{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:CQF2TUTOZV4MPXCDSKGPIG4Z2C","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":"749a1ef180dcc02e4edccc4b1d3db2ea5f09c8543514cf4343db0fcf175438f0","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-15T12:40:11Z","title_canon_sha256":"a5427cc2b911b154912191cc62f18f765f6a5e1a9e3f8ff4eef08db15de6cde7"},"schema_version":"1.0","source":{"id":"1711.05535","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.05535","created_at":"2026-07-05T03:00:43Z"},{"alias_kind":"arxiv_version","alias_value":"1711.05535v4","created_at":"2026-07-05T03:00:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.05535","created_at":"2026-07-05T03:00:43Z"},{"alias_kind":"pith_short_12","alias_value":"CQF2TUTOZV4M","created_at":"2026-07-05T03:00:43Z"},{"alias_kind":"pith_short_16","alias_value":"CQF2TUTOZV4MPXCD","created_at":"2026-07-05T03:00:43Z"},{"alias_kind":"pith_short_8","alias_value":"CQF2TUTO","created_at":"2026-07-05T03:00:43Z"}],"graph_snapshots":[{"event_id":"sha256:02c296c228e57770f892d1b64d7421393e26f34966c5fcc916ebf800a6ad9511","target":"graph","created_at":"2026-07-05T03:00:43Z","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/1711.05535/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Matching images and sentences demands a fine understanding of both modalities. In this paper, we propose a new system to discriminatively embed the image and text to a shared visual-textual space. In this field, most existing works apply the ranking loss to pull the positive image / text pairs close and push the negative pairs apart from each other. However, directly deploying the ranking loss is hard for network learning, since it starts from the two heterogeneous features to build inter-modal relationship. To address this problem, we propose the instance loss which explicitly considers the i","authors_text":"Liang Zheng, Michael Garrett, Mingliang Xu, Yi-Dong Shen, Yi Yang, Zhedong Zheng","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-15T12:40:11Z","title":"Dual-Path Convolutional Image-Text Embeddings with Instance Loss"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.05535","kind":"arxiv","version":4},"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":"sha256:06487e9aaaa6c680f22ef2b61d273787018d7f22c29a3be3c1b672513e68b02a","target":"record","created_at":"2026-07-05T03:00:43Z","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":"749a1ef180dcc02e4edccc4b1d3db2ea5f09c8543514cf4343db0fcf175438f0","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-15T12:40:11Z","title_canon_sha256":"a5427cc2b911b154912191cc62f18f765f6a5e1a9e3f8ff4eef08db15de6cde7"},"schema_version":"1.0","source":{"id":"1711.05535","kind":"arxiv","version":4}},"canonical_sha256":"140ba9d26ecd78c7dc43928cf41b99d0a7f6c7c67a9c2a970d1046faebac5069","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"140ba9d26ecd78c7dc43928cf41b99d0a7f6c7c67a9c2a970d1046faebac5069","first_computed_at":"2026-07-05T03:00:43.357794Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:00:43.357794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DytlsND7WHhf/v1CKBjVvxf8ru6dkej11VhxFuU9l6biCM/5nm0fjIGuhbfXbs+JWAlB+24Qmf2xsDyRKxvIBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:00:43.358252Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.05535","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:06487e9aaaa6c680f22ef2b61d273787018d7f22c29a3be3c1b672513e68b02a","sha256:02c296c228e57770f892d1b64d7421393e26f34966c5fcc916ebf800a6ad9511"],"state_sha256":"cdde7c6c77fd4f182213f9d36e3da1db7828f6aac23936ef52a83b07d7840f04"}