{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3I2DHLDFAMMJO2K2725RYPFEAT","short_pith_number":"pith:3I2DHLDF","canonical_record":{"source":{"id":"2303.03144","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2023-03-06T13:59:37Z","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"title_canon_sha256":"a88adf4adb806f7a66290014644dd9b6bf3de6fcda112ab8ab42fd36bafe90d6","abstract_canon_sha256":"8513229213c26ce054a3138dbaa8b83b257a4c980e401f4561a8a17f2d91e3ff"},"schema_version":"1.0"},"canonical_sha256":"da3433ac65031897695afebb1c3ca404c53c7a6cdadd8c315db6c3ef9f5b6e99","source":{"kind":"arxiv","id":"2303.03144","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.03144","created_at":"2026-07-05T05:48:19Z"},{"alias_kind":"arxiv_version","alias_value":"2303.03144v1","created_at":"2026-07-05T05:48:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.03144","created_at":"2026-07-05T05:48:19Z"},{"alias_kind":"pith_short_12","alias_value":"3I2DHLDFAMMJ","created_at":"2026-07-05T05:48:19Z"},{"alias_kind":"pith_short_16","alias_value":"3I2DHLDFAMMJO2K2","created_at":"2026-07-05T05:48:19Z"},{"alias_kind":"pith_short_8","alias_value":"3I2DHLDF","created_at":"2026-07-05T05:48:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3I2DHLDFAMMJO2K2725RYPFEAT","target":"record","payload":{"canonical_record":{"source":{"id":"2303.03144","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2023-03-06T13:59:37Z","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"title_canon_sha256":"a88adf4adb806f7a66290014644dd9b6bf3de6fcda112ab8ab42fd36bafe90d6","abstract_canon_sha256":"8513229213c26ce054a3138dbaa8b83b257a4c980e401f4561a8a17f2d91e3ff"},"schema_version":"1.0"},"canonical_sha256":"da3433ac65031897695afebb1c3ca404c53c7a6cdadd8c315db6c3ef9f5b6e99","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:19.559914Z","signature_b64":"tbIy1lwmVihgNFNErPPwWcwJZL05S2kue9vwsTDxJysbMZ6imD+D6UlZ29GY20vGOMGmgfqgxeaNar0BqYWiBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da3433ac65031897695afebb1c3ca404c53c7a6cdadd8c315db6c3ef9f5b6e99","last_reissued_at":"2026-07-05T05:48:19.559572Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:19.559572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.03144","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":"2026-07-05T05:48:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AJAWtmAwkGFP7TxYipEqxH0RRDcR+yFfwT1W0bygflQGFaDbA57hskMLcCY6FULe97gc2IS4+Is2dE6iC+4kDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:29:13.906469Z"},"content_sha256":"f26067a1fb0eae1f5adf7256eb8a54f2f35bf0d255411fe87058560ce5b22757","schema_version":"1.0","event_id":"sha256:f26067a1fb0eae1f5adf7256eb8a54f2f35bf0d255411fe87058560ce5b22757"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3I2DHLDFAMMJO2K2725RYPFEAT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"IPA-CLIP: Integrating Phonetic Priors into Vision and Language Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Chihaya Matsuhira, Ichiro Ide, Keisuke Doman, Marc A. Kastner, Takahiro Komamizu, Takatsugu Hirayama, Yasutomo Kawanishi","submitted_at":"2023-03-06T13:59:37Z","abstract_excerpt":"Recently, large-scale Vision and Language (V\\&L) pretraining has become the standard backbone of many multimedia systems. While it has shown remarkable performance even in unseen situations, it often performs in ways not intuitive to humans. Particularly, they usually do not consider the pronunciation of the input, which humans would utilize to understand language, especially when it comes to unknown words. Thus, this paper inserts phonetic prior into Contrastive Language-Image Pretraining (CLIP), one of the V\\&L pretrained models, to make it consider the pronunciation similarity among its pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.03144","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/2303.03144/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":"2026-07-05T05:48:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rIMp7Z8i9f2iHGe2lDs/tfaxoK4iK4D3kw/dGRqD7ZLy3BuTDHOIIqa/EkJen/rnonlIZne+3t3bL6e0QCVgDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:29:13.906843Z"},"content_sha256":"8387e142779de8e8cde762b8b0150bfb2a88b0445c72e04fda1be4f8b30afc01","schema_version":"1.0","event_id":"sha256:8387e142779de8e8cde762b8b0150bfb2a88b0445c72e04fda1be4f8b30afc01"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3I2DHLDFAMMJO2K2725RYPFEAT/bundle.json","state_url