{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:E4ZAITTQ75JNC2IV5MN2KIX6AF","short_pith_number":"pith:E4ZAITTQ","canonical_record":{"source":{"id":"2011.06102","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-11-11T22:31:27Z","cross_cats_sorted":[],"title_canon_sha256":"3d93b1bfce3f37eea917c7551132143da127df98cc94f18cee4c315eea6afa4f","abstract_canon_sha256":"fc6daf3f78a626949ea9e235f49e30476d9c45a9a17bb8200d1658cd2fb6f326"},"schema_version":"1.0"},"canonical_sha256":"2732044e70ff52d16915eb1ba522fe016afa79c27a3528913f1c86ebfe56184c","source":{"kind":"arxiv","id":"2011.06102","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.06102","created_at":"2026-07-05T01:51:11Z"},{"alias_kind":"arxiv_version","alias_value":"2011.06102v1","created_at":"2026-07-05T01:51:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.06102","created_at":"2026-07-05T01:51:11Z"},{"alias_kind":"pith_short_12","alias_value":"E4ZAITTQ75JN","created_at":"2026-07-05T01:51:11Z"},{"alias_kind":"pith_short_16","alias_value":"E4ZAITTQ75JNC2IV","created_at":"2026-07-05T01:51:11Z"},{"alias_kind":"pith_short_8","alias_value":"E4ZAITTQ","created_at":"2026-07-05T01:51:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:E4ZAITTQ75JNC2IV5MN2KIX6AF","target":"record","payload":{"canonical_record":{"source":{"id":"2011.06102","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-11-11T22:31:27Z","cross_cats_sorted":[],"title_canon_sha256":"3d93b1bfce3f37eea917c7551132143da127df98cc94f18cee4c315eea6afa4f","abstract_canon_sha256":"fc6daf3f78a626949ea9e235f49e30476d9c45a9a17bb8200d1658cd2fb6f326"},"schema_version":"1.0"},"canonical_sha256":"2732044e70ff52d16915eb1ba522fe016afa79c27a3528913f1c86ebfe56184c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:11.949016Z","signature_b64":"vC0dB3KG3ngjNn7WnXrn+pbFFo1C0juMgIgOfXSo/KO7i6alJRWBM4JdmTdYm/aV02VobKk1/5iO702wLSTyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2732044e70ff52d16915eb1ba522fe016afa79c27a3528913f1c86ebfe56184c","last_reissued_at":"2026-07-05T01:51:11.948667Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:11.948667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.06102","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":"2026-07-05T01:51:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sIe2BaIy5QkKLvHi7uKBSEyrdKWgqv9t8r0+RZZ5NpLSzVUkIErJM3PciKA8z9iIpwbYeM/dx14xtaAnqizhDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T08:14:23.938425Z"},"content_sha256":"dcba03d6ca82ff87fc6cf1f9fe9c1778742cdca324f519b0ee1e39e2d5d62d13","schema_version":"1.0","event_id":"sha256:dcba03d6ca82ff87fc6cf1f9fe9c1778742cdca324f519b0ee1e39e2d5d62d13"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:E4ZAITTQ75JNC2IV5MN2KIX6AF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Multimodal Accuracy Through Modality Pre-training and Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aya Abdelsalam Ismail, Faisal Ishtiaq, Mahmudul Hasan","submitted_at":"2020-11-11T22:31:27Z","abstract_excerpt":"Training a multimodal network is challenging and it requires complex architectures to achieve reasonable performance. We show that one reason for this phenomena is the difference between the convergence rate of various modalities. We address this by pre-training modality-specific sub-networks in multimodal architectures independently before end-to-end training of the entire network. Furthermore, we show that the addition of an attention mechanism between sub-networks after pre-training helps identify the most important modality during ambiguous scenarios boosting the performance. We demonstrat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.06102","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/2011.06102/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":"2026-07-05T01:51:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7nK50qHP8+DLPjAqEeKeXcdes/7uVmpZphbEj7kkJHZcXMg3FIH8ZwWsr/aIHi+JZ9h0abVCQXtNbdyWg9jNCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T08:14:23.938799Z"},"content_sha256":"886b4a9cf6d37c760a18e1aab1d64710d2e023c94232ed82371fe09d739d3edd","schema_version":"1.0","event_id":"sha256:886b4a9cf6d37c760a18e1aab1d64710d2e023c94232ed82371fe09d739d3edd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E4ZAITTQ75JNC2IV5MN2KIX6AF/bundle.json","state_url":"https://pith.science