{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:US64ORCLZ56RGEIN3NJ64WRVX2","short_pith_number":"pith:US64ORCL","canonical_record":{"source":{"id":"2412.09353","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T15:22:03Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"title_canon_sha256":"e9066ef10231c2e8e4ae0b1409eb95a8801cc2678deb23b50c594ba2af914141","abstract_canon_sha256":"093ba0e7cdfad5f213f25219f3913347d6b61bc41e0f75afe2d1315153c29232"},"schema_version":"1.0"},"canonical_sha256":"a4bdc7444bcf7d13110ddb53ee5a35be92223bcb013a663e1f3c570b9333ed30","source":{"kind":"arxiv","id":"2412.09353","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09353","created_at":"2026-07-05T10:49:11Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09353v2","created_at":"2026-07-05T10:49:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09353","created_at":"2026-07-05T10:49:11Z"},{"alias_kind":"pith_short_12","alias_value":"US64ORCLZ56R","created_at":"2026-07-05T10:49:11Z"},{"alias_kind":"pith_short_16","alias_value":"US64ORCLZ56RGEIN","created_at":"2026-07-05T10:49:11Z"},{"alias_kind":"pith_short_8","alias_value":"US64ORCL","created_at":"2026-07-05T10:49:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:US64ORCLZ56RGEIN3NJ64WRVX2","target":"record","payload":{"canonical_record":{"source":{"id":"2412.09353","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T15:22:03Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"title_canon_sha256":"e9066ef10231c2e8e4ae0b1409eb95a8801cc2678deb23b50c594ba2af914141","abstract_canon_sha256":"093ba0e7cdfad5f213f25219f3913347d6b61bc41e0f75afe2d1315153c29232"},"schema_version":"1.0"},"canonical_sha256":"a4bdc7444bcf7d13110ddb53ee5a35be92223bcb013a663e1f3c570b9333ed30","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:11.932461Z","signature_b64":"fLc2lCsvXLBxUjv3IkFKIqg+k6QcHM7VyKL2dettudoPc0AHNQ6KgSBGREEblNK1Mgt8kAXuqh9ED0bCAet1BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4bdc7444bcf7d13110ddb53ee5a35be92223bcb013a663e1f3c570b9333ed30","last_reissued_at":"2026-07-05T10:49:11.931978Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:11.931978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.09353","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:49:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Zftk3pRlKA3NrMH+hKl6s89EiQnVmmyAqDVAmkLMpCxuoTwPO1K1O+G9WFbaHt7CW2iFiu6f75zSHicB9hNDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:58:48.226165Z"},"content_sha256":"8f4409bfc0ba5aaa7ceacf0ff5dfdc2ad16214a324895778a37990f0adff3d14","schema_version":"1.0","event_id":"sha256:8f4409bfc0ba5aaa7ceacf0ff5dfdc2ad16214a324895778a37990f0adff3d14"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:US64ORCLZ56RGEIN3NJ64WRVX2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Causal Graphical Models for Vision-Language Compositional Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Enver Sangineto, Fiorenzo Parascandolo, Lorenzo Baraldi, Nicholas Moratelli, Rita Cucchiara","submitted_at":"2024-12-12T15:22:03Z","abstract_excerpt":"Recent work has empirically shown that Vision-Language Models (VLMs) struggle to fully understand the compositional properties of the human language, usually modeling an image caption as a \"bag of words\". As a result, they perform poorly on compositional tasks, which require a deeper understanding of the different entities of a sentence (subject, verb, etc.) jointly with their mutual relationships in order to be solved. In this paper, we model the dependency relations among textual and visual tokens using a Causal Graphical Model (CGM), built using a dependency parser, and we train a decoder c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09353","kind":"arxiv","version":2},"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/2412.09353/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":"2026-07-05T10:49:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AYCoZbZuNaYOUhn03dt+2M/kcPau6PMupoMinTL3jmKp+GWaMdwWlhJNQ/CGoRCKiwISoaScEpBoKrrVM2VWDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:58:48.226680Z"},"content_sha256":"fb1fbf05ed7304350274eda6a45231136d3e5494ce1208a4f6982abc97c74363","schema_version":"1.0","event_id":"sha256:fb1fbf05ed7304350274eda6a45231136d3e5494ce1208a4f6982abc97c74363"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/US64ORCLZ56RGEIN3NJ64WRVX2/bundle.json","state_url":"https://pith.science