":"https://pith.science/pith/3I2DHLDFAMMJO2K2725RYPFEAT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3I2DHLDFAMMJO2K2725RYPFEAT/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":"2026-07-06T17:29:13Z","links":{"resolver":"https://pith.science/pith/3I2DHLDFAMMJO2K2725RYPFEAT","bundle":"https://pith.science/pith/3I2DHLDFAMMJO2K2725RYPFEAT/bundle.json","state":"https://pith.science/pith/3I2DHLDFAMMJO2K2725RYPFEAT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3I2DHLDFAMMJO2K2725RYPFEAT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3I2DHLDFAMMJO2K2725RYPFEAT","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":"8513229213c26ce054a3138dbaa8b83b257a4c980e401f4561a8a17f2d91e3ff","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2023-03-06T13:59:37Z","title_canon_sha256":"a88adf4adb806f7a66290014644dd9b6bf3de6fcda112ab8ab42fd36bafe90d6"},"schema_version":"1.0","source":{"id":"2303.03144","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.03144","created_at":"2026-07-05T05:48:19Z"},{"alias_kind":"arxiv_version","alias_value":"2303.03144v1","created_at":"2026-07-05T05:48:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.03144","created_at":"2026-07-05T05:48:19Z"},{"alias_kind":"pith_short_12","alias_value":"3I2DHLDFAMMJ","created_at":"2026-07-05T05:48:19Z"},{"alias_kind":"pith_short_16","alias_value":"3I2DHLDFAMMJO2K2","created_at":"2026-07-05T05:48:19Z"},{"alias_kind":"pith_short_8","alias_value":"3I2DHLDF","created_at":"2026-07-05T05:48:19Z"}],"graph_snapshots":[{"event_id":"sha256:8387e142779de8e8cde762b8b0150bfb2a88b0445c72e04fda1be4f8b30afc01","target":"graph","created_at":"2026-07-05T05:48:19Z","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/2303.03144/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, large-scale Vision and Language (V\\&L) pretraining has become the standard backbone of many multimedia systems. While it has shown remarkable performance even in unseen situations, it often performs in ways not intuitive to humans. Particularly, they usually do not consider the pronunciation of the input, which humans would utilize to understand language, especially when it comes to unknown words. Thus, this paper inserts phonetic prior into Contrastive Language-Image Pretraining (CLIP), one of the V\\&L pretrained models, to make it consider the pronunciation similarity among its pro","authors_text":"Chihaya Matsuhira, Ichiro Ide, Keisuke Doman, Marc A. Kastner, Takahiro Komamizu, Takatsugu Hirayama, Yasutomo Kawanishi","cross_cats":["cs.CL","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2023-03-06T13:59:37Z","title":"IPA-CLIP: Integrating Phonetic Priors into Vision and Language Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.03144","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:f26067a1fb0eae1f5adf7256eb8a54f2f35bf0d255411fe87058560ce5b22757","target":"record","created_at":"2026-07-05T05:48:19Z","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":"8513229213c26ce054a3138dbaa8b83b257a4c980e401f4561a8a17f2d91e3ff","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2023-03-06T13:59:37Z","title_canon_sha256":"a88adf4adb806f7a66290014644dd9b6bf3de6fcda112ab8ab42fd36bafe90d6"},"schema_version":"1.0","source":{"id":"2303.03144","kind":"arxiv","version":1}},"canonical_sha256":"da3433ac65031897695afebb1c3ca404c53c7a6cdadd8c315db6c3ef9f5b6e99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da3433ac65031897695afebb1c3ca404c53c7a6cdadd8c315db6c3ef9f5b6e99","first_computed_at":"2026-07-05T05:48:19.559572Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:48:19.559572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tbIy1lwmVihgNFNErPPwWcwJZL05S2kue9vwsTDxJysbMZ6imD+D6UlZ29GY20vGOMGmgfqgxeaNar0BqYWiBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:48:19.559914Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.03144","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f26067a1fb0eae1f5adf7256eb8a54f2f35bf0d255411fe87058560ce5b22757","sha256:8387e142779de8e8cde762b8b0150bfb2a88b0445c72e04fda1be4f8b30afc01"],"state_sha256":"bfdd9c555db1817d218a2e8176260928079a4fab43bd437bfed55ed5d33f7a2c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GY2fn/mTHAbloJhaJLWiVhyzxlhhltktKIL6EHPbazYLzweUNW9Fl59VGCSpEgSrcL+j0eFFLFEOIzd3aw8VAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T17:29:13.908847Z","bundle_sha256":"a01c0468d63972910d20f4039658cb2e19c85d517a4a12cf30909054e2ae168d"}}