{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XVPLX7EQP77YTG4SETDTVFTH45","short_pith_number":"pith:XVPLX7EQ","canonical_record":{"source":{"id":"2305.18373","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-28T04:49:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d589c2dbefc72501cde08586d20930a29d58ee3da9bdc3eb5f34248acf0e28fc","abstract_canon_sha256":"7664b61974cda9ce15bf8208457d1da0aab37f2daff8714ea4b518c3d1419d66"},"schema_version":"1.0"},"canonical_sha256":"bd5ebbfc907fff899b9224c73a9667e77150688e3e0430baad5e3c15f3de2a5a","source":{"kind":"arxiv","id":"2305.18373","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.18373","created_at":"2026-07-05T06:15:00Z"},{"alias_kind":"arxiv_version","alias_value":"2305.18373v1","created_at":"2026-07-05T06:15:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18373","created_at":"2026-07-05T06:15:00Z"},{"alias_kind":"pith_short_12","alias_value":"XVPLX7EQP77Y","created_at":"2026-07-05T06:15:00Z"},{"alias_kind":"pith_short_16","alias_value":"XVPLX7EQP77YTG4S","created_at":"2026-07-05T06:15:00Z"},{"alias_kind":"pith_short_8","alias_value":"XVPLX7EQ","created_at":"2026-07-05T06:15:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XVPLX7EQP77YTG4SETDTVFTH45","target":"record","payload":{"canonical_record":{"source":{"id":"2305.18373","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-28T04:49:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d589c2dbefc72501cde08586d20930a29d58ee3da9bdc3eb5f34248acf0e28fc","abstract_canon_sha256":"7664b61974cda9ce15bf8208457d1da0aab37f2daff8714ea4b518c3d1419d66"},"schema_version":"1.0"},"canonical_sha256":"bd5ebbfc907fff899b9224c73a9667e77150688e3e0430baad5e3c15f3de2a5a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:00.194644Z","signature_b64":"BHREP98s5UjkUZDNY4vAjZP61TmP6DS+7piaQRYdIKrCyqqfR3Qsa/2zfmYCcHFPO+j5ODTWbRIehMpUpQjQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd5ebbfc907fff899b9224c73a9667e77150688e3e0430baad5e3c15f3de2a5a","last_reissued_at":"2026-07-05T06:15:00.194257Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:00.194257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.18373","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":"2026-07-05T06:15:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RGWC/9qHHOOQ8QrJTAb9Zll3fCRGvuhpSfjOfEJw3lQYK3JRUs+6JXeim1BGA2oBbsy0LwS5FdagyOi8utrSAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:29:25.995484Z"},"content_sha256":"1688f819744ac91e4c4f3f29be24612a29b35e2e875f5ae1ecfea1e562194457","schema_version":"1.0","event_id":"sha256:1688f819744ac91e4c4f3f29be24612a29b35e2e875f5ae1ecfea1e562194457"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XVPLX7EQP77YTG4SETDTVFTH45","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"KAFA: Rethinking Image Ad Understanding with Knowledge-Augmented Feature Adaptation of Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Arjun R. Akula, Garima Pruthi, Hao Su, Pradyumna Narayana, Sugato Basu, Varun Jampani, Zhiwei Jia","submitted_at":"2023-05-28T04:49:01Z","abstract_excerpt":"Image ad understanding is a crucial task with wide real-world applications. Although highly challenging with the involvement of diverse atypical scenes, real-world entities, and reasoning over scene-texts, how to interpret image ads is relatively under-explored, especially in the era of foundational vision-language models (VLMs) featuring impressive generalizability and adaptability. In this paper, we perform the first empirical study of image ad understanding through the lens of pre-trained VLMs. We benchmark and reveal practical challenges in adapting these VLMs to image ad understanding. We"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18373","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/2305.18373/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":"2026-07-05T06:15:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"82mUwH1QKWCtKjsuctmeUAQ58J25pbIfePcacknuL6MMxUsOt/KduB7D7+LRcnN6rVit2HfzM/jw2V/MG8iZCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:29:25.996102Z"},"content_sha256":"b3fb78adec5e302848908a27e36906e1f6965df468f7c7b55cc309ee051b871b","schema_version":"1.0","event_id":"sha256:b3fb78adec5e302848908a27e36906e1f6965df468f7c7b55cc309ee051b871b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XVPLX7EQP77YTG4SETDTVFTH45/bundle.json","state_url":"https://pith.science