU","created_at":"2026-05-25T02:02:38Z"},{"alias_kind":"pith_short_8","alias_value":"KLP2RQ4B","created_at":"2026-05-25T02:02:38Z"}],"graph_snapshots":[{"event_id":"sha256:892b275f6689d07b3b42ab8951514a48616cf79b26aa97157743bf2cc1e4631d","target":"graph","created_at":"2026-05-25T02:02:38Z","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/2605.23892/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual geometry transformers have become powerful architectures for multi-view 3D reconstruction, enabling joint prediction of multiple 3D attributes in a feed-forward manner. However, their computational cost grows quadratically with the input sequence length due to the global attention layers inside these models. This limits both their scalability and efficiency. In this work, we address this challenge with a simple yet general strategy: restricting the number of key/value tokens that each query interacts with during global attention. To achieve effective token selection, we introduce a two-","authors_text":"Erik Sandstr\\\"om, Federico Tombari, Igor Gilitschenski, Marie-Julie Rakotosaona, Michael Oechsle, Shuhong Zheng","cross_cats":["cs.AI","cs.GR","cs.LG","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-22T17:55:13Z","title":"Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23892","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":"sha256:77c56538c6923e6c1de3b2891c2d9f4d54538aabf205fc92adf76cc4620d1889","target":"record","created_at":"2026-05-25T02:02:38Z","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":"4a6804214bdddaac914311b072a3302a228977bbeacab739c3b7b34ffcfb4698","cross_cats_sorted":["cs.AI","cs.GR","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-22T17:55:13Z","title_canon_sha256":"ccbc359fc601dc916e1317549f5addd2d9c7be63361b2e77396eef62ee1d1036"},"schema_version":"1.0","source":{"id":"2605.23892","kind":"arxiv","version":1}},"canonical_sha256":"52dfa8c381edcaf3a854a4a3c18f3c02e433f239401470621684561277ae1c36","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52dfa8c381edcaf3a854a4a3c18f3c02e433f239401470621684561277ae1c36","first_computed_at":"2026-05-25T02:02:38.112782Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:02:38.112782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5NVRIFxHeQKmOBqhgtReqrBbTiiLEyCij/CgCEBwo/Uja4tVculAZpBcba7ZjsywhxwBfHUdSj9QcHXIMTfyAA==","signature_status":"signed_v1","signed_at":"2026-05-25T02:02:38.113558Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.23892","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77c56538c6923e6c1de3b2891c2d9f4d54538aabf205fc92adf76cc4620d1889","sha256:892b275f6689d07b3b42ab8951514a48616cf79b26aa97157743bf2cc1e4631d"],"state_sha256":"4f76d9d54a6af6602f9a42d5719892e0aa0752f1e3744c702e4184d017ac0c7d"}