{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:TGU3F4DJJIKKBPYUTQBJWZEENN","short_pith_number":"pith:TGU3F4DJ","canonical_record":{"source":{"id":"1811.00357","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-01T13:19:27Z","cross_cats_sorted":[],"title_canon_sha256":"1af3973fa61227078536cee1efb9760af6de02f7cb6718bccddc78b5f6b5ae1e","abstract_canon_sha256":"8920a32d01480dbef52b701203b5e3fe81698d0c21ce0e51f57fe7f51f2aeab8"},"schema_version":"1.0"},"canonical_sha256":"99a9b2f0694a14a0bf149c029b64846b76d9b6a614e05b4c25523d0c751faf26","source":{"kind":"arxiv","id":"1811.00357","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.00357","created_at":"2026-05-17T23:46:03Z"},{"alias_kind":"arxiv_version","alias_value":"1811.00357v2","created_at":"2026-05-17T23:46:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00357","created_at":"2026-05-17T23:46:03Z"},{"alias_kind":"pith_short_12","alias_value":"TGU3F4DJJIKK","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"TGU3F4DJJIKKBPYU","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"TGU3F4DJ","created_at":"2026-05-18T12:32:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:TGU3F4DJJIKKBPYUTQBJWZEENN","target":"record","payload":{"canonical_record":{"source":{"id":"1811.00357","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-01T13:19:27Z","cross_cats_sorted":[],"title_canon_sha256":"1af3973fa61227078536cee1efb9760af6de02f7cb6718bccddc78b5f6b5ae1e","abstract_canon_sha256":"8920a32d01480dbef52b701203b5e3fe81698d0c21ce0e51f57fe7f51f2aeab8"},"schema_version":"1.0"},"canonical_sha256":"99a9b2f0694a14a0bf149c029b64846b76d9b6a614e05b4c25523d0c751faf26","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:03.873392Z","signature_b64":"HPLI8bttbFVfErskPP6FlVZRK2ykpeG0zvn4lkMDHVqrbZYGE40b8QL3s3fsNJQ2jIC00WQ4IJSpDtwbqeQGCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99a9b2f0694a14a0bf149c029b64846b76d9b6a614e05b4c25523d0c751faf26","last_reissued_at":"2026-05-17T23:46:03.872748Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:03.872748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.00357","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":"2026-05-17T23:46:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tLupR7Jd5rq3fsHbRCgWbMCL7pb5ebytqUhiaJ6jXA5Ah7379mN8AwZlLy38Kw7NRenxy9FrYmjVZXt5KvoOAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T19:58:12.317759Z"},"content_sha256":"41a0c3e92a5ae9b7f7b1b1ae5663addc4c71096ba34207b04e6a9456caeeeb54","schema_version":"1.0","event_id":"sha256:41a0c3e92a5ae9b7f7b1b1ae5663addc4c71096ba34207b04e6a9456caeeeb54"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:TGU3F4DJJIKKBPYUTQBJWZEENN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Latent Variable Model for Multi-modal Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Iacer Calixto, Miguel Rios, Wilker Aziz","submitted_at":"2018-11-01T13:19:27Z","abstract_excerpt":"In this work, we propose to model the interaction between visual and textual features for multi-modal neural machine translation (MMT) through a latent variable model. This latent variable can be seen as a multi-modal stochastic embedding of an image and its description in a foreign language. It is used in a target-language decoder and also to predict image features. Importantly, our model formulation utilises visual and textual inputs during training but does not require that images be available at test time. We show that our latent variable MMT formulation improves considerably over strong b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00357","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":"2026-05-17T23:46:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RC6gScpxSB/+KQQZ0RQb0UrqY3QxT7FObFxqc9tIA8+M9uUVbb547JKC6nmdkLv7RKE3LQlYGKtazkiQkwAuAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T19:58:12.318449Z"},"content_sha256":"0b8e9bb10c88781d257c44fa1b8a2edd05594df63c88d048a5a218fe2f33aba2","schema_version":"1.0","event_id":"sha256:0b8e9bb10c88781d257c44fa1b8a2edd05594df63c88d048a5a218fe2f33aba2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TGU3F4DJJIKKBPYUTQBJWZEENN/bundle.json","state_url":"https://pith.science