{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:FVY2AUATKAK55DSSQPOJM2YOEJ","short_pith_number":"pith:FVY2AUAT","canonical_record":{"source":{"id":"1708.00584","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-02T02:51:32Z","cross_cats_sorted":[],"title_canon_sha256":"3d8686cb8b988a035aa87d605a608933f6dd7bf6660c2771d04423b9db7abb1f","abstract_canon_sha256":"26a055122b1462c18b0661ba9d199b2be7241934ed015d473b34ae0d073747ca"},"schema_version":"1.0"},"canonical_sha256":"2d71a050135015de8e5283dc966b0e22741d036240bddf6d907d794d056028a6","source":{"kind":"arxiv","id":"1708.00584","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.00584","created_at":"2026-05-18T00:38:45Z"},{"alias_kind":"arxiv_version","alias_value":"1708.00584v1","created_at":"2026-05-18T00:38:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.00584","created_at":"2026-05-18T00:38:45Z"},{"alias_kind":"pith_short_12","alias_value":"FVY2AUATKAK5","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"FVY2AUATKAK55DSS","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"FVY2AUAT","created_at":"2026-05-18T12:31:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:FVY2AUATKAK55DSSQPOJM2YOEJ","target":"record","payload":{"canonical_record":{"source":{"id":"1708.00584","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-02T02:51:32Z","cross_cats_sorted":[],"title_canon_sha256":"3d8686cb8b988a035aa87d605a608933f6dd7bf6660c2771d04423b9db7abb1f","abstract_canon_sha256":"26a055122b1462c18b0661ba9d199b2be7241934ed015d473b34ae0d073747ca"},"schema_version":"1.0"},"canonical_sha256":"2d71a050135015de8e5283dc966b0e22741d036240bddf6d907d794d056028a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:45.329077Z","signature_b64":"hbOyxPMjcGnPxidiIOjXFFLCBEjI73PTKMuhDExM++XpE28Bmlo709mBZ+JW0T/q1pHunuwHGoXJZDbNOZQEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d71a050135015de8e5283dc966b0e22741d036240bddf6d907d794d056028a6","last_reissued_at":"2026-05-18T00:38:45.328639Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:45.328639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1708.00584","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":"2026-05-18T00:38:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kGVZwyPYFKG5+5nW7leEmgHsD1P3JlU67HRqfAbYOjcoCuywsbpL4oGU9u0KgF6AR/uTl4Su0iZGrc051SRiBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T02:36:02.767666Z"},"content_sha256":"78e5cfd8a0eedf2b940348d162e19c38fcbd414cd2551e3f9fed7e931733bf73","schema_version":"1.0","event_id":"sha256:78e5cfd8a0eedf2b940348d162e19c38fcbd414cd2551e3f9fed7e931733bf73"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:FVY2AUATKAK55DSSQPOJM2YOEJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Simple Loss Function for Improving the Convergence and Accuracy of Visual Question Answering Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ilija Ilievski, Jiashi Feng","submitted_at":"2017-08-02T02:51:32Z","abstract_excerpt":"Visual question answering as recently proposed multimodal learning task has enjoyed wide attention from the deep learning community. Lately, the focus was on developing new representation fusion methods and attention mechanisms to achieve superior performance. On the other hand, very little focus has been put on the models' loss function, arguably one of the most important aspects of training deep learning models. The prevailing practice is to use cross entropy loss function that penalizes the probability given to all the answers in the vocabulary except the single most common answer for the p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.00584","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":"2026-05-18T00:38:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jSF88BtkRCBXOWwgffIA8GTH4xj7kSqRcaJ5crTGOKN9CvELA3PBjKLvj/TZun+5nzPfkIH00ScEnch1rBmhBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T02:36:02.768024Z"},"content_sha256":"72718407a07c474c36a39679545c2fd2c44f2f611752446e9738be282a4bb263","schema_version":"1.0","event_id":"sha256:72718407a07c474c36a39679545c2fd2c44f2f611752446e9738be282a4bb263"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FVY2AUATKAK55DSSQPOJM2YOEJ/bundle.json","state_url":"https://pith.science