{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:2OINEZJI5C6NT7IWLJYDRIHLRH","short_pith_number":"pith:2OINEZJI","canonical_record":{"source":{"id":"2210.09550","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-18T02:55:58Z","cross_cats_sorted":[],"title_canon_sha256":"b069a2dbd94700187de05023bfd8b4ec8dbdb2d2447604f69b0d44a234ae0c56","abstract_canon_sha256":"290e6bc8910aa4de63d227c332e7e14f13ceeb0e96e797587e20f252d917efbb"},"schema_version":"1.0"},"canonical_sha256":"d390d26528e8bcd9fd165a7038a0eb89cb40cdd0e0c67ae90a1ac1bd3ff732fc","source":{"kind":"arxiv","id":"2210.09550","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.09550","created_at":"2026-07-05T05:07:56Z"},{"alias_kind":"arxiv_version","alias_value":"2210.09550v1","created_at":"2026-07-05T05:07:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09550","created_at":"2026-07-05T05:07:56Z"},{"alias_kind":"pith_short_12","alias_value":"2OINEZJI5C6N","created_at":"2026-07-05T05:07:56Z"},{"alias_kind":"pith_short_16","alias_value":"2OINEZJI5C6NT7IW","created_at":"2026-07-05T05:07:56Z"},{"alias_kind":"pith_short_8","alias_value":"2OINEZJI","created_at":"2026-07-05T05:07:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:2OINEZJI5C6NT7IWLJYDRIHLRH","target":"record","payload":{"canonical_record":{"source":{"id":"2210.09550","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-18T02:55:58Z","cross_cats_sorted":[],"title_canon_sha256":"b069a2dbd94700187de05023bfd8b4ec8dbdb2d2447604f69b0d44a234ae0c56","abstract_canon_sha256":"290e6bc8910aa4de63d227c332e7e14f13ceeb0e96e797587e20f252d917efbb"},"schema_version":"1.0"},"canonical_sha256":"d390d26528e8bcd9fd165a7038a0eb89cb40cdd0e0c67ae90a1ac1bd3ff732fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:07:56.842544Z","signature_b64":"mArs7ydQOMSj3giGjw67LTPyPZGtQ6nXQ9/PLu/OU7kWGMBiCsHFLMUaNuqSKsmPZ32UaPGHrHO9Y1ttllYiCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d390d26528e8bcd9fd165a7038a0eb89cb40cdd0e0c67ae90a1ac1bd3ff732fc","last_reissued_at":"2026-07-05T05:07:56.842082Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:07:56.842082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.09550","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":"2026-07-05T05:07:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZbV4S2IwXf3ntPXKx2b77b0XM99uB+NByGSbLY+fLiRBKXmdYR2nTXCfRq3Y0ukot6WuUuE8pmkV1uxk3ggwBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T17:18:28.546374Z"},"content_sha256":"402c23ed07ce09584ef56906a0203f2a007b0fc80a9b2e3f12672fc12d6c2a40","schema_version":"1.0","event_id":"sha256:402c23ed07ce09584ef56906a0203f2a007b0fc80a9b2e3f12672fc12d6c2a40"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:2OINEZJI5C6NT7IWLJYDRIHLRH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Probing Cross-modal Semantics Alignment Capability from the Textual Perspective","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiajun Chen, Jianbing Zhang, Mianzhi Pan, Shi Zong, Shujian Huang, Xinyu Dai, Zheng Ma","submitted_at":"2022-10-18T02:55:58Z","abstract_excerpt":"In recent years, vision and language pre-training (VLP) models have advanced the state-of-the-art results in a variety of cross-modal downstream tasks. Aligning cross-modal semantics is claimed to be one of the essential capabilities of VLP models. However, it still remains unclear about the inner working mechanism of alignment in VLP models. In this paper, we propose a new probing method that is based on image captioning to first empirically study the cross-modal semantics alignment of VLP models. Our probing method is built upon the fact that given an image-caption pair, the VLP models will "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09550","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/2210.09550/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":"2026-07-05T05:07:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ybv+aL9zknkRHI+msLP8xd5LfUu2btkNMGvKCbQ5edv3/NxLpxP/L1PKtaTWNtLhfr79UPbRH28/+5jpXtk3Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T17:18:28.547289Z"},"content_sha256":"7d1d626426efd4508b2a09701ecc794fe4e591d689f3e0c2f1d871093aa3bebf","schema_version":"1.0","event_id":"sha256:7d1d626426efd4508b2a09701ecc794fe4e591d689f3e0c2f1d871093aa3bebf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2OINEZJI5C6NT7IWLJYDRIHLRH/bundle.json","state_url