/pith/US64ORCLZ56RGEIN3NJ64WRVX2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/US64ORCLZ56RGEIN3NJ64WRVX2/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":"2026-08-04T20:58:48Z","links":{"resolver":"https://pith.science/pith/US64ORCLZ56RGEIN3NJ64WRVX2","bundle":"https://pith.science/pith/US64ORCLZ56RGEIN3NJ64WRVX2/bundle.json","state":"https://pith.science/pith/US64ORCLZ56RGEIN3NJ64WRVX2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/US64ORCLZ56RGEIN3NJ64WRVX2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:US64ORCLZ56RGEIN3NJ64WRVX2","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":"093ba0e7cdfad5f213f25219f3913347d6b61bc41e0f75afe2d1315153c29232","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T15:22:03Z","title_canon_sha256":"e9066ef10231c2e8e4ae0b1409eb95a8801cc2678deb23b50c594ba2af914141"},"schema_version":"1.0","source":{"id":"2412.09353","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09353","created_at":"2026-07-05T10:49:11Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09353v2","created_at":"2026-07-05T10:49:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09353","created_at":"2026-07-05T10:49:11Z"},{"alias_kind":"pith_short_12","alias_value":"US64ORCLZ56R","created_at":"2026-07-05T10:49:11Z"},{"alias_kind":"pith_short_16","alias_value":"US64ORCLZ56RGEIN","created_at":"2026-07-05T10:49:11Z"},{"alias_kind":"pith_short_8","alias_value":"US64ORCL","created_at":"2026-07-05T10:49:11Z"}],"graph_snapshots":[{"event_id":"sha256:fb1fbf05ed7304350274eda6a45231136d3e5494ce1208a4f6982abc97c74363","target":"graph","created_at":"2026-07-05T10:49:11Z","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/2412.09353/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work has empirically shown that Vision-Language Models (VLMs) struggle to fully understand the compositional properties of the human language, usually modeling an image caption as a \"bag of words\". As a result, they perform poorly on compositional tasks, which require a deeper understanding of the different entities of a sentence (subject, verb, etc.) jointly with their mutual relationships in order to be solved. In this paper, we model the dependency relations among textual and visual tokens using a Causal Graphical Model (CGM), built using a dependency parser, and we train a decoder c","authors_text":"Enver Sangineto, Fiorenzo Parascandolo, Lorenzo Baraldi, Nicholas Moratelli, Rita Cucchiara","cross_cats":["cs.AI","cs.CL","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T15:22:03Z","title":"Causal Graphical Models for Vision-Language Compositional Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09353","kind":"arxiv","version":2},"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":"sha256:8f4409bfc0ba5aaa7ceacf0ff5dfdc2ad16214a324895778a37990f0adff3d14","target":"record","created_at":"2026-07-05T10:49:11Z","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":"093ba0e7cdfad5f213f25219f3913347d6b61bc41e0f75afe2d1315153c29232","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T15:22:03Z","title_canon_sha256":"e9066ef10231c2e8e4ae0b1409eb95a8801cc2678deb23b50c594ba2af914141"},"schema_version":"1.0","source":{"id":"2412.09353","kind":"arxiv","version":2}},"canonical_sha256":"a4bdc7444bcf7d13110ddb53ee5a35be92223bcb013a663e1f3c570b9333ed30","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a4bdc7444bcf7d13110ddb53ee5a35be92223bcb013a663e1f3c570b9333ed30","first_computed_at":"2026-07-05T10:49:11.931978Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:49:11.931978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fLc2lCsvXLBxUjv3IkFKIqg+k6QcHM7VyKL2dettudoPc0AHNQ6KgSBGREEblNK1Mgt8kAXuqh9ED0bCAet1BA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:49:11.932461Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.09353","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f4409bfc0ba5aaa7ceacf0ff5dfdc2ad16214a324895778a37990f0adff3d14","sha256:fb1fbf05ed7304350274eda6a45231136d3e5494ce1208a4f6982abc97c74363"],"state_sha256":"be26afbf6475830c782402db9af3a999bcc702333c5cc9d819babba773463392"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OQZFJPOcaI/Lg4RrfY3yqsMMPiO/bVOAQuxcFo2uaPRECiiSzonamrkf64GQIb15EznGHiKDecuVKJIf4hOrBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T20:58:48.230911Z","bundle_sha256":"fbb8e58c2e676df202f6a4acdd296d9a066012bb00a57038fe8c6e9f9d48d76a"}}