{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZU4JTVZ3VHXFA2QEDPRVE7F3KQ","short_pith_number":"pith:ZU4JTVZ3","canonical_record":{"source":{"id":"2308.10509","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-21T06:50:29Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"1bad85c909bbe8a785cd7486437128ebc47a76ad5f692831479c57405f738d9f","abstract_canon_sha256":"565c9335a8ec8c8dcf7ef71d9f665398ebcf7e4643d5a20fe9d120a63126f917"},"schema_version":"1.0"},"canonical_sha256":"cd3899d73ba9ee506a041be3527cbb543a023ed4d5641421528a3ef0901b0bd6","source":{"kind":"arxiv","id":"2308.10509","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.10509","created_at":"2026-07-05T08:02:21Z"},{"alias_kind":"arxiv_version","alias_value":"2308.10509v2","created_at":"2026-07-05T08:02:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10509","created_at":"2026-07-05T08:02:21Z"},{"alias_kind":"pith_short_12","alias_value":"ZU4JTVZ3VHXF","created_at":"2026-07-05T08:02:21Z"},{"alias_kind":"pith_short_16","alias_value":"ZU4JTVZ3VHXFA2QE","created_at":"2026-07-05T08:02:21Z"},{"alias_kind":"pith_short_8","alias_value":"ZU4JTVZ3","created_at":"2026-07-05T08:02:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZU4JTVZ3VHXFA2QEDPRVE7F3KQ","target":"record","payload":{"canonical_record":{"source":{"id":"2308.10509","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-21T06:50:29Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"1bad85c909bbe8a785cd7486437128ebc47a76ad5f692831479c57405f738d9f","abstract_canon_sha256":"565c9335a8ec8c8dcf7ef71d9f665398ebcf7e4643d5a20fe9d120a63126f917"},"schema_version":"1.0"},"canonical_sha256":"cd3899d73ba9ee506a041be3527cbb543a023ed4d5641421528a3ef0901b0bd6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:21.108918Z","signature_b64":"3l+DKvGttCHNJfxhi0Tm6TyzAALYaexhJ6h4RxOQW1WI5d6IzTkt6zqvj7EVdXmCnG/5+UhTyloQ4xKhnEQbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd3899d73ba9ee506a041be3527cbb543a023ed4d5641421528a3ef0901b0bd6","last_reissued_at":"2026-07-05T08:02:21.108423Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:21.108423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.10509","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":"2026-07-05T08:02:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EU1kQeON6+qm7tHQJzMgxgYsTHL7VOJnUZuPBo2KxpY4gL54Gwv8sh4Uw8JSpmkUiQbb9B0U7Bnd9ZfNdtqiDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:46:35.476330Z"},"content_sha256":"7a14f5384dd1742575632492d1759a0554151f18323ae0dc23673b19bdb8bb06","schema_version":"1.0","event_id":"sha256:7a14f5384dd1742575632492d1759a0554151f18323ae0dc23673b19bdb8bb06"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZU4JTVZ3VHXFA2QEDPRVE7F3KQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Examination of the Compositionality of Large Generative Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Junwei Liang, Rong Li, Teli Ma","submitted_at":"2023-08-21T06:50:29Z","abstract_excerpt":"With the success of Large Language Models (LLMs), many Generative Vision-Language Models (GVLMs) have been constructed via multimodal instruction tuning. However, the performance of GVLMs in multimodal compositional reasoning remains under-explored. In this paper, we examine both the evaluation metrics (VisualGPTScore, etc.) and current benchmarks for evaluating the compositionality of GVLMs. We identify the syntactical bias in current benchmarks, which is exploited by the linguistic capability of GVLMs. The bias renders VisualGPTScore an insufficient metric for assessing GVLMs. To combat this"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10509","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/2308.10509/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":"2026-07-05T08:02:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mE9RLeYTwWxlHpFiEafV3FZCNL1RrEfT5IQpHCf/W7ThuQVGKC/cWp0glDDY12bOtDZrOrcVFqqDQ+ZC7cJcAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:46:35.476839Z"},"content_sha256":"42c76d785662876eecbc42fe4c41dbf4284c0d97ea24eda8c595efcd6886374d","schema_version":"1.0","event_id":"sha256:42c76d785662876eecbc42fe4c41dbf4284c0d97ea24eda8c595efcd6886374d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZU4JTVZ3VHXFA2QEDPRVE7F3KQ/bundle.json","state_url":"https://pith