":"https://pith.science/pith/2OINEZJI5C6NT7IWLJYDRIHLRH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2OINEZJI5C6NT7IWLJYDRIHLRH/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":"2026-08-10T17:18:28Z","links":{"resolver":"https://pith.science/pith/2OINEZJI5C6NT7IWLJYDRIHLRH","bundle":"https://pith.science/pith/2OINEZJI5C6NT7IWLJYDRIHLRH/bundle.json","state":"https://pith.science/pith/2OINEZJI5C6NT7IWLJYDRIHLRH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2OINEZJI5C6NT7IWLJYDRIHLRH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2OINEZJI5C6NT7IWLJYDRIHLRH","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":"290e6bc8910aa4de63d227c332e7e14f13ceeb0e96e797587e20f252d917efbb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-18T02:55:58Z","title_canon_sha256":"b069a2dbd94700187de05023bfd8b4ec8dbdb2d2447604f69b0d44a234ae0c56"},"schema_version":"1.0","source":{"id":"2210.09550","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.09550","created_at":"2026-07-05T05:07:56Z"},{"alias_kind":"arxiv_version","alias_value":"2210.09550v1","created_at":"2026-07-05T05:07:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09550","created_at":"2026-07-05T05:07:56Z"},{"alias_kind":"pith_short_12","alias_value":"2OINEZJI5C6N","created_at":"2026-07-05T05:07:56Z"},{"alias_kind":"pith_short_16","alias_value":"2OINEZJI5C6NT7IW","created_at":"2026-07-05T05:07:56Z"},{"alias_kind":"pith_short_8","alias_value":"2OINEZJI","created_at":"2026-07-05T05:07:56Z"}],"graph_snapshots":[{"event_id":"sha256:7d1d626426efd4508b2a09701ecc794fe4e591d689f3e0c2f1d871093aa3bebf","target":"graph","created_at":"2026-07-05T05:07:56Z","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/2210.09550/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, vision and language pre-training (VLP) models have advanced the state-of-the-art results in a variety of cross-modal downstream tasks. Aligning cross-modal semantics is claimed to be one of the essential capabilities of VLP models. However, it still remains unclear about the inner working mechanism of alignment in VLP models. In this paper, we propose a new probing method that is based on image captioning to first empirically study the cross-modal semantics alignment of VLP models. Our probing method is built upon the fact that given an image-caption pair, the VLP models will ","authors_text":"Jiajun Chen, Jianbing Zhang, Mianzhi Pan, Shi Zong, Shujian Huang, Xinyu Dai, Zheng Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-18T02:55:58Z","title":"Probing Cross-modal Semantics Alignment Capability from the Textual Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09550","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":"sha256:402c23ed07ce09584ef56906a0203f2a007b0fc80a9b2e3f12672fc12d6c2a40","target":"record","created_at":"2026-07-05T05:07:56Z","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":"290e6bc8910aa4de63d227c332e7e14f13ceeb0e96e797587e20f252d917efbb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-18T02:55:58Z","title_canon_sha256":"b069a2dbd94700187de05023bfd8b4ec8dbdb2d2447604f69b0d44a234ae0c56"},"schema_version":"1.0","source":{"id":"2210.09550","kind":"arxiv","version":1}},"canonical_sha256":"d390d26528e8bcd9fd165a7038a0eb89cb40cdd0e0c67ae90a1ac1bd3ff732fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d390d26528e8bcd9fd165a7038a0eb89cb40cdd0e0c67ae90a1ac1bd3ff732fc","first_computed_at":"2026-07-05T05:07:56.842082Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:07:56.842082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mArs7ydQOMSj3giGjw67LTPyPZGtQ6nXQ9/PLu/OU7kWGMBiCsHFLMUaNuqSKsmPZ32UaPGHrHO9Y1ttllYiCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:07:56.842544Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.09550","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:402c23ed07ce09584ef56906a0203f2a007b0fc80a9b2e3f12672fc12d6c2a40","sha256:7d1d626426efd4508b2a09701ecc794fe4e591d689f3e0c2f1d871093aa3bebf"],"state_sha256":"68f72400ed01eb4f696928a3fc98f1c5892eef331e9f987f99ec5316b0580061"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E/i2eyETbo6+o70EiOcttMXOo+uLKHfynnelUvhhqZQVmFyiaVMcUsEOvcPHwgZEXuqlaoJilzc44mHZZt5UAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T17:18:28.555404Z","bundle_sha256":"8da6527786665a7cf214daf2c03f30ca023c1c5f40510e0b72591e37aae628e1"}}