{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:STW3IDBTLPEPC6XT647L4645L5","short_pith_number":"pith:STW3IDBT","canonical_record":{"source":{"id":"1712.03449","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-12-09T23:17:22Z","cross_cats_sorted":[],"title_canon_sha256":"408040a0a1c27bf49cc5ddbb143ebab8ee939080129f248018cfb92058c2c092","abstract_canon_sha256":"11fc07eb1acebb50f1f0a62ee68a9f3c54d51ecfdac3026988a065e9ce8b48df"},"schema_version":"1.0"},"canonical_sha256":"94edb40c335bc8f17af3f73ebe7b9d5f4da2ac9a1fb16d2cfd9c9098c6d8bc16","source":{"kind":"arxiv","id":"1712.03449","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.03449","created_at":"2026-05-18T00:14:34Z"},{"alias_kind":"arxiv_version","alias_value":"1712.03449v1","created_at":"2026-05-18T00:14:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.03449","created_at":"2026-05-18T00:14:34Z"},{"alias_kind":"pith_short_12","alias_value":"STW3IDBTLPEP","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"STW3IDBTLPEPC6XT","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"STW3IDBT","created_at":"2026-05-18T12:31:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:STW3IDBTLPEPC6XT647L4645L5","target":"record","payload":{"canonical_record":{"source":{"id":"1712.03449","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-12-09T23:17:22Z","cross_cats_sorted":[],"title_canon_sha256":"408040a0a1c27bf49cc5ddbb143ebab8ee939080129f248018cfb92058c2c092","abstract_canon_sha256":"11fc07eb1acebb50f1f0a62ee68a9f3c54d51ecfdac3026988a065e9ce8b48df"},"schema_version":"1.0"},"canonical_sha256":"94edb40c335bc8f17af3f73ebe7b9d5f4da2ac9a1fb16d2cfd9c9098c6d8bc16","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:34.245166Z","signature_b64":"2a78kj7fPH9gep3dozneDaEpF5TEW7ugeU4LG03UHqMIA0B704trSQtXz17SjzziwJMAOKtitxMBjv2WAyxHDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94edb40c335bc8f17af3f73ebe7b9d5f4da2ac9a1fb16d2cfd9c9098c6d8bc16","last_reissued_at":"2026-05-18T00:14:34.244582Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:34.244582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.03449","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":"2026-05-18T00:14:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mcgvHlpNmIpuMphmTlmDb1wr2tvgaBXvxIQ3+xvWgT9hiCG9U6uva7X1EWRRByva10/LawkKGmhm3A3CgUByCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T14:09:43.611647Z"},"content_sha256":"581ad5a266905c6aadcec586e9507725d558c29c4173d6dda4f031224f31d9c9","schema_version":"1.0","event_id":"sha256:581ad5a266905c6aadcec586e9507725d558c29c4173d6dda4f031224f31d9c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:STW3IDBTLPEPC6XT647L4645L5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Modulating and attending the source image during encoding improves Multimodal Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jean-Benoit Delbrouck, St\\'ephane Dupont","submitted_at":"2017-12-09T23:17:22Z","abstract_excerpt":"We propose a new and fully end-to-end approach for multimodal translation where the source text encoder modulates the entire visual input processing using conditional batch normalization, in order to compute the most informative image features for our task. Additionally, we propose a new attention mechanism derived from this original idea, where the attention model for the visual input is conditioned on the source text encoder representations. In the paper, we detail our models as well as the image analysis pipeline. Finally, we report experimental results. They are, as far as we know, the new"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.03449","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":"2026-05-18T00:14:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gG/tE7gN9WxrmzmtvcYf0qwhkXbE06j0ONjN2JFOZ5DAwWNv6OjBBqyTkDG7vgT22WRalg6RWOFCJ+mO/I/jAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T14:09:43.611978Z"},"content_sha256":"112113c6588fcb3284a0dca7d8dfcc90cb5ae55f68a9dbb6c43664312a6e6937","schema_version":"1.0","event_id":"sha256:112113c6588fcb3284a0dca7d8dfcc90cb5ae55f68a9dbb6c43664312a6e6937"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/STW3IDBTLPEPC6XT647L4645L5/bundle.json","state_url":"https://pith.science