{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ANBGJTW2SLDQCDYZWZBZFFTYOL","short_pith_number":"pith:ANBGJTW2","canonical_record":{"source":{"id":"1906.08595","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2019-06-20T13:20:22Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"48d49f303e04deecb0870d4b32c9afa95565ea1d8f2786841f47e5aa1755ff0e","abstract_canon_sha256":"59bda1bd1fd8f4b5098305f3bb0ac8170e3b9f787f4f2ea296e1863387a98f53"},"schema_version":"1.0"},"canonical_sha256":"034264ceda92c7010f19b64392967872efd76d61eedb665dbb912b399268a2b3","source":{"kind":"arxiv","id":"1906.08595","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.08595","created_at":"2026-05-17T23:42:51Z"},{"alias_kind":"arxiv_version","alias_value":"1906.08595v1","created_at":"2026-05-17T23:42:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08595","created_at":"2026-05-17T23:42:51Z"},{"alias_kind":"pith_short_12","alias_value":"ANBGJTW2SLDQ","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"ANBGJTW2SLDQCDYZ","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"ANBGJTW2","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ANBGJTW2SLDQCDYZWZBZFFTYOL","target":"record","payload":{"canonical_record":{"source":{"id":"1906.08595","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2019-06-20T13:20:22Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"48d49f303e04deecb0870d4b32c9afa95565ea1d8f2786841f47e5aa1755ff0e","abstract_canon_sha256":"59bda1bd1fd8f4b5098305f3bb0ac8170e3b9f787f4f2ea296e1863387a98f53"},"schema_version":"1.0"},"canonical_sha256":"034264ceda92c7010f19b64392967872efd76d61eedb665dbb912b399268a2b3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:51.987833Z","signature_b64":"v5I/zdA2805IDY96JUYSVV8phnwtaGa1v6hbTwfx/UBWQQwsmDJpTpXW27Ipx9QdVPaBoXZveU9cxc+gIeRoAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"034264ceda92c7010f19b64392967872efd76d61eedb665dbb912b399268a2b3","last_reissued_at":"2026-05-17T23:42:51.987421Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:51.987421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.08595","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":"2026-05-17T23:42:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Iv0fR0+aS3Tq0SFANziQy9jnXQNFXIzq14agIOfm1fc0BrxRxgfGBRfaDtcwuSD8DgPu1XiNcTtN9pTXnJHkCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T08:33:36.182552Z"},"content_sha256":"708efafa52e7005fc63f0045cbd1812776eb63d9b6d8ce95e93de93058fdc8fe","schema_version":"1.0","event_id":"sha256:708efafa52e7005fc63f0045cbd1812776eb63d9b6d8ce95e93de93058fdc8fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ANBGJTW2SLDQCDYZWZBZFFTYOL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding, Categorizing and Predicting Semantic Image-Text Relations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.MM","authors_text":"Avishek Anand, Christian Otto, Matthias Springstein, Ralph Ewerth","submitted_at":"2019-06-20T13:20:22Z","abstract_excerpt":"Two modalities are often used to convey information in a complementary and beneficial manner, e.g., in online news, videos, educational resources, or scientific publications. The automatic understanding of semantic correlations between text and associated images as well as their interplay has a great potential for enhanced multimodal web search and recommender systems. However, automatic understanding of multimodal information is still an unsolved research problem. Recent approaches such as image captioning focus on precisely describing visual content and translating it to text, but typically "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.08595","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":""},"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":"2026-05-17T23:42:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n+FhKAonUt0Y5BU78lfqndH992fOJ/7FekLImgTybQXnXOc18pGfNd1ImPdn/cD2uTpAWEqhCdMLfanl41l+AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T08:33:36.183265Z"},"content_sha256":"d80771c5661a1fb5590972914e010385390cc8aad6e02b8d5163dc2f50e710d7","schema_version":"1.0","event_id":"sha256:d80771c5661a1fb5590972914e010385390cc8aad6e02b8d5163dc2f50e710d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ANBGJTW2SLDQCDYZWZBZFFTYOL/bundle.json","state_url":