{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:WYCMOO2MKURE6PGXOVNKPWTPIS","short_pith_number":"pith:WYCMOO2M","canonical_record":{"source":{"id":"1711.06420","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-17T06:10:03Z","cross_cats_sorted":[],"title_canon_sha256":"54b25faa510bed216dc1e1789f8d4d9e727c6c122efb9ec9cfd14af1d4c57e25","abstract_canon_sha256":"1527994b0fb50a35654d31557902ad01473c81fb6bab811bc455db87438049c3"},"schema_version":"1.0"},"canonical_sha256":"b604c73b4c55224f3cd7755aa7da6f44bfd855f3b22db0d335d297ab8ff1e14a","source":{"kind":"arxiv","id":"1711.06420","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.06420","created_at":"2026-05-18T00:13:21Z"},{"alias_kind":"arxiv_version","alias_value":"1711.06420v2","created_at":"2026-05-18T00:13:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.06420","created_at":"2026-05-18T00:13:21Z"},{"alias_kind":"pith_short_12","alias_value":"WYCMOO2MKURE","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WYCMOO2MKURE6PGX","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WYCMOO2M","created_at":"2026-05-18T12:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:WYCMOO2MKURE6PGXOVNKPWTPIS","target":"record","payload":{"canonical_record":{"source":{"id":"1711.06420","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-17T06:10:03Z","cross_cats_sorted":[],"title_canon_sha256":"54b25faa510bed216dc1e1789f8d4d9e727c6c122efb9ec9cfd14af1d4c57e25","abstract_canon_sha256":"1527994b0fb50a35654d31557902ad01473c81fb6bab811bc455db87438049c3"},"schema_version":"1.0"},"canonical_sha256":"b604c73b4c55224f3cd7755aa7da6f44bfd855f3b22db0d335d297ab8ff1e14a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:21.767194Z","signature_b64":"je4m5ztvC1huJEaMRcXqZRfg08s2bVy7+e8JrrRI2Ea9ZPzlIkT0sr8JCacLfdSfWCl3EDJ4BXG7P67hL6qeCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b604c73b4c55224f3cd7755aa7da6f44bfd855f3b22db0d335d297ab8ff1e14a","last_reissued_at":"2026-05-18T00:13:21.766618Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:21.766618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.06420","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:13:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U/jvvZodAlBx4ap0yvEXQMAZZLba6Bx2orbAQD/homKt4YJxvIt1sWuIvR58LI519BCWxodQdvmQBn51MP8PDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T21:55:10.298475Z"},"content_sha256":"2c7d9c63c4fba771cdcf0cecc4622c8e15342ccbceb998d3ec30709715ab9e8f","schema_version":"1.0","event_id":"sha256:2c7d9c63c4fba771cdcf0cecc4622c8e15342ccbceb998d3ec30709715ab9e8f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:WYCMOO2MKURE6PGXOVNKPWTPIS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gang Wang, Jianfei Cai, Jiuxiang Gu, Li Niu, Shafiq Joty","submitted_at":"2017-11-17T06:10:03Z","abstract_excerpt":"Textual-visual cross-modal retrieval has been a hot research topic in both computer vision and natural language processing communities. Learning appropriate representations for multi-modal data is crucial for the cross-modal retrieval performance. Unlike existing image-text retrieval approaches that embed image-text pairs as single feature vectors in a common representational space, we propose to incorporate generative processes into the cross-modal feature embedding, through which we are able to learn not only the global abstract features but also the local grounded features. Extensive experi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.06420","kind":"arxiv","version":2},"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":"2026-05-18T00:13:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YeO5tK54oePsSxJ+qL5vIZohd6295p65LTw/U2C1QAB05tKHQG1abQYW9lufT70DOfkzftT1LkdzpKq9kiB+Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T21:55:10.298820Z"},"content_sha256":"9843fa018719bba2b64c4092a40154ac593ea8fbd811ecc269dbfa366eda57b5","schema_version":"1.0","event_id":"sha256:9843fa018719bba2b64c4092a40154ac593ea8fbd811ecc269dbfa366eda57b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WYCMOO2MKURE6PGXOVNKPWTPIS/bundle.json","state_url":"https://pith.science/pith/WYCMOO2MKURE6