{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:7NZUKOT53XRIQXZT52UDJFNY2E","short_pith_number":"pith:7NZUKOT5","canonical_record":{"source":{"id":"1705.06676","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-18T16:23:22Z","cross_cats_sorted":[],"title_canon_sha256":"4a76577bfc6ccd4ced8f004017ed3fd13b5c9139a6af472118a24ffbe450cef0","abstract_canon_sha256":"b1ee5c639dddca598ce5b50bd89cce28e07de8b5c14085c072161d2a8a6cfb98"},"schema_version":"1.0"},"canonical_sha256":"fb73453a7ddde2885f33eea83495b8d126f844ff3bc83434c576c93da680c319","source":{"kind":"arxiv","id":"1705.06676","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.06676","created_at":"2026-05-18T00:44:06Z"},{"alias_kind":"arxiv_version","alias_value":"1705.06676v1","created_at":"2026-05-18T00:44:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.06676","created_at":"2026-05-18T00:44:06Z"},{"alias_kind":"pith_short_12","alias_value":"7NZUKOT53XRI","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"7NZUKOT53XRIQXZT","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"7NZUKOT5","created_at":"2026-05-18T12:31:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:7NZUKOT53XRIQXZT52UDJFNY2E","target":"record","payload":{"canonical_record":{"source":{"id":"1705.06676","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-18T16:23:22Z","cross_cats_sorted":[],"title_canon_sha256":"4a76577bfc6ccd4ced8f004017ed3fd13b5c9139a6af472118a24ffbe450cef0","abstract_canon_sha256":"b1ee5c639dddca598ce5b50bd89cce28e07de8b5c14085c072161d2a8a6cfb98"},"schema_version":"1.0"},"canonical_sha256":"fb73453a7ddde2885f33eea83495b8d126f844ff3bc83434c576c93da680c319","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:06.525527Z","signature_b64":"mR5gsWdHmrcUwegbC9h8VU+DbDne6UDQM7miJ7KkvU1NJPAq9S9ODFYCMVMPN0d2MJmQ+oFaMdFhsiUqRof2Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb73453a7ddde2885f33eea83495b8d126f844ff3bc83434c576c93da680c319","last_reissued_at":"2026-05-18T00:44:06.524854Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:06.524854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.06676","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":"2026-05-18T00:44:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E6hFe+i//22MDgBfbRSgCvXy8bGqenkudSRfPIsSDnxO2VCtPM3BWAy3nFnm6Q+loMZ+zP7RaSd02uq3bEaAAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T13:07:39.443496Z"},"content_sha256":"34d537a5a2910c2f4c3fa17a4ae4ce6e3b1b0c66cfdcff98f984cd466440b059","schema_version":"1.0","event_id":"sha256:34d537a5a2910c2f4c3fa17a4ae4ce6e3b1b0c66cfdcff98f984cd466440b059"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:7NZUKOT53XRIQXZT52UDJFNY2E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MUTAN: Multimodal Tucker Fusion for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hedi Ben-younes, Matthieu Cord, Nicolas Thome, R\\'emi Cadene","submitted_at":"2017-05-18T16:23:22Z","abstract_excerpt":"Bilinear models provide an appealing framework for mixing and merging information in Visual Question Answering (VQA) tasks. They help to learn high level associations between question meaning and visual concepts in the image, but they suffer from huge dimensionality issues. We introduce MUTAN, a multimodal tensor-based Tucker decomposition to efficiently parametrize bilinear interactions between visual and textual representations. Additionally to the Tucker framework, we design a low-rank matrix-based decomposition to explicitly constrain the interaction rank. With MUTAN, we control the comple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.06676","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":"2026-05-18T00:44:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9xItatkOci/QK5lUS2n9ON2vVyiX2OFAh8wb9SmY+CSD0PiwQL53ZsEv6hS98JSw4tEOu+3sqh2miURpgJnAAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T13:07:39.443991Z"},"content_sha256":"ad434af789a47b84cc8218ad4ff94757b8079ef8ba9d2c4b9bd1316a54516b63","schema_version":"1.0","event_id":"sha256:ad434af789a47b84cc8218ad4ff94757b8079ef8ba9d2c4b9bd1316a54516b63"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7NZUKOT53XRIQXZT52UDJFNY2E/bundle.json","state_url":"https://pith.science/