/pith/FVY2AUATKAK55DSSQPOJM2YOEJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FVY2AUATKAK55DSSQPOJM2YOEJ/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":"2026-05-31T02:36:02Z","links":{"resolver":"https://pith.science/pith/FVY2AUATKAK55DSSQPOJM2YOEJ","bundle":"https://pith.science/pith/FVY2AUATKAK55DSSQPOJM2YOEJ/bundle.json","state":"https://pith.science/pith/FVY2AUATKAK55DSSQPOJM2YOEJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FVY2AUATKAK55DSSQPOJM2YOEJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:FVY2AUATKAK55DSSQPOJM2YOEJ","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":"26a055122b1462c18b0661ba9d199b2be7241934ed015d473b34ae0d073747ca","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-02T02:51:32Z","title_canon_sha256":"3d8686cb8b988a035aa87d605a608933f6dd7bf6660c2771d04423b9db7abb1f"},"schema_version":"1.0","source":{"id":"1708.00584","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.00584","created_at":"2026-05-18T00:38:45Z"},{"alias_kind":"arxiv_version","alias_value":"1708.00584v1","created_at":"2026-05-18T00:38:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.00584","created_at":"2026-05-18T00:38:45Z"},{"alias_kind":"pith_short_12","alias_value":"FVY2AUATKAK5","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"FVY2AUATKAK55DSS","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"FVY2AUAT","created_at":"2026-05-18T12:31:15Z"}],"graph_snapshots":[{"event_id":"sha256:72718407a07c474c36a39679545c2fd2c44f2f611752446e9738be282a4bb263","target":"graph","created_at":"2026-05-18T00:38:45Z","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":"Visual question answering as recently proposed multimodal learning task has enjoyed wide attention from the deep learning community. Lately, the focus was on developing new representation fusion methods and attention mechanisms to achieve superior performance. On the other hand, very little focus has been put on the models' loss function, arguably one of the most important aspects of training deep learning models. The prevailing practice is to use cross entropy loss function that penalizes the probability given to all the answers in the vocabulary except the single most common answer for the p","authors_text":"Ilija Ilievski, Jiashi Feng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-02T02:51:32Z","title":"A Simple Loss Function for Improving the Convergence and Accuracy of Visual Question Answering Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.00584","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":"sha256:78e5cfd8a0eedf2b940348d162e19c38fcbd414cd2551e3f9fed7e931733bf73","target":"record","created_at":"2026-05-18T00:38:45Z","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":"26a055122b1462c18b0661ba9d199b2be7241934ed015d473b34ae0d073747ca","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-02T02:51:32Z","title_canon_sha256":"3d8686cb8b988a035aa87d605a608933f6dd7bf6660c2771d04423b9db7abb1f"},"schema_version":"1.0","source":{"id":"1708.00584","kind":"arxiv","version":1}},"canonical_sha256":"2d71a050135015de8e5283dc966b0e22741d036240bddf6d907d794d056028a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d71a050135015de8e5283dc966b0e22741d036240bddf6d907d794d056028a6","first_computed_at":"2026-05-18T00:38:45.328639Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:38:45.328639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hbOyxPMjcGnPxidiIOjXFFLCBEjI73PTKMuhDExM++XpE28Bmlo709mBZ+JW0T/q1pHunuwHGoXJZDbNOZQEBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:38:45.329077Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.00584","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78e5cfd8a0eedf2b940348d162e19c38fcbd414cd2551e3f9fed7e931733bf73","sha256:72718407a07c474c36a39679545c2fd2c44f2f611752446e9738be282a4bb263"],"state_sha256":"39d14523ad3d9216183de7d39f65cc077d53ce1dfe71f1453b8af492c6df9389"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ervW6v19qmUEJxtZfKBqe/gnRhJYx7aJPmIQi814nd4JePzVfBxjbaLmGaW8tO957J8mgM7Mf1Nf0YvGsD6yCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T02:36:02.770485Z","bundle_sha256":"7b9b8e73019f57ab2bc9584f16d7c8dbebac0339bb7f7d9104e8125e1095853b"}}