{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RTUTUG7XIBLLPUH2Z2MGNBAKMZ","short_pith_number":"pith:RTUTUG7X","canonical_record":{"source":{"id":"2405.04671","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-07T21:05:50Z","cross_cats_sorted":[],"title_canon_sha256":"60af0710abae413dd106526bd51849c9bbe823a9732d73e4a7196004fe18779b","abstract_canon_sha256":"2e6607cb63a3b45a540bfd244cfae4c01471a58e40b7ca710367c38ab5da76a5"},"schema_version":"1.0"},"canonical_sha256":"8ce93a1bf74056b7d0face9866840a667280f086757938122cf6a54fe5c9fe74","source":{"kind":"arxiv","id":"2405.04671","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.04671","created_at":"2026-07-05T08:16:52Z"},{"alias_kind":"arxiv_version","alias_value":"2405.04671v1","created_at":"2026-07-05T08:16:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04671","created_at":"2026-07-05T08:16:52Z"},{"alias_kind":"pith_short_12","alias_value":"RTUTUG7XIBLL","created_at":"2026-07-05T08:16:52Z"},{"alias_kind":"pith_short_16","alias_value":"RTUTUG7XIBLLPUH2","created_at":"2026-07-05T08:16:52Z"},{"alias_kind":"pith_short_8","alias_value":"RTUTUG7X","created_at":"2026-07-05T08:16:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RTUTUG7XIBLLPUH2Z2MGNBAKMZ","target":"record","payload":{"canonical_record":{"source":{"id":"2405.04671","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-07T21:05:50Z","cross_cats_sorted":[],"title_canon_sha256":"60af0710abae413dd106526bd51849c9bbe823a9732d73e4a7196004fe18779b","abstract_canon_sha256":"2e6607cb63a3b45a540bfd244cfae4c01471a58e40b7ca710367c38ab5da76a5"},"schema_version":"1.0"},"canonical_sha256":"8ce93a1bf74056b7d0face9866840a667280f086757938122cf6a54fe5c9fe74","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:52.283613Z","signature_b64":"oBAfCFkNw0dFhVHBmt2QVSCe5KhZ0r8sCl6pTuk+qZAq+PH7oVg4zws7c5C9nPGjNah4lK9pntx3J9LiM1ZtAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ce93a1bf74056b7d0face9866840a667280f086757938122cf6a54fe5c9fe74","last_reissued_at":"2026-07-05T08:16:52.283115Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:52.283115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.04671","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":"2026-07-05T08:16:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WDpJD/8KwZ+kNsAwi+4whXrg8W/RAYuqV4cGUXaZgWbw/ZS9L5merk62YXeGXaaULDGj9mGcubCzxu9TvPXuDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T07:02:15.461033Z"},"content_sha256":"de313d21f9873571d5390121fcd278dd38049bda7fee807c46fde29060e644bb","schema_version":"1.0","event_id":"sha256:de313d21f9873571d5390121fcd278dd38049bda7fee807c46fde29060e644bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RTUTUG7XIBLLPUH2Z2MGNBAKMZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Interpretable Tensor Fusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andriy Balinskyy, Antoine Ledent, Marius Kloft, Philipp Liznerski, Purvanshi Mehta, Saurabh Varshneya, Waleed Mustafa","submitted_at":"2024-05-07T21:05:50Z","abstract_excerpt":"Conventional machine learning methods are predominantly designed to predict outcomes based on a single data type. However, practical applications may encompass data of diverse types, such as text, images, and audio. We introduce interpretable tensor fusion (InTense), a multimodal learning method for training neural networks to simultaneously learn multimodal data representations and their interpretable fusion. InTense can separately capture both linear combinations and multiplicative interactions of diverse data types, thereby disentangling higher-order interactions from the individual effects"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04671","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2405.04671/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T08:16:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2+H5lU5xwFpmjWL4DspisN88bgNRFOaHZUyzhACYmCHDX1GlTE+tnQIOdGxW6e6FPvQpEIb7dPAMK5Ifc6xLCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T07:02:15.461668Z"},"content_sha256":"127d501d8c98d6864488ed964d1f931856d9fecb54f3503b769a9584a81e7d78","schema_version":"1.0","event_id":"sha256:127d501d8c98d6864488ed964d1f931856d9fecb54f3503b769a9584a81e7d78"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RTUTUG7XIBLLPUH2Z2MGNBAKMZ/bundle.json","state_url":"https://pith.science