{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XRQ3225LOLU7FHZWL3522Q3NUI","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":"9e7fa31391af33722632c75ec82fda712ac6ea2b7e7ccced042d5b2d4be7b9e5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-28T13:45:04Z","title_canon_sha256":"8206cb50bf2c8664ca6c6cdc380bfec655441ae3b42390f1ee97ef1492c59eeb"},"schema_version":"1.0","source":{"id":"2508.20783","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.20783","created_at":"2026-07-05T12:01:10Z"},{"alias_kind":"arxiv_version","alias_value":"2508.20783v1","created_at":"2026-07-05T12:01:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20783","created_at":"2026-07-05T12:01:10Z"},{"alias_kind":"pith_short_12","alias_value":"XRQ3225LOLU7","created_at":"2026-07-05T12:01:10Z"},{"alias_kind":"pith_short_16","alias_value":"XRQ3225LOLU7FHZW","created_at":"2026-07-05T12:01:10Z"},{"alias_kind":"pith_short_8","alias_value":"XRQ3225L","created_at":"2026-07-05T12:01:10Z"}],"graph_snapshots":[{"event_id":"sha256:f3135565b6be984b3d621cee9b058c036a9cb422892808b3a46e713abb68f8f6","target":"graph","created_at":"2026-07-05T12:01:10Z","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/2508.20783/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A fundamental aspect of the semantics of natural language is that novel meanings can be formed from the composition of previously known parts. Vision-language models (VLMs) have made significant progress in recent years, however, there is evidence that they are unable to perform this kind of composition. For example, given an image of a red cube and a blue cylinder, a VLM such as CLIP is likely to incorrectly label the image as a red cylinder or a blue cube, indicating it represents the image as a `bag-of-words' and fails to capture compositional semantics. Diffusion models have recently gaine","authors_text":"Beth Pearson, Bilal Boulbarss, Martha Lewis, Michael Wray","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-28T13:45:04Z","title":"Evaluating Compositional Generalisation in VLMs and Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20783","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:d4504f70e2e2c2977c0477dad47474deb705eb0d34c27bb1cf694fbd280b81a7","target":"record","created_at":"2026-07-05T12:01:10Z","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":"9e7fa31391af33722632c75ec82fda712ac6ea2b7e7ccced042d5b2d4be7b9e5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-28T13:45:04Z","title_canon_sha256":"8206cb50bf2c8664ca6c6cdc380bfec655441ae3b42390f1ee97ef1492c59eeb"},"schema_version":"1.0","source":{"id":"2508.20783","kind":"arxiv","version":1}},"canonical_sha256":"bc61bd6bab72e9f29f365efbad436da22b523f00739b4c740978cad6048082c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc61bd6bab72e9f29f365efbad436da22b523f00739b4c740978cad6048082c3","first_computed_at":"2026-07-05T12:01:10.782293Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:10.782293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JGiUYlL84Q5DpXohAY0sdIb/osHilCKVj69qo+qpgoH8s365kSciSvmVr6VBMfVp5CD8m2lQ0uStuCxjU8+0Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:10.782837Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.20783","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4504f70e2e2c2977c0477dad47474deb705eb0d34c27bb1cf694fbd280b81a7","sha256:f3135565b6be984b3d621cee9b058c036a9cb422892808b3a46e713abb68f8f6"],"state_sha256":"23242548ed4ef8ec8771beae7dd27cdc1a5af262af4e4a2537a8dd3c4220c890"}