/pith/TGU3F4DJJIKKBPYUTQBJWZEENN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TGU3F4DJJIKKBPYUTQBJWZEENN/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":"2026-06-06T19:58:12Z","links":{"resolver":"https://pith.science/pith/TGU3F4DJJIKKBPYUTQBJWZEENN","bundle":"https://pith.science/pith/TGU3F4DJJIKKBPYUTQBJWZEENN/bundle.json","state":"https://pith.science/pith/TGU3F4DJJIKKBPYUTQBJWZEENN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TGU3F4DJJIKKBPYUTQBJWZEENN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:TGU3F4DJJIKKBPYUTQBJWZEENN","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":"8920a32d01480dbef52b701203b5e3fe81698d0c21ce0e51f57fe7f51f2aeab8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-01T13:19:27Z","title_canon_sha256":"1af3973fa61227078536cee1efb9760af6de02f7cb6718bccddc78b5f6b5ae1e"},"schema_version":"1.0","source":{"id":"1811.00357","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.00357","created_at":"2026-05-17T23:46:03Z"},{"alias_kind":"arxiv_version","alias_value":"1811.00357v2","created_at":"2026-05-17T23:46:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00357","created_at":"2026-05-17T23:46:03Z"},{"alias_kind":"pith_short_12","alias_value":"TGU3F4DJJIKK","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"TGU3F4DJJIKKBPYU","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"TGU3F4DJ","created_at":"2026-05-18T12:32:53Z"}],"graph_snapshots":[{"event_id":"sha256:0b8e9bb10c88781d257c44fa1b8a2edd05594df63c88d048a5a218fe2f33aba2","target":"graph","created_at":"2026-05-17T23:46:03Z","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":"In this work, we propose to model the interaction between visual and textual features for multi-modal neural machine translation (MMT) through a latent variable model. This latent variable can be seen as a multi-modal stochastic embedding of an image and its description in a foreign language. It is used in a target-language decoder and also to predict image features. Importantly, our model formulation utilises visual and textual inputs during training but does not require that images be available at test time. We show that our latent variable MMT formulation improves considerably over strong b","authors_text":"Iacer Calixto, Miguel Rios, Wilker Aziz","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-01T13:19:27Z","title":"Latent Variable Model for Multi-modal Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00357","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":"sha256:41a0c3e92a5ae9b7f7b1b1ae5663addc4c71096ba34207b04e6a9456caeeeb54","target":"record","created_at":"2026-05-17T23:46:03Z","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":"8920a32d01480dbef52b701203b5e3fe81698d0c21ce0e51f57fe7f51f2aeab8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-01T13:19:27Z","title_canon_sha256":"1af3973fa61227078536cee1efb9760af6de02f7cb6718bccddc78b5f6b5ae1e"},"schema_version":"1.0","source":{"id":"1811.00357","kind":"arxiv","version":2}},"canonical_sha256":"99a9b2f0694a14a0bf149c029b64846b76d9b6a614e05b4c25523d0c751faf26","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"99a9b2f0694a14a0bf149c029b64846b76d9b6a614e05b4c25523d0c751faf26","first_computed_at":"2026-05-17T23:46:03.872748Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:03.872748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HPLI8bttbFVfErskPP6FlVZRK2ykpeG0zvn4lkMDHVqrbZYGE40b8QL3s3fsNJQ2jIC00WQ4IJSpDtwbqeQGCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:03.873392Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.00357","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41a0c3e92a5ae9b7f7b1b1ae5663addc4c71096ba34207b04e6a9456caeeeb54","sha256:0b8e9bb10c88781d257c44fa1b8a2edd05594df63c88d048a5a218fe2f33aba2"],"state_sha256":"48881e4137cf8105f57ba22c012d44b6c9ca9db2165c57a9c2c81dcf01fa4bb2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Esg+Q/ZifD7lxxz7WRdD27SiOgRQB4jNuis86dEl0KqRqWRVFrI6s/tnepS5B/qepZFOV23iS7Y6Eot80+d1Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T19:58:12.322047Z","bundle_sha256":"a42451031f25a2662df8ef8c4d369b8698753062258ec60e98ec2099aaae5442"}}