{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WOJPRA7RAQ3STV3HPK5RBTGWLM","short_pith_number":"pith:WOJPRA7R","canonical_record":{"source":{"id":"2606.13288","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T12:45:25Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"3f3668285b91a351955253fa3a77d109df8a92d6f42e9962ec019581e3d001cd","abstract_canon_sha256":"ba46a50445986e2a717b181115189327da2113f14961ada4b490a6b4eb46cf40"},"schema_version":"1.0"},"canonical_sha256":"b392f883f1043729d7677abb10ccd65b17bf0eaac7068864f70996803381ef9c","source":{"kind":"arxiv","id":"2606.13288","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.13288","created_at":"2026-06-12T01:09:50Z"},{"alias_kind":"arxiv_version","alias_value":"2606.13288v1","created_at":"2026-06-12T01:09:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13288","created_at":"2026-06-12T01:09:50Z"},{"alias_kind":"pith_short_12","alias_value":"WOJPRA7RAQ3S","created_at":"2026-06-12T01:09:50Z"},{"alias_kind":"pith_short_16","alias_value":"WOJPRA7RAQ3STV3H","created_at":"2026-06-12T01:09:50Z"},{"alias_kind":"pith_short_8","alias_value":"WOJPRA7R","created_at":"2026-06-12T01:09:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WOJPRA7RAQ3STV3HPK5RBTGWLM","target":"record","payload":{"canonical_record":{"source":{"id":"2606.13288","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T12:45:25Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"3f3668285b91a351955253fa3a77d109df8a92d6f42e9962ec019581e3d001cd","abstract_canon_sha256":"ba46a50445986e2a717b181115189327da2113f14961ada4b490a6b4eb46cf40"},"schema_version":"1.0"},"canonical_sha256":"b392f883f1043729d7677abb10ccd65b17bf0eaac7068864f70996803381ef9c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:50.756976Z","signature_b64":"nNvWS8rFd9QvB4MCrfD1V6F7+fEOHDGin1HDwiU0Ru9lfU6PLWyniaaiM97XSlCfHOlJnHaQ6NCgKSWHf5C6Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b392f883f1043729d7677abb10ccd65b17bf0eaac7068864f70996803381ef9c","last_reissued_at":"2026-06-12T01:09:50.755929Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:50.755929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.13288","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-12T01:09:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F/eziKwiqbqWlcWwcCROQnFLORoZEAhAWqdzKGmRYkw0cuz6Fxpo09Px4YDTAQsmuTaZWenEqd9dBHEVGC+9Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T09:51:02.524449Z"},"content_sha256":"67ee53d64fc0f016c437aeeb31be9079efaf858acb8dae3acb7c94e000792ae3","schema_version":"1.0","event_id":"sha256:67ee53d64fc0f016c437aeeb31be9079efaf858acb8dae3acb7c94e000792ae3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WOJPRA7RAQ3STV3HPK5RBTGWLM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cross-Modal Masked Compositional Concept Modeling for Enhancing Visio-Linguistic Compositionality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Wei Li, Xinmei Tian, Zhen Huang","submitted_at":"2026-06-11T12:45:25Z","abstract_excerpt":"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, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13288","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/2606.13288/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-12T01:09:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1ijaC89y5vwhagPOjLEdPLOaDNU4BvqbU/JMMAGkzZwqiXpjCsxt/16zeOh2xPZZqYf9jPD5jwl119rC0w4AAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T09:51:02.524825Z"},"content_sha256":"d5b21f95aff709ea4a6ed44139c2234814fb94b3928455d61f3c6574df65d61b","schema_version":"1.0","event_id":"sha256:d5b21f95aff709ea4a6ed44139c2234814fb94b3928455d61f3c6574df65d61b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WOJPRA7RAQ3STV3HPK5RBTGWLM/bundle.json","state_url":"https://pith.science/