{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XVP7XFJLARJDJNPNUPFNDTK2YY","short_pith_number":"pith:XVP7XFJL","canonical_record":{"source":{"id":"2308.03151","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-06T15:56:31Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"dec12837e8a5e0f6c7bc0d3150579cbf86ed8c45a611f204f88e02801e774f48","abstract_canon_sha256":"81fd6cbc3e2bda6dd149945e0af51d760b9030e622450a7108a9b92bedf72e02"},"schema_version":"1.0"},"canonical_sha256":"bd5ffb952b045234b5eda3cad1cd5ac63f181d160f5bd3e4cddea969c262141d","source":{"kind":"arxiv","id":"2308.03151","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.03151","created_at":"2026-07-05T06:38:12Z"},{"alias_kind":"arxiv_version","alias_value":"2308.03151v1","created_at":"2026-07-05T06:38:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.03151","created_at":"2026-07-05T06:38:12Z"},{"alias_kind":"pith_short_12","alias_value":"XVP7XFJLARJD","created_at":"2026-07-05T06:38:12Z"},{"alias_kind":"pith_short_16","alias_value":"XVP7XFJLARJDJNPN","created_at":"2026-07-05T06:38:12Z"},{"alias_kind":"pith_short_8","alias_value":"XVP7XFJL","created_at":"2026-07-05T06:38:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XVP7XFJLARJDJNPNUPFNDTK2YY","target":"record","payload":{"canonical_record":{"source":{"id":"2308.03151","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-06T15:56:31Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"dec12837e8a5e0f6c7bc0d3150579cbf86ed8c45a611f204f88e02801e774f48","abstract_canon_sha256":"81fd6cbc3e2bda6dd149945e0af51d760b9030e622450a7108a9b92bedf72e02"},"schema_version":"1.0"},"canonical_sha256":"bd5ffb952b045234b5eda3cad1cd5ac63f181d160f5bd3e4cddea969c262141d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:38:12.787941Z","signature_b64":"utGShGZr5HYsyLFrWR1ugOurLZBFv77ryXo2mUCGMwusTIJwpB2imrGtqKU3yBA3SxDRIqBeFBOjL296hxRDAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd5ffb952b045234b5eda3cad1cd5ac63f181d160f5bd3e4cddea969c262141d","last_reissued_at":"2026-07-05T06:38:12.787353Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:38:12.787353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.03151","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":"2026-07-05T06:38:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/dUn3NoUPPvH6OTukZwfJARndC5OQApfjLKis86NnsOq3E4HTkjjWNShoW1V2jG+xcCCbfV9XSO8joy/BsNKBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:18:50.778091Z"},"content_sha256":"f240104cfeb168d2c28e52e33e650d67c4b987a0e5f94e589f6ae7150a8507c3","schema_version":"1.0","event_id":"sha256:f240104cfeb168d2c28e52e33e650d67c4b987a0e5f94e589f6ae7150a8507c3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XVP7XFJLARJDJNPNUPFNDTK2YY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Food-500 Cap: A Fine-Grained Food Caption Benchmark for Evaluating Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Jiajun Chen, Jianbing Zhang, Kanzhi Cheng, Mianzhi Pan, Shujian Huang, Wenhan Wu, Zheng Ma","submitted_at":"2023-08-06T15:56:31Z","abstract_excerpt":"Vision-language models (VLMs) have shown impressive performance in substantial downstream multi-modal tasks. However, only comparing the fine-tuned performance on downstream tasks leads to the poor interpretability of VLMs, which is adverse to their future improvement. Several prior works have identified this issue and used various probing methods under a zero-shot setting to detect VLMs' limitations, but they all examine VLMs using general datasets instead of specialized ones. In practical applications, VLMs are usually applied to specific scenarios, such as e-commerce and news fields, so the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.03151","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/2308.03151/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":"2026-07-05T06:38:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3xMVAHlCMr2tHeT6D/+7PWgczLwrkPLIUAOJubbX5CDYyGsa6iIx97uGy5hSdw05DqWqbP4c9kDk1uu4aUCdDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:18:50.778589Z"},"content_sha256":"93d17eb6a539d4da14dc868975d1df1c57ed55d09877edfc079e7d36139fb465","schema_version":"1.0","event_id":"sha256:93d17eb6a539d4da14dc868975d1df1c57ed55d09877edfc079e7d36139fb465"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XVP7XFJLARJDJNPNUPFNDTK2YY/bundle.json","state_url