/pith/XVPLX7EQP77YTG4SETDTVFTH45/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XVPLX7EQP77YTG4SETDTVFTH45/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":"2026-08-05T09:29:25Z","links":{"resolver":"https://pith.science/pith/XVPLX7EQP77YTG4SETDTVFTH45","bundle":"https://pith.science/pith/XVPLX7EQP77YTG4SETDTVFTH45/bundle.json","state":"https://pith.science/pith/XVPLX7EQP77YTG4SETDTVFTH45/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XVPLX7EQP77YTG4SETDTVFTH45/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XVPLX7EQP77YTG4SETDTVFTH45","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":"7664b61974cda9ce15bf8208457d1da0aab37f2daff8714ea4b518c3d1419d66","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-28T04:49:01Z","title_canon_sha256":"d589c2dbefc72501cde08586d20930a29d58ee3da9bdc3eb5f34248acf0e28fc"},"schema_version":"1.0","source":{"id":"2305.18373","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.18373","created_at":"2026-07-05T06:15:00Z"},{"alias_kind":"arxiv_version","alias_value":"2305.18373v1","created_at":"2026-07-05T06:15:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18373","created_at":"2026-07-05T06:15:00Z"},{"alias_kind":"pith_short_12","alias_value":"XVPLX7EQP77Y","created_at":"2026-07-05T06:15:00Z"},{"alias_kind":"pith_short_16","alias_value":"XVPLX7EQP77YTG4S","created_at":"2026-07-05T06:15:00Z"},{"alias_kind":"pith_short_8","alias_value":"XVPLX7EQ","created_at":"2026-07-05T06:15:00Z"}],"graph_snapshots":[{"event_id":"sha256:b3fb78adec5e302848908a27e36906e1f6965df468f7c7b55cc309ee051b871b","target":"graph","created_at":"2026-07-05T06:15:00Z","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/2305.18373/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image ad understanding is a crucial task with wide real-world applications. Although highly challenging with the involvement of diverse atypical scenes, real-world entities, and reasoning over scene-texts, how to interpret image ads is relatively under-explored, especially in the era of foundational vision-language models (VLMs) featuring impressive generalizability and adaptability. In this paper, we perform the first empirical study of image ad understanding through the lens of pre-trained VLMs. We benchmark and reveal practical challenges in adapting these VLMs to image ad understanding. We","authors_text":"Arjun R. Akula, Garima Pruthi, Hao Su, Pradyumna Narayana, Sugato Basu, Varun Jampani, Zhiwei Jia","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-28T04:49:01Z","title":"KAFA: Rethinking Image Ad Understanding with Knowledge-Augmented Feature Adaptation of Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18373","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":"sha256:1688f819744ac91e4c4f3f29be24612a29b35e2e875f5ae1ecfea1e562194457","target":"record","created_at":"2026-07-05T06:15:00Z","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":"7664b61974cda9ce15bf8208457d1da0aab37f2daff8714ea4b518c3d1419d66","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-28T04:49:01Z","title_canon_sha256":"d589c2dbefc72501cde08586d20930a29d58ee3da9bdc3eb5f34248acf0e28fc"},"schema_version":"1.0","source":{"id":"2305.18373","kind":"arxiv","version":1}},"canonical_sha256":"bd5ebbfc907fff899b9224c73a9667e77150688e3e0430baad5e3c15f3de2a5a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd5ebbfc907fff899b9224c73a9667e77150688e3e0430baad5e3c15f3de2a5a","first_computed_at":"2026-07-05T06:15:00.194257Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:15:00.194257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BHREP98s5UjkUZDNY4vAjZP61TmP6DS+7piaQRYdIKrCyqqfR3Qsa/2zfmYCcHFPO+j5ODTWbRIehMpUpQjQCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:15:00.194644Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.18373","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1688f819744ac91e4c4f3f29be24612a29b35e2e875f5ae1ecfea1e562194457","sha256:b3fb78adec5e302848908a27e36906e1f6965df468f7c7b55cc309ee051b871b"],"state_sha256":"a529b997cc7397e07b2082462db2bde0c35cced39110037779fe3ef7a906b4b7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L6x++K4jrWkA+yJ4AvwhNrYSkzKLqxLi+NcBaSSq+dAZJvsAeQsENbZ30Tdp7PI5QVyq/HGADBiD0S4/aKB+Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T09:29:25.999838Z","bundle_sha256":"84f61146fa70471ed75b00f439c70036692a4b23806fbcd64a31c7dc9cdaaae1"}}