/pith/RTUTUG7XIBLLPUH2Z2MGNBAKMZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RTUTUG7XIBLLPUH2Z2MGNBAKMZ/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":"2026-07-09T07:02:15Z","links":{"resolver":"https://pith.science/pith/RTUTUG7XIBLLPUH2Z2MGNBAKMZ","bundle":"https://pith.science/pith/RTUTUG7XIBLLPUH2Z2MGNBAKMZ/bundle.json","state":"https://pith.science/pith/RTUTUG7XIBLLPUH2Z2MGNBAKMZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RTUTUG7XIBLLPUH2Z2MGNBAKMZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RTUTUG7XIBLLPUH2Z2MGNBAKMZ","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":"2e6607cb63a3b45a540bfd244cfae4c01471a58e40b7ca710367c38ab5da76a5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-07T21:05:50Z","title_canon_sha256":"60af0710abae413dd106526bd51849c9bbe823a9732d73e4a7196004fe18779b"},"schema_version":"1.0","source":{"id":"2405.04671","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.04671","created_at":"2026-07-05T08:16:52Z"},{"alias_kind":"arxiv_version","alias_value":"2405.04671v1","created_at":"2026-07-05T08:16:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04671","created_at":"2026-07-05T08:16:52Z"},{"alias_kind":"pith_short_12","alias_value":"RTUTUG7XIBLL","created_at":"2026-07-05T08:16:52Z"},{"alias_kind":"pith_short_16","alias_value":"RTUTUG7XIBLLPUH2","created_at":"2026-07-05T08:16:52Z"},{"alias_kind":"pith_short_8","alias_value":"RTUTUG7X","created_at":"2026-07-05T08:16:52Z"}],"graph_snapshots":[{"event_id":"sha256:127d501d8c98d6864488ed964d1f931856d9fecb54f3503b769a9584a81e7d78","target":"graph","created_at":"2026-07-05T08:16:52Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2405.04671/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Conventional machine learning methods are predominantly designed to predict outcomes based on a single data type. However, practical applications may encompass data of diverse types, such as text, images, and audio. We introduce interpretable tensor fusion (InTense), a multimodal learning method for training neural networks to simultaneously learn multimodal data representations and their interpretable fusion. InTense can separately capture both linear combinations and multiplicative interactions of diverse data types, thereby disentangling higher-order interactions from the individual effects","authors_text":"Andriy Balinskyy, Antoine Ledent, Marius Kloft, Philipp Liznerski, Purvanshi Mehta, Saurabh Varshneya, Waleed Mustafa","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-07T21:05:50Z","title":"Interpretable Tensor Fusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04671","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:de313d21f9873571d5390121fcd278dd38049bda7fee807c46fde29060e644bb","target":"record","created_at":"2026-07-05T08:16:52Z","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":"2e6607cb63a3b45a540bfd244cfae4c01471a58e40b7ca710367c38ab5da76a5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-07T21:05:50Z","title_canon_sha256":"60af0710abae413dd106526bd51849c9bbe823a9732d73e4a7196004fe18779b"},"schema_version":"1.0","source":{"id":"2405.04671","kind":"arxiv","version":1}},"canonical_sha256":"8ce93a1bf74056b7d0face9866840a667280f086757938122cf6a54fe5c9fe74","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ce93a1bf74056b7d0face9866840a667280f086757938122cf6a54fe5c9fe74","first_computed_at":"2026-07-05T08:16:52.283115Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:16:52.283115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oBAfCFkNw0dFhVHBmt2QVSCe5KhZ0r8sCl6pTuk+qZAq+PH7oVg4zws7c5C9nPGjNah4lK9pntx3J9LiM1ZtAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:16:52.283613Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.04671","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de313d21f9873571d5390121fcd278dd38049bda7fee807c46fde29060e644bb","sha256:127d501d8c98d6864488ed964d1f931856d9fecb54f3503b769a9584a81e7d78"],"state_sha256":"b1c468a52894479960d7774199193e85edc85c2bf59b806606907c96bcf53dea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HroYXAHPiWjFuYMR/r4nFXi1Q9UmtT/MHn/PEg/ZiIJQB20ij59GLJoJmyqH9ynwG93cq+qyHidIjA88S9K8AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T07:02:15.465158Z","bundle_sha256":"e3138a1f7a13112edff4241158606ba9370c525f349ae289350feab1a71a1dea"}}