{"_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_b287be2f10518180edd891904d45d455da1290c2c7f19a6df09f9b5d9fa15bbc","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_b287be2f10518180edd891904d45d455da1290c2c7f19a6df09f9b5d9fa15bbc","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"b61c957173291206bc4e0e8846c87ff725b4838e305ee0f77a79c9e201b61c7d","published":"Fri, 12 Jun 2026 00:00:00 -0400","receipt_hash":"b61c957173291206bc4e0e8846c87ff725b4838e305ee0f77a79c9e201b61c7d","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":"b61c957173291206bc4e0e8846c87ff725b4838e305ee0f77a79c9e201b61c7d","observed_at":"2026-06-12T04:43:44.933383Z","parent_run_hash":"a8b304a31db3809a528f5a45e58597f7bb9f23028e53b4f9ed2f5599dd731b5e","published":"Fri, 12 Jun 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:2606.13288v1 Announce Type: cross \nAbstract: Contrastively trained vision-language models like CLIP, have made remarkable progress in learning joint image-text representations, but still face challenges in compositional understanding. They often exhibit a \"bag-of-words\" behavior--struggling to capture the object relations, attribute-object bindings, and word order dependencies. This limitation arises not only from the reliance on global, single-vector representations for optimization, but also from the insufficient exploitation and modeling of the rich compositional information inherently present in paired image text data. In this work, we propose MACCO (MAsked Compositional Concept MOdeling), a framework that masks compositional concepts in one modality and reconstructs them conditioned on the full contextual information from the other, enabling the model to capture and align cross-modal compositional structures more effectively. To facilitate this process, we introduce two auxi","title":"Cross-Modal Masked Compositional Concept Modeling for Enhancing Visio-Linguistic Compositionality","url":"https://arxiv.org/abs/2606.13288","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.13288v1 Announce Type: cross \nAbstract: Contrastively trained vision-language models like CLIP, have made remarkable progress in learning joint image-text representations, but still face challenges in compositional understanding. They often exhibit a \"bag-of-words\" behavior--struggling to capture the object relations, attribute-object bindings, and word order dependencies. This limitation arises not only from the reliance on global, single-vector representations for optimization, but also from the insufficient exploitation and modeling of the rich compositional information inherently present in paired image text data. In this work, we propose MACCO (MAsked Compositional Concept MOdeling), a framework that masks compositional concepts in one modality and reconstructs them conditioned on the full contextual information from the other, enabling the model to capture and align cross-modal compositional structures more effectively. To facilitate this process, we introduce two auxi","title":"Cross-Modal Masked Compositional Concept Modeling for Enhancing Visio-Linguistic Compositionality","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-12T04:43:44Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.13288"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:37f4334c9362ebeb1f0a3715f32d55582cebce55b90cc67e4c45670c51079c1141a549f7be13dcbe17d42b095c64d0c99b1c6a2b794ceade3ab6ee395feea008","signer":"crovia.substrate","subject":{"observed_at":"2026-06-12T04:43:44Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.13288"},"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":"56946aae13aad70dfc86c06fbbd85c58cce4ab71acf44615decb0a3837f44671","leaf_index":229772,"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":"151a1624656a0c6257ed7432f4f37e1048bb0ec6a39e3a845afe0a3f92b88398","side":"right"},{"sibling":"3774358ec2dcd3f667125f66818f4d56f338a8559d6599f2584926d39b883727","side":"right"},{"sibling":"afea6bb862706aa3c829a460413cb04f7ab73cfe6162ba45f56989131c7b5e8e","side":"left"},{"sibling":"27a6833d28cf1cc76c81ab35e2f68c529d432aca49c6e6dc6f2a8d27d54b27dc","side":"left"},{"sibling":"45a32b7aef6152d34dcb5759a3d2c12cdd6b2bc2b476b845db396597a6626cb3","side":"right"},{"sibling":"f980b09d747f400406442a2d8e6636d297423fefcfc4f6dd933ef6f37a1d3e0c","side":"right"},{"sibling":"f8bab1c4b4d78ecdc0c7c24f3f0491d32c6f49b960c42926df1ece7da77ecd89","side":"right"},{"sibling":"ae0aa292f48289283e26aa363532f22206cc7cea51771c75c6c011c898bec69c","side":"left"},{"sibling":"99d288e6cd43a807fba958865176bb1c08b82471afe942f6e4989eaeeb7275aa","side":"left"},{"sibling":"d385017d38a86f6abc492026a7cd60ceb3b3ff2486142dc49e5acb179f4b7d11","side":"right"},{"sibling":"bde25d7e94e64717e426a97f6fcb4907e92b5c61fc89d92d7e0947a2249c3f6b","side":"right"},{"sibling":"d10d772a4984cae00e65ab24af21d1d260e475bbaae3f17871859eb705bd3999","side":"right"},{"sibling":"e79159853f2f35ddae8e3247d515e433c534277b287d65bbd77ae989aa4992fa","side":"right"},{"sibling":"3054319f1840cce0eaaf0bc4b1ae38e5bf8b6210927d924a750775cc7d77cca6","side":"right"},{"sibling":"0fd8b5059f279c4a4a6688de2472fdbc25543fee183df19b21dacca880354cff","side":"right"},{"sibling":"a04392fb9f2a3a620840e3b3fecd93d12e6d224e481c162389d8ae64e7194599","side":"left"},{"sibling":"c300cf0154c136afc09b1702a0be98f4ba5b6dc5cf57e8cc714ec1eaf4196eff","side":"left"},{"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":232015,"merkle_root":"62bfb7809bb55667ad7eeebdb48267b9b2c1ee89bb808ea1e6d3a814a15aa402","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260617T133701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-17T13:39:59Z","sig_algorithm":"ed25519","signature":"930a3563c643cc7518d048b12a1f5392a96a5edce49533ba0a56f11b6cc69319bb1c800aacc46b52a6941c4d05dae255a45cac757d6093c971b96852c24f140e","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_b287be2f10518180edd891904d45d455da1290c2c7f19a6df09f9b5d9fa15bbc"}}