{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:KYMGNR77DRT632YORJ4JQR6SOH","short_pith_number":"pith:KYMGNR77","canonical_record":{"source":{"id":"1804.09539","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2018-04-25T13:22:38Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"a2fa463f9968f1771d4c3328755970019001aee88f1b3ac5bb269cc7606259a1","abstract_canon_sha256":"fe7961175e070151db5643dac653004192f75909d6550d7c7b7c9af3d557152e"},"schema_version":"1.0"},"canonical_sha256":"561866c7ff1c67edeb0e8a789847d271d6f4383a458558ee7ce016045d3fd6fb","source":{"kind":"arxiv","id":"1804.09539","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.09539","created_at":"2026-05-18T00:17:31Z"},{"alias_kind":"arxiv_version","alias_value":"1804.09539v1","created_at":"2026-05-18T00:17:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.09539","created_at":"2026-05-18T00:17:31Z"},{"alias_kind":"pith_short_12","alias_value":"KYMGNR77DRT6","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"KYMGNR77DRT632YO","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"KYMGNR77","created_at":"2026-05-18T12:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:KYMGNR77DRT632YORJ4JQR6SOH","target":"record","payload":{"canonical_record":{"source":{"id":"1804.09539","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2018-04-25T13:22:38Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"a2fa463f9968f1771d4c3328755970019001aee88f1b3ac5bb269cc7606259a1","abstract_canon_sha256":"fe7961175e070151db5643dac653004192f75909d6550d7c7b7c9af3d557152e"},"schema_version":"1.0"},"canonical_sha256":"561866c7ff1c67edeb0e8a789847d271d6f4383a458558ee7ce016045d3fd6fb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:31.488665Z","signature_b64":"9SbAlEqhHjxPxNOBAlwngqivy8ivWX6rhvL00Akw9yjv1wUJPXzpaaPFQWEksDqeTgdwoV11TroSQv9fiXTiBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"561866c7ff1c67edeb0e8a789847d271d6f4383a458558ee7ce016045d3fd6fb","last_reissued_at":"2026-05-18T00:17:31.488025Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:31.488025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.09539","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":"2026-05-18T00:17:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tC5YEUCSV9fCEilRzx1kcx3G8EvFQ+49p6mLs05VPnfGnMtqPhHrFwwL0DIXAvfbeEv420yFoDycbYazK3BeCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T00:14:58.268786Z"},"content_sha256":"8d77e911d51562577044c4fec077360204a2845d52a79a6f3326134d6167106a","schema_version":"1.0","event_id":"sha256:8d77e911d51562577044c4fec077360204a2845d52a79a6f3326134d6167106a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:KYMGNR77DRT632YORJ4JQR6SOH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cross-media Multi-level Alignment with Relation Attention Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.MM","authors_text":"Jinwei Qi, Yuxin Peng, Yuxin Yuan","submitted_at":"2018-04-25T13:22:38Z","abstract_excerpt":"With the rapid growth of multimedia data, such as image and text, it is a highly challenging problem to effectively correlate and retrieve the data of different media types. Naturally, when correlating an image with textual description, people focus on not only the alignment between discriminative image regions and key words, but also the relations lying in the visual and textual context. Relation understanding is essential for cross-media correlation learning, which is ignored by prior cross-media retrieval works. To address the above issue, we propose Cross-media Relation Attention Network ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.09539","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":"2026-05-18T00:17:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XPl5e4nG4J5Hf1ayw1dKQdLn8aTxXHh0aNcDbSvarPDFDLC2QgGcI5lsg0h+DJb3+lnWNz9feDgFquMUyOnJDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T00:14:58.269129Z"},"content_sha256":"495a131e8de5d640a23d1a388a2a73dcbe399664a70a6a71419d2e56fa57d9c2","schema_version":"1.0","event_id":"sha256:495a131e8de5d640a23d1a388a2a73dcbe399664a70a6a71419d2e56fa57d9c2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KYMGNR77DRT632YORJ4JQR6SOH/bundle.json","state_url