{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:2F76QRCNNOR5TOAA46TAYU2HQF","short_pith_number":"pith:2F76QRCN","canonical_record":{"source":{"id":"1905.13339","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2019-05-30T22:33:15Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"39264cdca53deb8f964c428adb002bd9891b1266bc80f80b16e1469a4f2467df","abstract_canon_sha256":"2e0bb97828af18fb5c2f9d8db17e9067f70c87e6a34518ec6b25ca7a394b5175"},"schema_version":"1.0"},"canonical_sha256":"d17fe8444d6ba3d9b800e7a60c53478170a58d21321e178751724fccfd35d6d4","source":{"kind":"arxiv","id":"1905.13339","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.13339","created_at":"2026-05-17T23:44:35Z"},{"alias_kind":"arxiv_version","alias_value":"1905.13339v1","created_at":"2026-05-17T23:44:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13339","created_at":"2026-05-17T23:44:35Z"},{"alias_kind":"pith_short_12","alias_value":"2F76QRCNNOR5","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"2F76QRCNNOR5TOAA","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"2F76QRCN","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:2F76QRCNNOR5TOAA46TAYU2HQF","target":"record","payload":{"canonical_record":{"source":{"id":"1905.13339","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2019-05-30T22:33:15Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"39264cdca53deb8f964c428adb002bd9891b1266bc80f80b16e1469a4f2467df","abstract_canon_sha256":"2e0bb97828af18fb5c2f9d8db17e9067f70c87e6a34518ec6b25ca7a394b5175"},"schema_version":"1.0"},"canonical_sha256":"d17fe8444d6ba3d9b800e7a60c53478170a58d21321e178751724fccfd35d6d4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:35.251645Z","signature_b64":"WnUfK5DcdroUpQak6wRU0QzmEFrETbl/ZbuRr/bLW92HTQRMkqaFEry3IhfRYfMLnDh5gFZgBqMr/p22RgaNAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d17fe8444d6ba3d9b800e7a60c53478170a58d21321e178751724fccfd35d6d4","last_reissued_at":"2026-05-17T23:44:35.251179Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:35.251179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.13339","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":"2026-05-17T23:44:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BM62LNsJkuIK5wp8+hc9CrD7z+V3Iy1ETEYhpwlTMSwp6QGrVvGYRHmELAOwU1eyu/8eCz/H+WER7KR0C/YDDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T06:31:27.234909Z"},"content_sha256":"5997d1b28df78a95978c9b96510432aecace5458d69de4c7e0b6de38026baa26","schema_version":"1.0","event_id":"sha256:5997d1b28df78a95978c9b96510432aecace5458d69de4c7e0b6de38026baa26"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:2F76QRCNNOR5TOAA46TAYU2HQF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multitask Text-to-Visual Embedding with Titles and Clickthrough Data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CV","authors_text":"Baldo Faieta, Pranav Aggarwal, Saeid Motiian, Zhe Lin","submitted_at":"2019-05-30T22:33:15Z","abstract_excerpt":"Text-visual (or called semantic-visual) embedding is a central problem in vision-language research. It typically involves mapping of an image and a text description to a common feature space through a CNN image encoder and a RNN language encoder. In this paper, we propose a new method for learning text-visual embedding using both image titles and click-through data from an image search engine. We also propose a new triplet loss function by modeling positive awareness of the embedding, and introduce a novel mini-batch-based hard negative sampling approach for better data efficiency in the learn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13339","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":"2026-05-17T23:44:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fvuMthkfnHL6DTfW3FP5IWTCD0rblL8HBVkZN4TISdycDaCf2Kf4Tf8RJoiWpI0GarSZFYKSRT2Myl8ECI0vCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T06:31:27.235646Z"},"content_sha256":"4eb86026aff26fa79ff78cc2ebf57666fcfc43d3602b6d51e7f39e7048cb5c02","schema_version":"1.0","event_id":"sha256:4eb86026aff26fa79ff78cc2ebf57666fcfc43d3602b6d51e7f39e7048cb5c02"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2F76QRCNNOR5TOAA46TAYU2HQF/bundle.json","state_url":"https