{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_d728df1c6d35a0aa7a46cc12340b22a5ae16b7939d0f665f073cdc69bb93b8a6","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_d728df1c6d35a0aa7a46cc12340b22a5ae16b7939d0f665f073cdc69bb93b8a6","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"94bd0397fcc69767ac898a0e984f7e87b86d4b43673912e7aa9cda4145871052","published":"Mon, 25 May 2026 00:00:00 -0400","receipt_hash":"94bd0397fcc69767ac898a0e984f7e87b86d4b43673912e7aa9cda4145871052","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"94bd0397fcc69767ac898a0e984f7e87b86d4b43673912e7aa9cda4145871052","observed_at":"2026-05-25T04:43:48.841018Z","parent_run_hash":"56713422f06ad87427cd8cdcdb1ed341feb016b33c37198d9b168328d1df15fb","published":"Mon, 25 May 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2605.23482v1 Announce Type: cross \nAbstract: Dataset distillation compresses large training sets into compact synthetic datasets while preserving downstream performance. As modern systems increasingly operate on paired vision-language inputs, multimodal distillation must preserve representation quality and cross-modal alignment under tight compute and memory budgets, yet prior methods often require heavy computes and overlook their correlations. To address this, we present Multimodal Distribution Matching (MDM), a geometry-aware framework for efficient and generalizable multimodal distillation. Specifically, MDM integrates complementary components at the data, model, and loss levels. At the data level, it initializes synthetic image-text pairs by sampling from clusters in the joint embedding space. At the model level, it forms a mixed teacher by interpolating independently fine-tuned models in weight space according to their angular deviation from the pretrained anchor. At the lo","title":"Multimodal Distribution Matching for Vision-Language Dataset Distillation","url":"https://arxiv.org/abs/2605.23482","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.23482v1 Announce Type: cross \nAbstract: Dataset distillation compresses large training sets into compact synthetic datasets while preserving downstream performance. As modern systems increasingly operate on paired vision-language inputs, multimodal distillation must preserve representation quality and cross-modal alignment under tight compute and memory budgets, yet prior methods often require heavy computes and overlook their correlations. To address this, we present Multimodal Distribution Matching (MDM), a geometry-aware framework for efficient and generalizable multimodal distillation. Specifically, MDM integrates complementary components at the data, model, and loss levels. At the data level, it initializes synthetic image-text pairs by sampling from clusters in the joint embedding space. At the model level, it forms a mixed teacher by interpolating independently fine-tuned models in weight space according to their angular deviation from the pretrained anchor. At the lo","title":"Multimodal Distribution Matching for Vision-Language Dataset Distillation","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-25T04:43:48Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.23482"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:ccced0cb1b0cac2cc3b237c5342f2e849b4032026b09296e07aeba7676e3694143217f4b72ddd7ddd35cd0ac692bda2fa7bfc779ba2d042005734f0d3b2a3c05","signer":"crovia.substrate","subject":{"observed_at":"2026-05-25T04:43:48Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.23482"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"08c2a80d2440b2a9c3e94b80c65957fcecddea3743cb87aeaf5e57cedadf88a2","leaf_index":149628,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"e4eaea3d10e878a3f918e1bda1e25feeaea09a890237df5059476b0984aac337","side":"right"},{"sibling":"d1c90d2721269eed89e61ce56cdbf8d7d460d33a19efa32b89b0c98c0e88223f","side":"right"},{"sibling":"406b0f7c071f0e87659665dc448eb070ccc0e1713cfd37292af89db50c4a581e","side":"left"},{"sibling":"cfa4689cd3fbc89fbe043bd61b21e615ba5f75bfe6e3f763f4061583a9d79ebc","side":"left"},{"sibling":"333dfe5710df18a838c953dd598c82d68b4ccb83573b2680bedd21eb5c162b7d","side":"left"},{"sibling":"5df497e37e962e4d5fdbb2e4e3b53d14c2262282fd731be5587421ab6dfeeae8","side":"left"},{"sibling":"8d24747938b263ade5303d014d2d33076a8efb5253cd81037ad041974a0da523","side":"left"},{"sibling":"d1061d17b49728c47097edde7c7b5b412447bff3df4a459862df4fa81f21f616","side":"right"},{"sibling":"e044acc52c31efe134c902c984299ea3452b42df993d096ed61ad8be9d530bbc","side":"right"},{"sibling":"6be461ecf12dedf98a31921aa7b5c32d4a32df6897e0f697b8bf1a4ba3e2d324","side":"right"},{"sibling":"c2861a8cef3eb66bf2726aa377c24a6bf6e8b7489dcd0e870b61d62a35ccadfb","side":"right"},{"sibling":"134949308b15cffd6792ee2cf678119af34d69a64764d7c89cd47573c94e1cda","side":"left"},{"sibling":"debbc1a6232ea7970009b91bdc2345041b2de5ac59551f955855d579001e512c","side":"right"},{"sibling":"216869846f40bd905626884f58cb67b9019e488b3656946a7808c436ab7339ac","side":"right"},{"sibling":"35ca36cee447f0ef7064a25d55f59357c66901e31427729c4c1d8b14aa8adb6c","side":"left"},{"sibling":"e734b0c6d6d13acb5f4cf00367b3913e5bbf1aa717377aa4e4820c6de24b7673","side":"right"},{"sibling":"4bbb7f78e96179bb9cdd06d7207b66b3503ab68e4880438263025b04ebe8f7ec","side":"right"},{"sibling":"d841ad93efda0869e5eb97678f348f03f5caab4353e05ff4bf18f47fb945b822","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":149835,"merkle_root":"51484a548bc0cf3d178eec868e98935c87f0aa83369143b7c96b048585e5ba01","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260525T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-25T05:37:33Z","sig_algorithm":"ed25519","signature":"99a657e53a015ace0bade5d7fbb3f60f950b6d1e1128251a63afcc454a492422cae5efdc0c18503b4f7e62f371bd48f2889be78d9048c4681d6c1e73f754d705","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_d728df1c6d35a0aa7a46cc12340b22a5ae16b7939d0f665f073cdc69bb93b8a6"}}