{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LIQOHEGO5GT3R3F2WZJ2DY65EU","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":"95b36f0e169ad8e0f674a4520d6cb14550795ae2d468b1e87dd421779249db34","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-07T13:05:47Z","title_canon_sha256":"6da1af74bb26f6c4c2d2e664ab806b9e6ebf8c966fbd0a4b5b88f9eaff87207e"},"schema_version":"1.0","source":{"id":"2311.03964","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.03964","created_at":"2026-07-05T07:10:08Z"},{"alias_kind":"arxiv_version","alias_value":"2311.03964v1","created_at":"2026-07-05T07:10:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.03964","created_at":"2026-07-05T07:10:08Z"},{"alias_kind":"pith_short_12","alias_value":"LIQOHEGO5GT3","created_at":"2026-07-05T07:10:08Z"},{"alias_kind":"pith_short_16","alias_value":"LIQOHEGO5GT3R3F2","created_at":"2026-07-05T07:10:08Z"},{"alias_kind":"pith_short_8","alias_value":"LIQOHEGO","created_at":"2026-07-05T07:10:08Z"}],"graph_snapshots":[{"event_id":"sha256:6052de55644c50aaf517ce8cee1fc939974e2fff046d2d655a0293ab9f42b345","target":"graph","created_at":"2026-07-05T07:10:08Z","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/2311.03964/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contemporary large-scale visual language models (VLMs) exhibit strong representation capacities, making them ubiquitous for enhancing image and text understanding tasks. They are often trained in a contrastive manner on a large and diverse corpus of images and corresponding text captions scraped from the internet. Despite this, VLMs often struggle with compositional reasoning tasks which require a fine-grained understanding of the complex interactions of objects and their attributes. This failure can be attributed to two main factors: 1) Contrastive approaches have traditionally focused on min","authors_text":"Daniel Cremers, Hang Li, Qadeer Khan, Ugur Sahin, Volker Tresp","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-07T13:05:47Z","title":"Enhancing Multimodal Compositional Reasoning of Visual Language Models with Generative Negative Mining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.03964","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":"sha256:1ca397d9048285951bba8a9543ad3e07a2057536135b8413f0e418202a5f03b4","target":"record","created_at":"2026-07-05T07:10:08Z","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":"95b36f0e169ad8e0f674a4520d6cb14550795ae2d468b1e87dd421779249db34","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-07T13:05:47Z","title_canon_sha256":"6da1af74bb26f6c4c2d2e664ab806b9e6ebf8c966fbd0a4b5b88f9eaff87207e"},"schema_version":"1.0","source":{"id":"2311.03964","kind":"arxiv","version":1}},"canonical_sha256":"5a20e390cee9a7b8ecbab653a1e3dd250ba8e29602f2a8028f812682ef793e48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a20e390cee9a7b8ecbab653a1e3dd250ba8e29602f2a8028f812682ef793e48","first_computed_at":"2026-07-05T07:10:08.822613Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:10:08.822613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MVJnIkvmjbQJpftedqPAuxNLobe6xevujBbU6g2z+u5y3sbjl4/KZ4NSG6Ij1d0AuES/z5ZsANrGDt9z6Ar4Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:10:08.823032Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.03964","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ca397d9048285951bba8a9543ad3e07a2057536135b8413f0e418202a5f03b4","sha256:6052de55644c50aaf517ce8cee1fc939974e2fff046d2d655a0293ab9f42b345"],"state_sha256":"1a9f6c1aae5eaa8ec760cb9063ea9f943a9b7b4bec4667e878462a01db83b2de"}