":"https://pith.science/pith/XVP7XFJLARJDJNPNUPFNDTK2YY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XVP7XFJLARJDJNPNUPFNDTK2YY/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":"2026-08-05T17:18:50Z","links":{"resolver":"https://pith.science/pith/XVP7XFJLARJDJNPNUPFNDTK2YY","bundle":"https://pith.science/pith/XVP7XFJLARJDJNPNUPFNDTK2YY/bundle.json","state":"https://pith.science/pith/XVP7XFJLARJDJNPNUPFNDTK2YY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XVP7XFJLARJDJNPNUPFNDTK2YY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XVP7XFJLARJDJNPNUPFNDTK2YY","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":"81fd6cbc3e2bda6dd149945e0af51d760b9030e622450a7108a9b92bedf72e02","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-06T15:56:31Z","title_canon_sha256":"dec12837e8a5e0f6c7bc0d3150579cbf86ed8c45a611f204f88e02801e774f48"},"schema_version":"1.0","source":{"id":"2308.03151","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.03151","created_at":"2026-07-05T06:38:12Z"},{"alias_kind":"arxiv_version","alias_value":"2308.03151v1","created_at":"2026-07-05T06:38:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.03151","created_at":"2026-07-05T06:38:12Z"},{"alias_kind":"pith_short_12","alias_value":"XVP7XFJLARJD","created_at":"2026-07-05T06:38:12Z"},{"alias_kind":"pith_short_16","alias_value":"XVP7XFJLARJDJNPN","created_at":"2026-07-05T06:38:12Z"},{"alias_kind":"pith_short_8","alias_value":"XVP7XFJL","created_at":"2026-07-05T06:38:12Z"}],"graph_snapshots":[{"event_id":"sha256:93d17eb6a539d4da14dc868975d1df1c57ed55d09877edfc079e7d36139fb465","target":"graph","created_at":"2026-07-05T06:38:12Z","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/2308.03151/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) have shown impressive performance in substantial downstream multi-modal tasks. However, only comparing the fine-tuned performance on downstream tasks leads to the poor interpretability of VLMs, which is adverse to their future improvement. Several prior works have identified this issue and used various probing methods under a zero-shot setting to detect VLMs' limitations, but they all examine VLMs using general datasets instead of specialized ones. In practical applications, VLMs are usually applied to specific scenarios, such as e-commerce and news fields, so the","authors_text":"Jiajun Chen, Jianbing Zhang, Kanzhi Cheng, Mianzhi Pan, Shujian Huang, Wenhan Wu, Zheng Ma","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-06T15:56:31Z","title":"Food-500 Cap: A Fine-Grained Food Caption Benchmark for Evaluating Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.03151","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:f240104cfeb168d2c28e52e33e650d67c4b987a0e5f94e589f6ae7150a8507c3","target":"record","created_at":"2026-07-05T06:38:12Z","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":"81fd6cbc3e2bda6dd149945e0af51d760b9030e622450a7108a9b92bedf72e02","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-06T15:56:31Z","title_canon_sha256":"dec12837e8a5e0f6c7bc0d3150579cbf86ed8c45a611f204f88e02801e774f48"},"schema_version":"1.0","source":{"id":"2308.03151","kind":"arxiv","version":1}},"canonical_sha256":"bd5ffb952b045234b5eda3cad1cd5ac63f181d160f5bd3e4cddea969c262141d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd5ffb952b045234b5eda3cad1cd5ac63f181d160f5bd3e4cddea969c262141d","first_computed_at":"2026-07-05T06:38:12.787353Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:38:12.787353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"utGShGZr5HYsyLFrWR1ugOurLZBFv77ryXo2mUCGMwusTIJwpB2imrGtqKU3yBA3SxDRIqBeFBOjL296hxRDAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:38:12.787941Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.03151","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f240104cfeb168d2c28e52e33e650d67c4b987a0e5f94e589f6ae7150a8507c3","sha256:93d17eb6a539d4da14dc868975d1df1c57ed55d09877edfc079e7d36139fb465"],"state_sha256":"35480e7759b3dff09217df4f17302911bec091d725fed1010c531a626869a6d5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q+ue2hf+2Y4YZ4TYuHgJAnZbePYMIhyVTaFd9W3tsWwgWSKxubiNypf2+5ZtBUGv6Azh/ePSd9K92bx5ZJuBAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T17:18:50.782333Z","bundle_sha256":"bc566fbe62240b33ad0f9af769fa24b96db81cb6eb86546f456518cc923759e0"}}