/pith/E4ZAITTQ75JNC2IV5MN2KIX6AF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E4ZAITTQ75JNC2IV5MN2KIX6AF/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":"2026-08-13T08:14:23Z","links":{"resolver":"https://pith.science/pith/E4ZAITTQ75JNC2IV5MN2KIX6AF","bundle":"https://pith.science/pith/E4ZAITTQ75JNC2IV5MN2KIX6AF/bundle.json","state":"https://pith.science/pith/E4ZAITTQ75JNC2IV5MN2KIX6AF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E4ZAITTQ75JNC2IV5MN2KIX6AF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:E4ZAITTQ75JNC2IV5MN2KIX6AF","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":"fc6daf3f78a626949ea9e235f49e30476d9c45a9a17bb8200d1658cd2fb6f326","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-11-11T22:31:27Z","title_canon_sha256":"3d93b1bfce3f37eea917c7551132143da127df98cc94f18cee4c315eea6afa4f"},"schema_version":"1.0","source":{"id":"2011.06102","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.06102","created_at":"2026-07-05T01:51:11Z"},{"alias_kind":"arxiv_version","alias_value":"2011.06102v1","created_at":"2026-07-05T01:51:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.06102","created_at":"2026-07-05T01:51:11Z"},{"alias_kind":"pith_short_12","alias_value":"E4ZAITTQ75JN","created_at":"2026-07-05T01:51:11Z"},{"alias_kind":"pith_short_16","alias_value":"E4ZAITTQ75JNC2IV","created_at":"2026-07-05T01:51:11Z"},{"alias_kind":"pith_short_8","alias_value":"E4ZAITTQ","created_at":"2026-07-05T01:51:11Z"}],"graph_snapshots":[{"event_id":"sha256:886b4a9cf6d37c760a18e1aab1d64710d2e023c94232ed82371fe09d739d3edd","target":"graph","created_at":"2026-07-05T01:51:11Z","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/2011.06102/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training a multimodal network is challenging and it requires complex architectures to achieve reasonable performance. We show that one reason for this phenomena is the difference between the convergence rate of various modalities. We address this by pre-training modality-specific sub-networks in multimodal architectures independently before end-to-end training of the entire network. Furthermore, we show that the addition of an attention mechanism between sub-networks after pre-training helps identify the most important modality during ambiguous scenarios boosting the performance. We demonstrat","authors_text":"Aya Abdelsalam Ismail, Faisal Ishtiaq, Mahmudul Hasan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-11-11T22:31:27Z","title":"Improving Multimodal Accuracy Through Modality Pre-training and Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.06102","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:dcba03d6ca82ff87fc6cf1f9fe9c1778742cdca324f519b0ee1e39e2d5d62d13","target":"record","created_at":"2026-07-05T01:51:11Z","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":"fc6daf3f78a626949ea9e235f49e30476d9c45a9a17bb8200d1658cd2fb6f326","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-11-11T22:31:27Z","title_canon_sha256":"3d93b1bfce3f37eea917c7551132143da127df98cc94f18cee4c315eea6afa4f"},"schema_version":"1.0","source":{"id":"2011.06102","kind":"arxiv","version":1}},"canonical_sha256":"2732044e70ff52d16915eb1ba522fe016afa79c27a3528913f1c86ebfe56184c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2732044e70ff52d16915eb1ba522fe016afa79c27a3528913f1c86ebfe56184c","first_computed_at":"2026-07-05T01:51:11.948667Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:51:11.948667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vC0dB3KG3ngjNn7WnXrn+pbFFo1C0juMgIgOfXSo/KO7i6alJRWBM4JdmTdYm/aV02VobKk1/5iO702wLSTyCw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:51:11.949016Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.06102","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dcba03d6ca82ff87fc6cf1f9fe9c1778742cdca324f519b0ee1e39e2d5d62d13","sha256:886b4a9cf6d37c760a18e1aab1d64710d2e023c94232ed82371fe09d739d3edd"],"state_sha256":"3664cdd4f3a71fbcb008ee6c67049ffd4141108779ff18d137a5bd33d389524a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nDbnydwr/txAZ3K2yyzAdsLWgpyVf860OZf5ON3G7LQOzVGXlqBFdqu4wql0VwU8DD0I7v+OEDtGPV8ofUQSBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T08:14:23.941830Z","bundle_sha256":"0ef32b66685cfadf68cab6b0370209f834d7688e470df86b1195a4fefcced948"}}