.science/pith/ZU4JTVZ3VHXFA2QEDPRVE7F3KQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZU4JTVZ3VHXFA2QEDPRVE7F3KQ/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":"2026-08-04T07:46:35Z","links":{"resolver":"https://pith.science/pith/ZU4JTVZ3VHXFA2QEDPRVE7F3KQ","bundle":"https://pith.science/pith/ZU4JTVZ3VHXFA2QEDPRVE7F3KQ/bundle.json","state":"https://pith.science/pith/ZU4JTVZ3VHXFA2QEDPRVE7F3KQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZU4JTVZ3VHXFA2QEDPRVE7F3KQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZU4JTVZ3VHXFA2QEDPRVE7F3KQ","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":"565c9335a8ec8c8dcf7ef71d9f665398ebcf7e4643d5a20fe9d120a63126f917","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-21T06:50:29Z","title_canon_sha256":"1bad85c909bbe8a785cd7486437128ebc47a76ad5f692831479c57405f738d9f"},"schema_version":"1.0","source":{"id":"2308.10509","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.10509","created_at":"2026-07-05T08:02:21Z"},{"alias_kind":"arxiv_version","alias_value":"2308.10509v2","created_at":"2026-07-05T08:02:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10509","created_at":"2026-07-05T08:02:21Z"},{"alias_kind":"pith_short_12","alias_value":"ZU4JTVZ3VHXF","created_at":"2026-07-05T08:02:21Z"},{"alias_kind":"pith_short_16","alias_value":"ZU4JTVZ3VHXFA2QE","created_at":"2026-07-05T08:02:21Z"},{"alias_kind":"pith_short_8","alias_value":"ZU4JTVZ3","created_at":"2026-07-05T08:02:21Z"}],"graph_snapshots":[{"event_id":"sha256:42c76d785662876eecbc42fe4c41dbf4284c0d97ea24eda8c595efcd6886374d","target":"graph","created_at":"2026-07-05T08:02:21Z","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/2308.10509/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the success of Large Language Models (LLMs), many Generative Vision-Language Models (GVLMs) have been constructed via multimodal instruction tuning. However, the performance of GVLMs in multimodal compositional reasoning remains under-explored. In this paper, we examine both the evaluation metrics (VisualGPTScore, etc.) and current benchmarks for evaluating the compositionality of GVLMs. We identify the syntactical bias in current benchmarks, which is exploited by the linguistic capability of GVLMs. The bias renders VisualGPTScore an insufficient metric for assessing GVLMs. To combat this","authors_text":"Junwei Liang, Rong Li, Teli Ma","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-21T06:50:29Z","title":"An Examination of the Compositionality of Large Generative Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10509","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":"sha256:7a14f5384dd1742575632492d1759a0554151f18323ae0dc23673b19bdb8bb06","target":"record","created_at":"2026-07-05T08:02:21Z","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":"565c9335a8ec8c8dcf7ef71d9f665398ebcf7e4643d5a20fe9d120a63126f917","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-21T06:50:29Z","title_canon_sha256":"1bad85c909bbe8a785cd7486437128ebc47a76ad5f692831479c57405f738d9f"},"schema_version":"1.0","source":{"id":"2308.10509","kind":"arxiv","version":2}},"canonical_sha256":"cd3899d73ba9ee506a041be3527cbb543a023ed4d5641421528a3ef0901b0bd6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd3899d73ba9ee506a041be3527cbb543a023ed4d5641421528a3ef0901b0bd6","first_computed_at":"2026-07-05T08:02:21.108423Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:21.108423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3l+DKvGttCHNJfxhi0Tm6TyzAALYaexhJ6h4RxOQW1WI5d6IzTkt6zqvj7EVdXmCnG/5+UhTyloQ4xKhnEQbCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:21.108918Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.10509","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a14f5384dd1742575632492d1759a0554151f18323ae0dc23673b19bdb8bb06","sha256:42c76d785662876eecbc42fe4c41dbf4284c0d97ea24eda8c595efcd6886374d"],"state_sha256":"23dd09c5b8ead01a92aba2fbd41e8137751048f2f765ba67b1efa220f591ef63"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vTv98TWAT5VI5IGbR9hakI8feVIREcu5SXqgUjZ854Av2uH9EZLWNFzDwDoMYBgSTJ2Wb9AI9nQxa64Iqj8tBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T07:46:35.499434Z","bundle_sha256":"1e0d057330349d59ab68808f5fcbcecec0fe145a8963c1dc53167a725fee07f7"}}