{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:KZOM6IISSFJRF3B4LKENJHMHSV","short_pith_number":"pith:KZOM6IIS","canonical_record":{"source":{"id":"2211.09371","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-17T06:55:49Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"a12ce2ecb2e813c620c24d361c54efe9cc509528b19769b70d9f918b0e9d176f","abstract_canon_sha256":"00816b214f800f1a543370301a8ba4d5a36b465e50576e5ee0702062588cf2c8"},"schema_version":"1.0"},"canonical_sha256":"565ccf2112915312ec3c5a88d49d879545029d4ad94c66bf61c53112e7a2153c","source":{"kind":"arxiv","id":"2211.09371","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.09371","created_at":"2026-07-05T05:52:23Z"},{"alias_kind":"arxiv_version","alias_value":"2211.09371v3","created_at":"2026-07-05T05:52:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09371","created_at":"2026-07-05T05:52:23Z"},{"alias_kind":"pith_short_12","alias_value":"KZOM6IISSFJR","created_at":"2026-07-05T05:52:23Z"},{"alias_kind":"pith_short_16","alias_value":"KZOM6IISSFJRF3B4","created_at":"2026-07-05T05:52:23Z"},{"alias_kind":"pith_short_8","alias_value":"KZOM6IIS","created_at":"2026-07-05T05:52:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:KZOM6IISSFJRF3B4LKENJHMHSV","target":"record","payload":{"canonical_record":{"source":{"id":"2211.09371","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-17T06:55:49Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"a12ce2ecb2e813c620c24d361c54efe9cc509528b19769b70d9f918b0e9d176f","abstract_canon_sha256":"00816b214f800f1a543370301a8ba4d5a36b465e50576e5ee0702062588cf2c8"},"schema_version":"1.0"},"canonical_sha256":"565ccf2112915312ec3c5a88d49d879545029d4ad94c66bf61c53112e7a2153c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:52:23.930948Z","signature_b64":"4y/aRYWF14hpusfiWloLncm81XW1RxQTb4glorTjY76hbsSnVrSgtrUXTBsWZZF2dN5d6mIVHCJTXoYOEKlADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"565ccf2112915312ec3c5a88d49d879545029d4ad94c66bf61c53112e7a2153c","last_reissued_at":"2026-07-05T05:52:23.930310Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:52:23.930310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.09371","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:52:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yjMZGlKrwqjnGdKf58cvDNE1a9aVWxgrpthD9N1P/osR54rmSUUXaDiEx0OONfXqSWYN+HsamiTiNvq4KBmICg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:20:27.001224Z"},"content_sha256":"327681670d999615a87001084f5e560bf915048ba99464da06789ddfde4e1121","schema_version":"1.0","event_id":"sha256:327681670d999615a87001084f5e560bf915048ba99464da06789ddfde4e1121"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:KZOM6IISSFJRF3B4LKENJHMHSV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CapEnrich: Enriching Caption Semantics for Web Images via Cross-modal Pre-trained Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Linli Yao, Qin Jin, Weijing Chen","submitted_at":"2022-11-17T06:55:49Z","abstract_excerpt":"Automatically generating textual descriptions for massive unlabeled images on the web can greatly benefit realistic web applications, e.g. multimodal retrieval and recommendation. However, existing models suffer from the problem of generating ``over-generic'' descriptions, such as their tendency to generate repetitive sentences with common concepts for different images. These generic descriptions fail to provide sufficient textual semantics for ever-changing web images. Inspired by the recent success of Vision-Language Pre-training (VLP) models that learn diverse image-text concept alignment d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09371","kind":"arxiv","version":3},"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/2211.09371/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":"2026-07-05T05:52:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8tdYM4fYMH4iwaj0qwyZG0zRdJR4eUf4ytirE9+BRzQ022cQ9CpqcFTgrg4aZjRm+VuPUQf3eHpnI/sKMV4kBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:20:27.001740Z"},"content_sha256":"897800beb0ef6b9a39b695670bce058ea86fa2602bd3d0cc7a52b2ecbd298f5f","schema_version":"1.0","event_id":"sha256:897800beb0ef6b9a39b695670bce058ea86fa2602bd3d0cc7a52b2ecbd298f5f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KZOM6IISSFJRF3B4LKENJHMHSV/bundle.json","state_url":"https://pith.science