/pith/STW3IDBTLPEPC6XT647L4645L5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/STW3IDBTLPEPC6XT647L4645L5/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":"2026-05-28T14:09:43Z","links":{"resolver":"https://pith.science/pith/STW3IDBTLPEPC6XT647L4645L5","bundle":"https://pith.science/pith/STW3IDBTLPEPC6XT647L4645L5/bundle.json","state":"https://pith.science/pith/STW3IDBTLPEPC6XT647L4645L5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/STW3IDBTLPEPC6XT647L4645L5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:STW3IDBTLPEPC6XT647L4645L5","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":"11fc07eb1acebb50f1f0a62ee68a9f3c54d51ecfdac3026988a065e9ce8b48df","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-12-09T23:17:22Z","title_canon_sha256":"408040a0a1c27bf49cc5ddbb143ebab8ee939080129f248018cfb92058c2c092"},"schema_version":"1.0","source":{"id":"1712.03449","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.03449","created_at":"2026-05-18T00:14:34Z"},{"alias_kind":"arxiv_version","alias_value":"1712.03449v1","created_at":"2026-05-18T00:14:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.03449","created_at":"2026-05-18T00:14:34Z"},{"alias_kind":"pith_short_12","alias_value":"STW3IDBTLPEP","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"STW3IDBTLPEPC6XT","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"STW3IDBT","created_at":"2026-05-18T12:31:43Z"}],"graph_snapshots":[{"event_id":"sha256:112113c6588fcb3284a0dca7d8dfcc90cb5ae55f68a9dbb6c43664312a6e6937","target":"graph","created_at":"2026-05-18T00:14:34Z","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":"We propose a new and fully end-to-end approach for multimodal translation where the source text encoder modulates the entire visual input processing using conditional batch normalization, in order to compute the most informative image features for our task. Additionally, we propose a new attention mechanism derived from this original idea, where the attention model for the visual input is conditioned on the source text encoder representations. In the paper, we detail our models as well as the image analysis pipeline. Finally, we report experimental results. They are, as far as we know, the new","authors_text":"Jean-Benoit Delbrouck, St\\'ephane Dupont","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-12-09T23:17:22Z","title":"Modulating and attending the source image during encoding improves Multimodal Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.03449","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":"sha256:581ad5a266905c6aadcec586e9507725d558c29c4173d6dda4f031224f31d9c9","target":"record","created_at":"2026-05-18T00:14:34Z","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":"11fc07eb1acebb50f1f0a62ee68a9f3c54d51ecfdac3026988a065e9ce8b48df","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-12-09T23:17:22Z","title_canon_sha256":"408040a0a1c27bf49cc5ddbb143ebab8ee939080129f248018cfb92058c2c092"},"schema_version":"1.0","source":{"id":"1712.03449","kind":"arxiv","version":1}},"canonical_sha256":"94edb40c335bc8f17af3f73ebe7b9d5f4da2ac9a1fb16d2cfd9c9098c6d8bc16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94edb40c335bc8f17af3f73ebe7b9d5f4da2ac9a1fb16d2cfd9c9098c6d8bc16","first_computed_at":"2026-05-18T00:14:34.244582Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:34.244582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2a78kj7fPH9gep3dozneDaEpF5TEW7ugeU4LG03UHqMIA0B704trSQtXz17SjzziwJMAOKtitxMBjv2WAyxHDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:34.245166Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.03449","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:581ad5a266905c6aadcec586e9507725d558c29c4173d6dda4f031224f31d9c9","sha256:112113c6588fcb3284a0dca7d8dfcc90cb5ae55f68a9dbb6c43664312a6e6937"],"state_sha256":"da2a968ed962446da735f5f7b8e84f43b9020f134e3cc6472a55ae63e9202d22"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1EkG0YYf5NBZQrVNKouIGOpPzHOq80mMpM5+iXfCyjAvihc7Gt+CCmjZUL9rl1UtsjxYRhAf8WBBXuGQTlOFDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T14:09:43.613868Z","bundle_sha256":"cb5c94d01890eae1cf58f42d4bb191198b2e7d273c9e6cc6922b29dc004162b3"}}