{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:6O3OGO2F74ZRQQBN63X3LG3FN4","short_pith_number":"pith:6O3OGO2F","canonical_record":{"source":{"id":"1504.03083","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-04-13T07:36:08Z","cross_cats_sorted":[],"title_canon_sha256":"605ab6fe68daa0dce8a5a2e31ba8b3d87bc9324f28999fb7484da42ef7a633d3","abstract_canon_sha256":"6f40e69af00ab8082c56a49dd4bf682d3f0173f5e6fe2c6217f7e136db9552a3"},"schema_version":"1.0"},"canonical_sha256":"f3b6e33b45ff3318402df6efb59b656f25b18fc2be9b6fe9eb5a9ee1f68d8299","source":{"kind":"arxiv","id":"1504.03083","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1504.03083","created_at":"2026-05-18T02:17:35Z"},{"alias_kind":"arxiv_version","alias_value":"1504.03083v2","created_at":"2026-05-18T02:17:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1504.03083","created_at":"2026-05-18T02:17:35Z"},{"alias_kind":"pith_short_12","alias_value":"6O3OGO2F74ZR","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_16","alias_value":"6O3OGO2F74ZRQQBN","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_8","alias_value":"6O3OGO2F","created_at":"2026-05-18T12:29:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:6O3OGO2F74ZRQQBN63X3LG3FN4","target":"record","payload":{"canonical_record":{"source":{"id":"1504.03083","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-04-13T07:36:08Z","cross_cats_sorted":[],"title_canon_sha256":"605ab6fe68daa0dce8a5a2e31ba8b3d87bc9324f28999fb7484da42ef7a633d3","abstract_canon_sha256":"6f40e69af00ab8082c56a49dd4bf682d3f0173f5e6fe2c6217f7e136db9552a3"},"schema_version":"1.0"},"canonical_sha256":"f3b6e33b45ff3318402df6efb59b656f25b18fc2be9b6fe9eb5a9ee1f68d8299","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:17:35.520296Z","signature_b64":"/yp5RVq4sscP1mbOW6JEfCNtMsocznXLOOsIIENtM2T1RWiaUdezYnd2aMMxJaXmEG02S6hXE9E9fSbN+qs4Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3b6e33b45ff3318402df6efb59b656f25b18fc2be9b6fe9eb5a9ee1f68d8299","last_reissued_at":"2026-05-18T02:17:35.519571Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:17:35.519571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1504.03083","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":"2026-05-18T02:17:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IjtYNh2X8+robz568mPRr5BcE8Gtx3Z4q1FWCLC5JK1V+OrWhb926hoioCPLD5YUzyEIZDxUap0ZVhq9zBpmCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T02:38:29.155392Z"},"content_sha256":"20e09181b646f162f5e8350364452a7764ab323328bd19cdea8191f777812918","schema_version":"1.0","event_id":"sha256:20e09181b646f162f5e8350364452a7764ab323328bd19cdea8191f777812918"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:6O3OGO2F74ZRQQBN63X3LG3FN4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Joint Learning of Distributed Representations for Images and Texts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianfeng Gao, Li Deng, Rupesh Srivastava, Xiaodong He","submitted_at":"2015-04-13T07:36:08Z","abstract_excerpt":"This technical report provides extra details of the deep multimodal similarity model (DMSM) which was proposed in (Fang et al. 2015, arXiv:1411.4952). The model is trained via maximizing global semantic similarity between images and their captions in natural language using the public Microsoft COCO database, which consists of a large set of images and their corresponding captions. The learned representations attempt to capture the combination of various visual concepts and cues."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1504.03083","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":"2026-05-18T02:17:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6EoY0zzQ4ZruU3zHr3ENph8MGWuxOVOHnvPkrZwWuQnFQJKhGoVhYB7TUTh7nlYQphOTpE/cdHj9Z+Gu2P9EAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T02:38:29.156050Z"},"content_sha256":"8edfab16081c37b8743abda48727385893117289b77add390849ac11fe1d9655","schema_version":"1.0","event_id":"sha256:8edfab16081c37b8743abda48727385893117289b77add390849ac11fe1d9655"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6O3OGO2F74ZRQQBN63X3LG3FN4/bundle.json","state_url":"https://pith.science