{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:BNAPW2HESHXI5NGA2C7V74XPK3","short_pith_number":"pith:BNAPW2HE","canonical_record":{"source":{"id":"1703.05908","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-17T06:59:51Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"b70045d17b1e12b2cfb339d8dcc3f0dac125e9b0ee0019f695431544309a2a9f","abstract_canon_sha256":"e1a70d850c40e13f5117cb8e369325cb67e28b3a4e056dea700167c4882ab25c"},"schema_version":"1.0"},"canonical_sha256":"0b40fb68e491ee8eb4c0d0bf5ff2ef56cbfd219c2c3ccebde00cc0bcb64dd44e","source":{"kind":"arxiv","id":"1703.05908","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.05908","created_at":"2026-05-18T00:48:25Z"},{"alias_kind":"arxiv_version","alias_value":"1703.05908v2","created_at":"2026-05-18T00:48:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.05908","created_at":"2026-05-18T00:48:25Z"},{"alias_kind":"pith_short_12","alias_value":"BNAPW2HESHXI","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BNAPW2HESHXI5NGA","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BNAPW2HE","created_at":"2026-05-18T12:31:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:BNAPW2HESHXI5NGA2C7V74XPK3","target":"record","payload":{"canonical_record":{"source":{"id":"1703.05908","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-17T06:59:51Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"b70045d17b1e12b2cfb339d8dcc3f0dac125e9b0ee0019f695431544309a2a9f","abstract_canon_sha256":"e1a70d850c40e13f5117cb8e369325cb67e28b3a4e056dea700167c4882ab25c"},"schema_version":"1.0"},"canonical_sha256":"0b40fb68e491ee8eb4c0d0bf5ff2ef56cbfd219c2c3ccebde00cc0bcb64dd44e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:25.611483Z","signature_b64":"ed/ScAy/m0+eGjYsPpcKDHAMjW9TuWQbHAVVaEah7d2si/H0ykysA+Sng269WVGxGRy7fNtolMlRPNyXTu+oDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b40fb68e491ee8eb4c0d0bf5ff2ef56cbfd219c2c3ccebde00cc0bcb64dd44e","last_reissued_at":"2026-05-18T00:48:25.611031Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:25.611031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.05908","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":"2026-05-18T00:48:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Srq8Ov+yg6n1nMMoZSMK5gYgUwPXhTNDZk1JuaAJ90fl30f3LVLbXu/CZ7Re8KYnZ4G63RXrz396F/NbdAOOCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:45:57.430894Z"},"content_sha256":"cc05234227b1388afaf42a329a67fa967af73c3c4565ba301318307e3a6278e3","schema_version":"1.0","event_id":"sha256:cc05234227b1388afaf42a329a67fa967af73c3c4565ba301318307e3a6278e3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:BNAPW2HESHXI5NGA2C7V74XPK3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Robust Visual-Semantic Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Liang-Kang Huang, Ruslan Salakhutdinov, Yao-Hung Hubert Tsai","submitted_at":"2017-03-17T06:59:51Z","abstract_excerpt":"Many of the existing methods for learning joint embedding of images and text use only supervised information from paired images and its textual attributes. Taking advantage of the recent success of unsupervised learning in deep neural networks, we propose an end-to-end learning framework that is able to extract more robust multi-modal representations across domains. The proposed method combines representation learning models (i.e., auto-encoders) together with cross-domain learning criteria (i.e., Maximum Mean Discrepancy loss) to learn joint embeddings for semantic and visual features. A nove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.05908","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":"2026-05-18T00:48:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+qiBCr/6Zqb9E/UDF5/JEY5DSwi43Pdk5M+2em1lIf8YdFYcZA2a1kBcduNLg7M3OdCoDDHJojacM4nkeLiZBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:45:57.431587Z"},"content_sha256":"cc4a4162fa70f30264996289337a9a609fe671e17c03bef4cb303300c515d82f","schema_version":"1.0","event_id":"sha256:cc4a4162fa70f30264996289337a9a609fe671e17c03bef4cb303300c515d82f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BNAPW2HESHXI5NGA2C7V74XPK3/bundle.json","state_url":"https://pith.science