"https://pith.science/pith/ANBGJTW2SLDQCDYZWZBZFFTYOL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ANBGJTW2SLDQCDYZWZBZFFTYOL/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":"2026-05-26T08:33:36Z","links":{"resolver":"https://pith.science/pith/ANBGJTW2SLDQCDYZWZBZFFTYOL","bundle":"https://pith.science/pith/ANBGJTW2SLDQCDYZWZBZFFTYOL/bundle.json","state":"https://pith.science/pith/ANBGJTW2SLDQCDYZWZBZFFTYOL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ANBGJTW2SLDQCDYZWZBZFFTYOL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ANBGJTW2SLDQCDYZWZBZFFTYOL","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":"59bda1bd1fd8f4b5098305f3bb0ac8170e3b9f787f4f2ea296e1863387a98f53","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2019-06-20T13:20:22Z","title_canon_sha256":"48d49f303e04deecb0870d4b32c9afa95565ea1d8f2786841f47e5aa1755ff0e"},"schema_version":"1.0","source":{"id":"1906.08595","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.08595","created_at":"2026-05-17T23:42:51Z"},{"alias_kind":"arxiv_version","alias_value":"1906.08595v1","created_at":"2026-05-17T23:42:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08595","created_at":"2026-05-17T23:42:51Z"},{"alias_kind":"pith_short_12","alias_value":"ANBGJTW2SLDQ","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"ANBGJTW2SLDQCDYZ","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"ANBGJTW2","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:d80771c5661a1fb5590972914e010385390cc8aad6e02b8d5163dc2f50e710d7","target":"graph","created_at":"2026-05-17T23:42:51Z","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"},"paper":{"abstract_excerpt":"Two modalities are often used to convey information in a complementary and beneficial manner, e.g., in online news, videos, educational resources, or scientific publications. The automatic understanding of semantic correlations between text and associated images as well as their interplay has a great potential for enhanced multimodal web search and recommender systems. However, automatic understanding of multimodal information is still an unsolved research problem. Recent approaches such as image captioning focus on precisely describing visual content and translating it to text, but typically ","authors_text":"Avishek Anand, Christian Otto, Matthias Springstein, Ralph Ewerth","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2019-06-20T13:20:22Z","title":"Understanding, Categorizing and Predicting Semantic Image-Text Relations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.08595","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":"sha256:708efafa52e7005fc63f0045cbd1812776eb63d9b6d8ce95e93de93058fdc8fe","target":"record","created_at":"2026-05-17T23:42:51Z","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":"59bda1bd1fd8f4b5098305f3bb0ac8170e3b9f787f4f2ea296e1863387a98f53","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2019-06-20T13:20:22Z","title_canon_sha256":"48d49f303e04deecb0870d4b32c9afa95565ea1d8f2786841f47e5aa1755ff0e"},"schema_version":"1.0","source":{"id":"1906.08595","kind":"arxiv","version":1}},"canonical_sha256":"034264ceda92c7010f19b64392967872efd76d61eedb665dbb912b399268a2b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"034264ceda92c7010f19b64392967872efd76d61eedb665dbb912b399268a2b3","first_computed_at":"2026-05-17T23:42:51.987421Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:51.987421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v5I/zdA2805IDY96JUYSVV8phnwtaGa1v6hbTwfx/UBWQQwsmDJpTpXW27Ipx9QdVPaBoXZveU9cxc+gIeRoAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:51.987833Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.08595","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:708efafa52e7005fc63f0045cbd1812776eb63d9b6d8ce95e93de93058fdc8fe","sha256:d80771c5661a1fb5590972914e010385390cc8aad6e02b8d5163dc2f50e710d7"],"state_sha256":"36ad6a167f20a04c0041ff6533271fc28598f1aca974f2fe514f0e2d31fd18e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"glW/XMkjYgyclaRCi88ghMG1zM4N5LP4xj3hTYf1tWkzDwBpK0NCBZa022T4vafMi4SPqczEVD8fUlWdC33iBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T08:33:36.186954Z","bundle_sha256":"78b9d183ecd41214fc637280258192a904bbe8f99541997cdd8258240104d618"}}