/pith/6O3OGO2F74ZRQQBN63X3LG3FN4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6O3OGO2F74ZRQQBN63X3LG3FN4/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":"2026-06-05T02:38:29Z","links":{"resolver":"https://pith.science/pith/6O3OGO2F74ZRQQBN63X3LG3FN4","bundle":"https://pith.science/pith/6O3OGO2F74ZRQQBN63X3LG3FN4/bundle.json","state":"https://pith.science/pith/6O3OGO2F74ZRQQBN63X3LG3FN4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6O3OGO2F74ZRQQBN63X3LG3FN4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:6O3OGO2F74ZRQQBN63X3LG3FN4","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":"6f40e69af00ab8082c56a49dd4bf682d3f0173f5e6fe2c6217f7e136db9552a3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-04-13T07:36:08Z","title_canon_sha256":"605ab6fe68daa0dce8a5a2e31ba8b3d87bc9324f28999fb7484da42ef7a633d3"},"schema_version":"1.0","source":{"id":"1504.03083","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1504.03083","created_at":"2026-05-18T02:17:35Z"},{"alias_kind":"arxiv_version","alias_value":"1504.03083v2","created_at":"2026-05-18T02:17:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1504.03083","created_at":"2026-05-18T02:17:35Z"},{"alias_kind":"pith_short_12","alias_value":"6O3OGO2F74ZR","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_16","alias_value":"6O3OGO2F74ZRQQBN","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_8","alias_value":"6O3OGO2F","created_at":"2026-05-18T12:29:07Z"}],"graph_snapshots":[{"event_id":"sha256:8edfab16081c37b8743abda48727385893117289b77add390849ac11fe1d9655","target":"graph","created_at":"2026-05-18T02:17:35Z","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":"This technical report provides extra details of the deep multimodal similarity model (DMSM) which was proposed in (Fang et al. 2015, arXiv:1411.4952). The model is trained via maximizing global semantic similarity between images and their captions in natural language using the public Microsoft COCO database, which consists of a large set of images and their corresponding captions. The learned representations attempt to capture the combination of various visual concepts and cues.","authors_text":"Jianfeng Gao, Li Deng, Rupesh Srivastava, Xiaodong He","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-04-13T07:36:08Z","title":"Joint Learning of Distributed Representations for Images and Texts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1504.03083","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":"sha256:20e09181b646f162f5e8350364452a7764ab323328bd19cdea8191f777812918","target":"record","created_at":"2026-05-18T02:17:35Z","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":"6f40e69af00ab8082c56a49dd4bf682d3f0173f5e6fe2c6217f7e136db9552a3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-04-13T07:36:08Z","title_canon_sha256":"605ab6fe68daa0dce8a5a2e31ba8b3d87bc9324f28999fb7484da42ef7a633d3"},"schema_version":"1.0","source":{"id":"1504.03083","kind":"arxiv","version":2}},"canonical_sha256":"f3b6e33b45ff3318402df6efb59b656f25b18fc2be9b6fe9eb5a9ee1f68d8299","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f3b6e33b45ff3318402df6efb59b656f25b18fc2be9b6fe9eb5a9ee1f68d8299","first_computed_at":"2026-05-18T02:17:35.519571Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:17:35.519571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/yp5RVq4sscP1mbOW6JEfCNtMsocznXLOOsIIENtM2T1RWiaUdezYnd2aMMxJaXmEG02S6hXE9E9fSbN+qs4Dw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:17:35.520296Z","signed_message":"canonical_sha256_bytes"},"source_id":"1504.03083","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20e09181b646f162f5e8350364452a7764ab323328bd19cdea8191f777812918","sha256:8edfab16081c37b8743abda48727385893117289b77add390849ac11fe1d9655"],"state_sha256":"6c045a080e8a25399dba9e5d056620442d9e20b38adb29b72b0a92f184320457"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tI0BSrHLPzdElsYbJX9cwAnEwEcESe4chO5c5CisovoX3F5eE+eYAoOHtlczBTUdGv/NdN7f/oDaMHiuyRpzAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T02:38:29.159286Z","bundle_sha256":"ac3d25aba1c515aeb8f1d5e595222cf122646554c0314b82fc031c144208b181"}}