/pith/BNAPW2HESHXI5NGA2C7V74XPK3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BNAPW2HESHXI5NGA2C7V74XPK3/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":"2026-05-27T14:45:57Z","links":{"resolver":"https://pith.science/pith/BNAPW2HESHXI5NGA2C7V74XPK3","bundle":"https://pith.science/pith/BNAPW2HESHXI5NGA2C7V74XPK3/bundle.json","state":"https://pith.science/pith/BNAPW2HESHXI5NGA2C7V74XPK3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BNAPW2HESHXI5NGA2C7V74XPK3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:BNAPW2HESHXI5NGA2C7V74XPK3","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":"e1a70d850c40e13f5117cb8e369325cb67e28b3a4e056dea700167c4882ab25c","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-17T06:59:51Z","title_canon_sha256":"b70045d17b1e12b2cfb339d8dcc3f0dac125e9b0ee0019f695431544309a2a9f"},"schema_version":"1.0","source":{"id":"1703.05908","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.05908","created_at":"2026-05-18T00:48:25Z"},{"alias_kind":"arxiv_version","alias_value":"1703.05908v2","created_at":"2026-05-18T00:48:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.05908","created_at":"2026-05-18T00:48:25Z"},{"alias_kind":"pith_short_12","alias_value":"BNAPW2HESHXI","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BNAPW2HESHXI5NGA","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BNAPW2HE","created_at":"2026-05-18T12:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:cc4a4162fa70f30264996289337a9a609fe671e17c03bef4cb303300c515d82f","target":"graph","created_at":"2026-05-18T00:48:25Z","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":"Many of the existing methods for learning joint embedding of images and text use only supervised information from paired images and its textual attributes. Taking advantage of the recent success of unsupervised learning in deep neural networks, we propose an end-to-end learning framework that is able to extract more robust multi-modal representations across domains. The proposed method combines representation learning models (i.e., auto-encoders) together with cross-domain learning criteria (i.e., Maximum Mean Discrepancy loss) to learn joint embeddings for semantic and visual features. A nove","authors_text":"Liang-Kang Huang, Ruslan Salakhutdinov, Yao-Hung Hubert Tsai","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-17T06:59:51Z","title":"Learning Robust Visual-Semantic Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.05908","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:cc05234227b1388afaf42a329a67fa967af73c3c4565ba301318307e3a6278e3","target":"record","created_at":"2026-05-18T00:48:25Z","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":"e1a70d850c40e13f5117cb8e369325cb67e28b3a4e056dea700167c4882ab25c","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-17T06:59:51Z","title_canon_sha256":"b70045d17b1e12b2cfb339d8dcc3f0dac125e9b0ee0019f695431544309a2a9f"},"schema_version":"1.0","source":{"id":"1703.05908","kind":"arxiv","version":2}},"canonical_sha256":"0b40fb68e491ee8eb4c0d0bf5ff2ef56cbfd219c2c3ccebde00cc0bcb64dd44e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b40fb68e491ee8eb4c0d0bf5ff2ef56cbfd219c2c3ccebde00cc0bcb64dd44e","first_computed_at":"2026-05-18T00:48:25.611031Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:48:25.611031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ed/ScAy/m0+eGjYsPpcKDHAMjW9TuWQbHAVVaEah7d2si/H0ykysA+Sng269WVGxGRy7fNtolMlRPNyXTu+oDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:48:25.611483Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.05908","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc05234227b1388afaf42a329a67fa967af73c3c4565ba301318307e3a6278e3","sha256:cc4a4162fa70f30264996289337a9a609fe671e17c03bef4cb303300c515d82f"],"state_sha256":"652c27b67d46f9d77b433b9af2d93291eb4649689111e78ced80f95149232940"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZjwJd+QmTQQqx1TS5tomBv9CW+CcxIlY6qJFqr8bB7FFEMQuVUCfXXAVEMiXuBHWCQ32dBzbGIr4WuQRfnm9Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T14:45:57.435178Z","bundle_sha256":"59569dd2da2e3c7aad14e609989cf0a7d51d95d857aa5f5a16bad533807c86e4"}}