pith/WOJPRA7RAQ3STV3HPK5RBTGWLM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WOJPRA7RAQ3STV3HPK5RBTGWLM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-02T09:51:02Z","links":{"resolver":"https://pith.science/pith/WOJPRA7RAQ3STV3HPK5RBTGWLM","bundle":"https://pith.science/pith/WOJPRA7RAQ3STV3HPK5RBTGWLM/bundle.json","state":"https://pith.science/pith/WOJPRA7RAQ3STV3HPK5RBTGWLM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WOJPRA7RAQ3STV3HPK5RBTGWLM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WOJPRA7RAQ3STV3HPK5RBTGWLM","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":"ba46a50445986e2a717b181115189327da2113f14961ada4b490a6b4eb46cf40","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T12:45:25Z","title_canon_sha256":"3f3668285b91a351955253fa3a77d109df8a92d6f42e9962ec019581e3d001cd"},"schema_version":"1.0","source":{"id":"2606.13288","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.13288","created_at":"2026-06-12T01:09:50Z"},{"alias_kind":"arxiv_version","alias_value":"2606.13288v1","created_at":"2026-06-12T01:09:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13288","created_at":"2026-06-12T01:09:50Z"},{"alias_kind":"pith_short_12","alias_value":"WOJPRA7RAQ3S","created_at":"2026-06-12T01:09:50Z"},{"alias_kind":"pith_short_16","alias_value":"WOJPRA7RAQ3STV3H","created_at":"2026-06-12T01:09:50Z"},{"alias_kind":"pith_short_8","alias_value":"WOJPRA7R","created_at":"2026-06-12T01:09:50Z"}],"graph_snapshots":[{"event_id":"sha256:d5b21f95aff709ea4a6ed44139c2234814fb94b3928455d61f3c6574df65d61b","target":"graph","created_at":"2026-06-12T01:09:50Z","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/2606.13288/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"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, ","authors_text":"Wei Li, Xinmei Tian, Zhen Huang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T12:45:25Z","title":"Cross-Modal Masked Compositional Concept Modeling for Enhancing Visio-Linguistic Compositionality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13288","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":"sha256:67ee53d64fc0f016c437aeeb31be9079efaf858acb8dae3acb7c94e000792ae3","target":"record","created_at":"2026-06-12T01:09:50Z","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":"ba46a50445986e2a717b181115189327da2113f14961ada4b490a6b4eb46cf40","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T12:45:25Z","title_canon_sha256":"3f3668285b91a351955253fa3a77d109df8a92d6f42e9962ec019581e3d001cd"},"schema_version":"1.0","source":{"id":"2606.13288","kind":"arxiv","version":1}},"canonical_sha256":"b392f883f1043729d7677abb10ccd65b17bf0eaac7068864f70996803381ef9c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b392f883f1043729d7677abb10ccd65b17bf0eaac7068864f70996803381ef9c","first_computed_at":"2026-06-12T01:09:50.755929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:09:50.755929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nNvWS8rFd9QvB4MCrfD1V6F7+fEOHDGin1HDwiU0Ru9lfU6PLWyniaaiM97XSlCfHOlJnHaQ6NCgKSWHf5C6Bw==","signature_status":"signed_v1","signed_at":"2026-06-12T01:09:50.756976Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.13288","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67ee53d64fc0f016c437aeeb31be9079efaf858acb8dae3acb7c94e000792ae3","sha256:d5b21f95aff709ea4a6ed44139c2234814fb94b3928455d61f3c6574df65d61b"],"state_sha256":"26479bdcdcec61617cd828bff65bbd07394e8ed238dbdc1af54245874084438f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cskdlWdNJpZhPKxaFrY3g7WrbevPE3xw+xLuaZyzqw+cWGlYuluzP2vVvdRTprVsKS8ZrKX6sX6EvbK0HqSvCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T09:51:02.527043Z","bundle_sha256":"0d94ba0d32086e434bd55c9cfc5e1106c34d848e742b12ed52521f9af1daf183"}}