pith/7NZUKOT53XRIQXZT52UDJFNY2E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7NZUKOT53XRIQXZT52UDJFNY2E/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":"2026-08-12T13:07:39Z","links":{"resolver":"https://pith.science/pith/7NZUKOT53XRIQXZT52UDJFNY2E","bundle":"https://pith.science/pith/7NZUKOT53XRIQXZT52UDJFNY2E/bundle.json","state":"https://pith.science/pith/7NZUKOT53XRIQXZT52UDJFNY2E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7NZUKOT53XRIQXZT52UDJFNY2E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:7NZUKOT53XRIQXZT52UDJFNY2E","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":"b1ee5c639dddca598ce5b50bd89cce28e07de8b5c14085c072161d2a8a6cfb98","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-18T16:23:22Z","title_canon_sha256":"4a76577bfc6ccd4ced8f004017ed3fd13b5c9139a6af472118a24ffbe450cef0"},"schema_version":"1.0","source":{"id":"1705.06676","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.06676","created_at":"2026-05-18T00:44:06Z"},{"alias_kind":"arxiv_version","alias_value":"1705.06676v1","created_at":"2026-05-18T00:44:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.06676","created_at":"2026-05-18T00:44:06Z"},{"alias_kind":"pith_short_12","alias_value":"7NZUKOT53XRI","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"7NZUKOT53XRIQXZT","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"7NZUKOT5","created_at":"2026-05-18T12:31:05Z"}],"graph_snapshots":[{"event_id":"sha256:ad434af789a47b84cc8218ad4ff94757b8079ef8ba9d2c4b9bd1316a54516b63","target":"graph","created_at":"2026-05-18T00:44:06Z","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":"Bilinear models provide an appealing framework for mixing and merging information in Visual Question Answering (VQA) tasks. They help to learn high level associations between question meaning and visual concepts in the image, but they suffer from huge dimensionality issues. We introduce MUTAN, a multimodal tensor-based Tucker decomposition to efficiently parametrize bilinear interactions between visual and textual representations. Additionally to the Tucker framework, we design a low-rank matrix-based decomposition to explicitly constrain the interaction rank. With MUTAN, we control the comple","authors_text":"Hedi Ben-younes, Matthieu Cord, Nicolas Thome, R\\'emi Cadene","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-18T16:23:22Z","title":"MUTAN: Multimodal Tucker Fusion for Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.06676","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":"sha256:34d537a5a2910c2f4c3fa17a4ae4ce6e3b1b0c66cfdcff98f984cd466440b059","target":"record","created_at":"2026-05-18T00:44:06Z","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":"b1ee5c639dddca598ce5b50bd89cce28e07de8b5c14085c072161d2a8a6cfb98","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-18T16:23:22Z","title_canon_sha256":"4a76577bfc6ccd4ced8f004017ed3fd13b5c9139a6af472118a24ffbe450cef0"},"schema_version":"1.0","source":{"id":"1705.06676","kind":"arxiv","version":1}},"canonical_sha256":"fb73453a7ddde2885f33eea83495b8d126f844ff3bc83434c576c93da680c319","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb73453a7ddde2885f33eea83495b8d126f844ff3bc83434c576c93da680c319","first_computed_at":"2026-05-18T00:44:06.524854Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:44:06.524854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mR5gsWdHmrcUwegbC9h8VU+DbDne6UDQM7miJ7KkvU1NJPAq9S9ODFYCMVMPN0d2MJmQ+oFaMdFhsiUqRof2Cw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:44:06.525527Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.06676","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34d537a5a2910c2f4c3fa17a4ae4ce6e3b1b0c66cfdcff98f984cd466440b059","sha256:ad434af789a47b84cc8218ad4ff94757b8079ef8ba9d2c4b9bd1316a54516b63"],"state_sha256":"0f4f513f58353621059255742d89014e8e8ebcded4c923972c0e945010bf7678"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZOxUodSf1wuQWDOmogz33A0jau6gbL1xXmXPqEW5PWlzrEa0H+4Ga/npyQbk5L45aPSP5F3JXTMnDEy0vLtfAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T13:07:39.448507Z","bundle_sha256":"bbcda0331572864b19dff87d58b34e6bf4f07789fc0c7f2f00967bfa7259c0c5"}}