/pith/KZOM6IISSFJRF3B4LKENJHMHSV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KZOM6IISSFJRF3B4LKENJHMHSV/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":"2026-08-09T11:20:27Z","links":{"resolver":"https://pith.science/pith/KZOM6IISSFJRF3B4LKENJHMHSV","bundle":"https://pith.science/pith/KZOM6IISSFJRF3B4LKENJHMHSV/bundle.json","state":"https://pith.science/pith/KZOM6IISSFJRF3B4LKENJHMHSV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KZOM6IISSFJRF3B4LKENJHMHSV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KZOM6IISSFJRF3B4LKENJHMHSV","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":"00816b214f800f1a543370301a8ba4d5a36b465e50576e5ee0702062588cf2c8","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-17T06:55:49Z","title_canon_sha256":"a12ce2ecb2e813c620c24d361c54efe9cc509528b19769b70d9f918b0e9d176f"},"schema_version":"1.0","source":{"id":"2211.09371","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.09371","created_at":"2026-07-05T05:52:23Z"},{"alias_kind":"arxiv_version","alias_value":"2211.09371v3","created_at":"2026-07-05T05:52:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09371","created_at":"2026-07-05T05:52:23Z"},{"alias_kind":"pith_short_12","alias_value":"KZOM6IISSFJR","created_at":"2026-07-05T05:52:23Z"},{"alias_kind":"pith_short_16","alias_value":"KZOM6IISSFJRF3B4","created_at":"2026-07-05T05:52:23Z"},{"alias_kind":"pith_short_8","alias_value":"KZOM6IIS","created_at":"2026-07-05T05:52:23Z"}],"graph_snapshots":[{"event_id":"sha256:897800beb0ef6b9a39b695670bce058ea86fa2602bd3d0cc7a52b2ecbd298f5f","target":"graph","created_at":"2026-07-05T05:52:23Z","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/2211.09371/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatically generating textual descriptions for massive unlabeled images on the web can greatly benefit realistic web applications, e.g. multimodal retrieval and recommendation. However, existing models suffer from the problem of generating ``over-generic'' descriptions, such as their tendency to generate repetitive sentences with common concepts for different images. These generic descriptions fail to provide sufficient textual semantics for ever-changing web images. Inspired by the recent success of Vision-Language Pre-training (VLP) models that learn diverse image-text concept alignment d","authors_text":"Linli Yao, Qin Jin, Weijing Chen","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-17T06:55:49Z","title":"CapEnrich: Enriching Caption Semantics for Web Images via Cross-modal Pre-trained Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09371","kind":"arxiv","version":3},"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":"sha256:327681670d999615a87001084f5e560bf915048ba99464da06789ddfde4e1121","target":"record","created_at":"2026-07-05T05:52:23Z","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":"00816b214f800f1a543370301a8ba4d5a36b465e50576e5ee0702062588cf2c8","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-17T06:55:49Z","title_canon_sha256":"a12ce2ecb2e813c620c24d361c54efe9cc509528b19769b70d9f918b0e9d176f"},"schema_version":"1.0","source":{"id":"2211.09371","kind":"arxiv","version":3}},"canonical_sha256":"565ccf2112915312ec3c5a88d49d879545029d4ad94c66bf61c53112e7a2153c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"565ccf2112915312ec3c5a88d49d879545029d4ad94c66bf61c53112e7a2153c","first_computed_at":"2026-07-05T05:52:23.930310Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:52:23.930310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4y/aRYWF14hpusfiWloLncm81XW1RxQTb4glorTjY76hbsSnVrSgtrUXTBsWZZF2dN5d6mIVHCJTXoYOEKlADA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:52:23.930948Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.09371","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:327681670d999615a87001084f5e560bf915048ba99464da06789ddfde4e1121","sha256:897800beb0ef6b9a39b695670bce058ea86fa2602bd3d0cc7a52b2ecbd298f5f"],"state_sha256":"815720c056435768d68185f76861ad763c7c6d43a21a8e449f589187841c4f9b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2nC4RkMC9EOgchGjMnNjA63Pp/30kDaYPmB21QE9Ho2VRXD/0Vf+HL+c4sUxPkUKsaO6f5xBzu/DiiG9YeaeBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T11:20:27.005679Z","bundle_sha256":"fc18e8cb357156c8ec6337a2ad0e6ac6afe1c9cb85e3a8410407fdd8a7a16e16"}}