":"https://pith.science/pith/KYMGNR77DRT632YORJ4JQR6SOH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KYMGNR77DRT632YORJ4JQR6SOH/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":"2026-06-09T00:14:58Z","links":{"resolver":"https://pith.science/pith/KYMGNR77DRT632YORJ4JQR6SOH","bundle":"https://pith.science/pith/KYMGNR77DRT632YORJ4JQR6SOH/bundle.json","state":"https://pith.science/pith/KYMGNR77DRT632YORJ4JQR6SOH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KYMGNR77DRT632YORJ4JQR6SOH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:KYMGNR77DRT632YORJ4JQR6SOH","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":"fe7961175e070151db5643dac653004192f75909d6550d7c7b7c9af3d557152e","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2018-04-25T13:22:38Z","title_canon_sha256":"a2fa463f9968f1771d4c3328755970019001aee88f1b3ac5bb269cc7606259a1"},"schema_version":"1.0","source":{"id":"1804.09539","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.09539","created_at":"2026-05-18T00:17:31Z"},{"alias_kind":"arxiv_version","alias_value":"1804.09539v1","created_at":"2026-05-18T00:17:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.09539","created_at":"2026-05-18T00:17:31Z"},{"alias_kind":"pith_short_12","alias_value":"KYMGNR77DRT6","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"KYMGNR77DRT632YO","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"KYMGNR77","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:495a131e8de5d640a23d1a388a2a73dcbe399664a70a6a71419d2e56fa57d9c2","target":"graph","created_at":"2026-05-18T00:17:31Z","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":"With the rapid growth of multimedia data, such as image and text, it is a highly challenging problem to effectively correlate and retrieve the data of different media types. Naturally, when correlating an image with textual description, people focus on not only the alignment between discriminative image regions and key words, but also the relations lying in the visual and textual context. Relation understanding is essential for cross-media correlation learning, which is ignored by prior cross-media retrieval works. To address the above issue, we propose Cross-media Relation Attention Network (","authors_text":"Jinwei Qi, Yuxin Peng, Yuxin Yuan","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2018-04-25T13:22:38Z","title":"Cross-media Multi-level Alignment with Relation Attention Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.09539","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":"sha256:8d77e911d51562577044c4fec077360204a2845d52a79a6f3326134d6167106a","target":"record","created_at":"2026-05-18T00:17:31Z","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":"fe7961175e070151db5643dac653004192f75909d6550d7c7b7c9af3d557152e","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2018-04-25T13:22:38Z","title_canon_sha256":"a2fa463f9968f1771d4c3328755970019001aee88f1b3ac5bb269cc7606259a1"},"schema_version":"1.0","source":{"id":"1804.09539","kind":"arxiv","version":1}},"canonical_sha256":"561866c7ff1c67edeb0e8a789847d271d6f4383a458558ee7ce016045d3fd6fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"561866c7ff1c67edeb0e8a789847d271d6f4383a458558ee7ce016045d3fd6fb","first_computed_at":"2026-05-18T00:17:31.488025Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:17:31.488025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9SbAlEqhHjxPxNOBAlwngqivy8ivWX6rhvL00Akw9yjv1wUJPXzpaaPFQWEksDqeTgdwoV11TroSQv9fiXTiBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:17:31.488665Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.09539","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d77e911d51562577044c4fec077360204a2845d52a79a6f3326134d6167106a","sha256:495a131e8de5d640a23d1a388a2a73dcbe399664a70a6a71419d2e56fa57d9c2"],"state_sha256":"5f8aa89ca7c7e917b61933f51e21b4b2424c9daac2775be33abab25922c09dec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5KkVLkIZS5c89K/hv64LwxL8lwzvMzl66vvkqJBBkPdx+9lDCJSqt/WD4imvl+xyLMuoAg7JP1QOSGOFosNQAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T00:14:58.271304Z","bundle_sha256":"ac4bdbd063360acd84b0609d3f32089021c90ddc09632d7e3d1d4b522435849b"}}