{"_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_f8fa32fd384cf4e38ee7e42f223aab46461d756010297b794f2fe6b7d628e8f9","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_f8fa32fd384cf4e38ee7e42f223aab46461d756010297b794f2fe6b7d628e8f9","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"0e1b210cad94369c892b88a6d3059ed3bd39f1acd739024b6e798acdcf27bde2","published":"Tue, 14 Jul 2026 00:00:00 -0400","receipt_hash":"0e1b210cad94369c892b88a6d3059ed3bd39f1acd739024b6e798acdcf27bde2","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":"0e1b210cad94369c892b88a6d3059ed3bd39f1acd739024b6e798acdcf27bde2","observed_at":"2026-07-14T04:43:37.834979Z","parent_run_hash":"66b89520a448b8d9fe7d8f602ef38b82b6c95e57f532ce72de51375b41870477","published":"Tue, 14 Jul 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:2604.22823v2 Announce Type: replace-cross \nAbstract: Multimodal Large Language Models (MLLMs) rely on multimodal pre-training over diverse data sources, where different datasets often induce complementary cross-modal alignment capabilities. Model merging provides a cost-effective mechanism for integrating multiple expert MLLMs with complementary strengths into a unified model. However, existing model merging research mainly focuses on post-finetuning scenarios, leaving the pre-training stage largely unexplored. We argue that the core of MLLM pre-training lies in establishing effective cross-modal alignment, which bridges visual and textual representations into a unified semantic space. Motivated by this insight, we introduce the post-alignment merging task, which aims to integrate cross-modal alignment capabilities learned from heterogeneous multimodal pre-training. This setting introduces two key challenges: cross-domain parameter interference, where parameter updates learned fr","title":"PivotMerge: Bridging Heterogeneous Multimodal Pre-training via Post-Alignment Model Merging","url":"https://arxiv.org/abs/2604.22823","vendor":"arxiv_cs_ai"},"summary":"arXiv:2604.22823v2 Announce Type: replace-cross \nAbstract: Multimodal Large Language Models (MLLMs) rely on multimodal pre-training over diverse data sources, where different datasets often induce complementary cross-modal alignment capabilities. Model merging provides a cost-effective mechanism for integrating multiple expert MLLMs with complementary strengths into a unified model. However, existing model merging research mainly focuses on post-finetuning scenarios, leaving the pre-training stage largely unexplored. We argue that the core of MLLM pre-training lies in establishing effective cross-modal alignment, which bridges visual and textual representations into a unified semantic space. Motivated by this insight, we introduce the post-alignment merging task, which aims to integrate cross-modal alignment capabilities learned from heterogeneous multimodal pre-training. This setting introduces two key challenges: cross-domain parameter interference, where parameter updates learned fr","title":"PivotMerge: Bridging Heterogeneous Multimodal Pre-training via Post-Alignment Model Merging","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-14T04:43:37Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2604.22823"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:4057e91809fdae34f7e10b41d7b65fede6696e2c8db7cd0451d04cc52abe355701db4e3c6137d7e4415dc0a2b84e4ca0a5987daec21cdceded5fa669a2f3f505","signer":"crovia.substrate","subject":{"observed_at":"2026-07-14T04:43:37Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2604.22823"},"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":"a148b069c88e7766f297897dc2ca34dc444ab7fc7ee2cd8a7e4f26f057c2714e","leaf_index":313226,"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":"16369ae30ed1bcf5a017f8fcbb68e0d553346a0d6395e984618477f2665ef16b","side":"right"},{"sibling":"8c27ff48cc8637559ddfbd57da260148c7079a9cd845e3de8008957e9e31e102","side":"left"},{"sibling":"9a65fa132855ae14ca24f0a0a6d6301e6b092c3cfcafb37e679483d01c40a7ec","side":"right"},{"sibling":"b3a48b099c93b90b512eed8eea77b213b9c7cc0b67d2979e759f1ae5c1d9d7cf","side":"left"},{"sibling":"f2749e9cad9cc537979ff97022b980347f1a32852230588b5aa00dc8cb0d35a8","side":"right"},{"sibling":"eaace69d5ad78fc736b64dc693935b021abfe4f551f3722ae52bd567b65e9b38","side":"right"},{"sibling":"80b26938907f117f51f78fb01183c45c33c68065966037db1d53385866d28084","side":"right"},{"sibling":"986f162bfceab84459f12c93071b6c3d1b7bd7f19c776e546d33962c0b6427f6","side":"left"},{"sibling":"ae8fbfdec46ce02d0a92359c6a034f0439394d13e731da90290f5ca7192e6da4","side":"left"},{"sibling":"8393dc03644000353c5d503b6ec261c022cd2aa85a649223916153bc8af2dc75","side":"left"},{"sibling":"1627ce6908965f2e5fbc7c16bc8e247867478c587014561d0de1359dc2dc0afc","side":"left"},{"sibling":"74e1ba9fd48bdd0f52777dd5b56c10706e73f42629013748eca13ef113cd59db","side":"right"},{"sibling":"682fd39539db5bce908d0ab6f180374728fed6b34a9a8c87c7b4eb5a726e30b8","side":"right"},{"sibling":"184927f71d667ac0c6ebeadb33394626973738b9107c6dc3c0c4949b44acf295","side":"right"},{"sibling":"f302542c38ba7c3aab7c9280dd60259ecec777dca6e6f71b6f0729b0b8791b72","side":"left"},{"sibling":"d8b9143917b539c543cf4448cec00131f8b807bd8004979c54ebe09798748c66","side":"left"},{"sibling":"c4c189d79669979b59d9aa976ee249c54a7e065b4a05bf49463459cc7f37428e","side":"right"},{"sibling":"19475e206bdf2698769a286db2c97c4d3f089741319f9b29a139038c6e511975","side":"right"},{"sibling":"1cecb7f447febd025aac272837c80de218aecc6485d2395a509b2a1f1b9c746e","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":313381,"merkle_root":"5f7d48580373d0ab0bc6bdf34f26de442f9a86d130946f7ee45addd1a55cb9f4","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260714T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-14T05:38:23Z","sig_algorithm":"ed25519","signature":"97364224142ed1b2a8925fed1bfba2e0a8a6a15f8ca0999b934846ad83584a78c7f0f5cd09dbc1c938b35383fcc5c8fa4b723118e30916628879d1c5fd3a9908","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_f8fa32fd384cf4e38ee7e42f223aab46461d756010297b794f2fe6b7d628e8f9"}}