{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2BRX35TCR7CQOOEER5IWO4LBL2","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":"2f2780dc8f05196d06c40d06e2229096f86fc29765bef2f69f557c675781bc03","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-03T02:57:09Z","title_canon_sha256":"4c6a2280a75713a1845b47fb955d06a3176d041fef4316919d4fb64630c6f488"},"schema_version":"1.0","source":{"id":"2606.07654","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07654","created_at":"2026-06-09T00:04:45Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07654v1","created_at":"2026-06-09T00:04:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07654","created_at":"2026-06-09T00:04:45Z"},{"alias_kind":"pith_short_12","alias_value":"2BRX35TCR7CQ","created_at":"2026-06-09T00:04:45Z"},{"alias_kind":"pith_short_16","alias_value":"2BRX35TCR7CQOOEE","created_at":"2026-06-09T00:04:45Z"},{"alias_kind":"pith_short_8","alias_value":"2BRX35TC","created_at":"2026-06-09T00:04:45Z"}],"graph_snapshots":[{"event_id":"sha256:18e7064657ba4432368194aefc7bfe7ebbb0b8421fd9eb41aa3e18e7f110f6f0","target":"graph","created_at":"2026-06-09T00:04:45Z","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/2606.07654/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-vector visual document retrievers achieve strong fine-grained matching by representing each page with multiple vectors from deep Vision-Language Models (VLMs), but this design makes deployment expensive in both storage and computational overhead. Existing efficiency techniques usually optimize only part of this budget, leaving multimodal retrievers without a unified way to trade accuracy for both vector width and encoder depth. Therefore, we propose MM-Matryoshka, a 2D Matryoshka training framework for budget-elastic Visual Document Retrieval (VDR), enabling ColPali-style multi-vector re","authors_text":"Haowen Xiang, Jiahao Huo, Mingdong Ou, Xuming Hu, Yibo Yan, Yi Cao, Yu Huang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-03T02:57:09Z","title":"MM-Matryoshka: Towards Budget-Elastic Visual Document Retrieval via a 2D Multimodal Matryoshka Training Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07654","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":"sha256:6f43f8ab36e9d5afa9b2f3a191ab39710391b838fb6a80c8c1369a29be2b2090","target":"record","created_at":"2026-06-09T00:04:45Z","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":"2f2780dc8f05196d06c40d06e2229096f86fc29765bef2f69f557c675781bc03","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-03T02:57:09Z","title_canon_sha256":"4c6a2280a75713a1845b47fb955d06a3176d041fef4316919d4fb64630c6f488"},"schema_version":"1.0","source":{"id":"2606.07654","kind":"arxiv","version":1}},"canonical_sha256":"d0637df6628fc50738848f516771615ebed89e1775d8130f8a3c1db0dfebe50f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d0637df6628fc50738848f516771615ebed89e1775d8130f8a3c1db0dfebe50f","first_computed_at":"2026-06-09T00:04:45.928310Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T00:04:45.928310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F7LlX0kIYgNIMGvqFGdejO3uN0/MtKd7mrP1FOATmmNylKF7YrbiZ7r+bJeDX9RPdruhITw9bNYzZyGyRxIyDA==","signature_status":"signed_v1","signed_at":"2026-06-09T00:04:45.928724Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07654","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f43f8ab36e9d5afa9b2f3a191ab39710391b838fb6a80c8c1369a29be2b2090","sha256:18e7064657ba4432368194aefc7bfe7ebbb0b8421fd9eb41aa3e18e7f110f6f0"],"state_sha256":"a67e1d2cdcc96cb1b1b1ee29ae115350cac345194a7b48c5fc91dd78a3115124"}