PGXOVNKPWTPIS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WYCMOO2MKURE6PGXOVNKPWTPIS/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":"2026-05-19T21:55:10Z","links":{"resolver":"https://pith.science/pith/WYCMOO2MKURE6PGXOVNKPWTPIS","bundle":"https://pith.science/pith/WYCMOO2MKURE6PGXOVNKPWTPIS/bundle.json","state":"https://pith.science/pith/WYCMOO2MKURE6PGXOVNKPWTPIS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WYCMOO2MKURE6PGXOVNKPWTPIS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:WYCMOO2MKURE6PGXOVNKPWTPIS","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":"1527994b0fb50a35654d31557902ad01473c81fb6bab811bc455db87438049c3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-17T06:10:03Z","title_canon_sha256":"54b25faa510bed216dc1e1789f8d4d9e727c6c122efb9ec9cfd14af1d4c57e25"},"schema_version":"1.0","source":{"id":"1711.06420","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.06420","created_at":"2026-05-18T00:13:21Z"},{"alias_kind":"arxiv_version","alias_value":"1711.06420v2","created_at":"2026-05-18T00:13:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.06420","created_at":"2026-05-18T00:13:21Z"},{"alias_kind":"pith_short_12","alias_value":"WYCMOO2MKURE","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WYCMOO2MKURE6PGX","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WYCMOO2M","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:9843fa018719bba2b64c4092a40154ac593ea8fbd811ecc269dbfa366eda57b5","target":"graph","created_at":"2026-05-18T00:13:21Z","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":"Textual-visual cross-modal retrieval has been a hot research topic in both computer vision and natural language processing communities. Learning appropriate representations for multi-modal data is crucial for the cross-modal retrieval performance. Unlike existing image-text retrieval approaches that embed image-text pairs as single feature vectors in a common representational space, we propose to incorporate generative processes into the cross-modal feature embedding, through which we are able to learn not only the global abstract features but also the local grounded features. Extensive experi","authors_text":"Gang Wang, Jianfei Cai, Jiuxiang Gu, Li Niu, Shafiq Joty","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-17T06:10:03Z","title":"Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.06420","kind":"arxiv","version":2},"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":"sha256:2c7d9c63c4fba771cdcf0cecc4622c8e15342ccbceb998d3ec30709715ab9e8f","target":"record","created_at":"2026-05-18T00:13:21Z","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":"1527994b0fb50a35654d31557902ad01473c81fb6bab811bc455db87438049c3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-17T06:10:03Z","title_canon_sha256":"54b25faa510bed216dc1e1789f8d4d9e727c6c122efb9ec9cfd14af1d4c57e25"},"schema_version":"1.0","source":{"id":"1711.06420","kind":"arxiv","version":2}},"canonical_sha256":"b604c73b4c55224f3cd7755aa7da6f44bfd855f3b22db0d335d297ab8ff1e14a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b604c73b4c55224f3cd7755aa7da6f44bfd855f3b22db0d335d297ab8ff1e14a","first_computed_at":"2026-05-18T00:13:21.766618Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:21.766618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"je4m5ztvC1huJEaMRcXqZRfg08s2bVy7+e8JrrRI2Ea9ZPzlIkT0sr8JCacLfdSfWCl3EDJ4BXG7P67hL6qeCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:21.767194Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.06420","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c7d9c63c4fba771cdcf0cecc4622c8e15342ccbceb998d3ec30709715ab9e8f","sha256:9843fa018719bba2b64c4092a40154ac593ea8fbd811ecc269dbfa366eda57b5"],"state_sha256":"7021101412a630ee710aa66c58e15beb2a547576013c589610201cc311bb26ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ztO610Mm6rFf1nqu555zbTivPObai6+WuASVKVzShbKKnVqyJ47e485hrLobIoGOjXU5ac3sQdxYNvDeaquUBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T21:55:10.300805Z","bundle_sha256":"05cbfe18d62191202e901b4708cf150d923bce6d05122ddeaa9c163a053452af"}}