{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2BRX35TCR7CQOOEER5IWO4LBL2","short_pith_number":"pith:2BRX35TC","schema_version":"1.0","canonical_sha256":"d0637df6628fc50738848f516771615ebed89e1775d8130f8a3c1db0dfebe50f","source":{"kind":"arxiv","id":"2606.07654","version":1},"attestation_state":"computed","paper":{"title":"MM-Matryoshka: Towards Budget-Elastic Visual Document Retrieval via a 2D Multimodal Matryoshka Training Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haowen Xiang, Jiahao Huo, Mingdong Ou, Xuming Hu, Yibo Yan, Yi Cao, Yu Huang","submitted_at":"2026-06-03T02:57:09Z","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"},"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":"2606.07654","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-03T02:57:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4c6a2280a75713a1845b47fb955d06a3176d041fef4316919d4fb64630c6f488","abstract_canon_sha256":"2f2780dc8f05196d06c40d06e2229096f86fc29765bef2f69f557c675781bc03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T00:04:45.928724Z","signature_b64":"F7LlX0kIYgNIMGvqFGdejO3uN0/MtKd7mrP1FOATmmNylKF7YrbiZ7r+bJeDX9RPdruhITw9bNYzZyGyRxIyDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0637df6628fc50738848f516771615ebed89e1775d8130f8a3c1db0dfebe50f","last_reissued_at":"2026-06-09T00:04:45.928310Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T00:04:45.928310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MM-Matryoshka: Towards Budget-Elastic Visual Document Retrieval via a 2D Multimodal Matryoshka Training Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haowen Xiang, Jiahao Huo, Mingdong Ou, Xuming Hu, Yibo Yan, Yi Cao, Yu Huang","submitted_at":"2026-06-03T02:57:09Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07654","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/2606.07654/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":"2606.07654","created_at":"2026-06-09T00:04:45.928384+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07654v1","created_at":"2026-06-09T00:04:45.928384+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07654","created_at":"2026-06-09T00:04:45.928384+00:00"},{"alias_kind":"pith_short_12","alias_value":"2BRX35TCR7CQ","created_at":"2026-06-09T00:04:45.928384+00:00"},{"alias_kind":"pith_short_16","alias_value":"2BRX35TCR7CQOOEE","created_at":"2026-06-09T00:04:45.928384+00:00"},{"alias_kind":"pith_short_8","alias_value":"2BRX35TC","created_at":"2026-06-09T00:04:45.928384+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/2BRX35TCR7CQOOEER5IWO4LBL2","json":"https://pith.science/pith/2BRX35TCR7CQOOEER5IWO4LBL2.json","graph_json":"https://pith.science/api/pith-number/2BRX35TCR7CQOOEER5IWO4LBL2/graph.json","events_json":"https://pith.science/api/pith-number/2BRX35TCR7CQOOEER5IWO4LBL2/events.json","paper":"https://pith.science/paper/2BRX35TC"},"agent_actions":{"view_html":"https://pith.science/pith/2BRX35TCR7CQOOEER5IWO4LBL2","download_json":"https://pith.science/pith/2BRX35TCR7CQOOEER5IWO4LBL2.json","view_paper":"https://pith.science/paper/2BRX35TC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07654&json=true","fetch_graph":"https://pith.science/api/pith-number/2BRX35TCR7CQOOEER5IWO4LBL2/graph.json","fetch_events":"https://pith.science/api/pith-number/2BRX35TCR7CQOOEER5IWO4LBL2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2BRX35TCR7CQOOEER5IWO4LBL2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2BRX35TCR7CQOOEER5IWO4LBL2/action/storage_attestation","attest_author":"https://pith.science/pith/2BRX35TCR7CQOOEER5IWO4LBL2/action/author_attestation","sign_citation":"https://pith.science/pith/2BRX35TCR7CQOOEER5IWO4LBL2/action/citation_signature","submit_replication":"https://pith.science/pith/2BRX35TCR7CQOOEER5IWO4LBL2/action/replication_record"}},"created_at":"2026-06-09T00:04:45.928384+00:00","updated_at":"2026-06-09T00:04:45.928384+00:00"}