://pith.science/pith/2F76QRCNNOR5TOAA46TAYU2HQF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2F76QRCNNOR5TOAA46TAYU2HQF/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":"2026-06-08T06:31:27Z","links":{"resolver":"https://pith.science/pith/2F76QRCNNOR5TOAA46TAYU2HQF","bundle":"https://pith.science/pith/2F76QRCNNOR5TOAA46TAYU2HQF/bundle.json","state":"https://pith.science/pith/2F76QRCNNOR5TOAA46TAYU2HQF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2F76QRCNNOR5TOAA46TAYU2HQF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:2F76QRCNNOR5TOAA46TAYU2HQF","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":"2e0bb97828af18fb5c2f9d8db17e9067f70c87e6a34518ec6b25ca7a394b5175","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2019-05-30T22:33:15Z","title_canon_sha256":"39264cdca53deb8f964c428adb002bd9891b1266bc80f80b16e1469a4f2467df"},"schema_version":"1.0","source":{"id":"1905.13339","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.13339","created_at":"2026-05-17T23:44:35Z"},{"alias_kind":"arxiv_version","alias_value":"1905.13339v1","created_at":"2026-05-17T23:44:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13339","created_at":"2026-05-17T23:44:35Z"},{"alias_kind":"pith_short_12","alias_value":"2F76QRCNNOR5","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"2F76QRCNNOR5TOAA","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"2F76QRCN","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:4eb86026aff26fa79ff78cc2ebf57666fcfc43d3602b6d51e7f39e7048cb5c02","target":"graph","created_at":"2026-05-17T23:44:35Z","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":"Text-visual (or called semantic-visual) embedding is a central problem in vision-language research. It typically involves mapping of an image and a text description to a common feature space through a CNN image encoder and a RNN language encoder. In this paper, we propose a new method for learning text-visual embedding using both image titles and click-through data from an image search engine. We also propose a new triplet loss function by modeling positive awareness of the embedding, and introduce a novel mini-batch-based hard negative sampling approach for better data efficiency in the learn","authors_text":"Baldo Faieta, Pranav Aggarwal, Saeid Motiian, Zhe Lin","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2019-05-30T22:33:15Z","title":"Multitask Text-to-Visual Embedding with Titles and Clickthrough Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13339","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":"sha256:5997d1b28df78a95978c9b96510432aecace5458d69de4c7e0b6de38026baa26","target":"record","created_at":"2026-05-17T23:44:35Z","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":"2e0bb97828af18fb5c2f9d8db17e9067f70c87e6a34518ec6b25ca7a394b5175","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2019-05-30T22:33:15Z","title_canon_sha256":"39264cdca53deb8f964c428adb002bd9891b1266bc80f80b16e1469a4f2467df"},"schema_version":"1.0","source":{"id":"1905.13339","kind":"arxiv","version":1}},"canonical_sha256":"d17fe8444d6ba3d9b800e7a60c53478170a58d21321e178751724fccfd35d6d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d17fe8444d6ba3d9b800e7a60c53478170a58d21321e178751724fccfd35d6d4","first_computed_at":"2026-05-17T23:44:35.251179Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:35.251179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WnUfK5DcdroUpQak6wRU0QzmEFrETbl/ZbuRr/bLW92HTQRMkqaFEry3IhfRYfMLnDh5gFZgBqMr/p22RgaNAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:35.251645Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.13339","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5997d1b28df78a95978c9b96510432aecace5458d69de4c7e0b6de38026baa26","sha256:4eb86026aff26fa79ff78cc2ebf57666fcfc43d3602b6d51e7f39e7048cb5c02"],"state_sha256":"c3236c5db7e28df3c2dfe19d42c467d43544d461d568683034da537495fc69f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PHtqGXdQBQHVgqGvLqgAc0ic7t+PlFvXpOoFCyWSzfal/a7O1NQGK09ulU/vvULQc8/j9aMOSXZB/xCesoKjBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T06:31:27.239842Z","bundle_sha256":"63fbb0634e936fac7f18ac2f0d5ee0fc480f224a0bc93bca1a15dbd9c1e2d823"}}