{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:QP2OG3GZNGKCJJAUD2KN7KIOEJ","short_pith_number":"pith:QP2OG3GZ","canonical_record":{"source":{"id":"1908.03289","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-09T03:03:23Z","cross_cats_sorted":[],"title_canon_sha256":"86a60722e70303d79fab3752d8a14c7d01cf903408cffbbef3a44cd114649336","abstract_canon_sha256":"fcca8892eea3f3edfbaf5f526f1151e5a28e3ce32fe6e580d04e451dac9d3ea3"},"schema_version":"1.0"},"canonical_sha256":"83f4e36cd9699424a4141e94dfa90e22590132f3218b20e4bd1af16ff8a19cac","source":{"kind":"arxiv","id":"1908.03289","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.03289","created_at":"2026-07-05T03:08:41Z"},{"alias_kind":"arxiv_version","alias_value":"1908.03289v2","created_at":"2026-07-05T03:08:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.03289","created_at":"2026-07-05T03:08:41Z"},{"alias_kind":"pith_short_12","alias_value":"QP2OG3GZNGKC","created_at":"2026-07-05T03:08:41Z"},{"alias_kind":"pith_short_16","alias_value":"QP2OG3GZNGKCJJAU","created_at":"2026-07-05T03:08:41Z"},{"alias_kind":"pith_short_8","alias_value":"QP2OG3GZ","created_at":"2026-07-05T03:08:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:QP2OG3GZNGKCJJAUD2KN7KIOEJ","target":"record","payload":{"canonical_record":{"source":{"id":"1908.03289","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-09T03:03:23Z","cross_cats_sorted":[],"title_canon_sha256":"86a60722e70303d79fab3752d8a14c7d01cf903408cffbbef3a44cd114649336","abstract_canon_sha256":"fcca8892eea3f3edfbaf5f526f1151e5a28e3ce32fe6e580d04e451dac9d3ea3"},"schema_version":"1.0"},"canonical_sha256":"83f4e36cd9699424a4141e94dfa90e22590132f3218b20e4bd1af16ff8a19cac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:08:41.515600Z","signature_b64":"QnbIAPG5cWHK1Jmr9LFILEfhgmIm4eOF9duifXmJc7rp8YA3j1tdEPifVYGcoI3b+t9LmlHkTi7sIvx0Gup1Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83f4e36cd9699424a4141e94dfa90e22590132f3218b20e4bd1af16ff8a19cac","last_reissued_at":"2026-07-05T03:08:41.515232Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:08:41.515232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.03289","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:08:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"knV/TvTH5WY4IEFaP4Ba9/jLb86GxW3Koj9ApnogiitDuT+OnVhfWGYrPDuPI7RqgZlRJs/eXyDsZ48vPY+NAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:38:47.340449Z"},"content_sha256":"b4b47053c137a9a23fd28f0d20b8353edf7a5169f3ec321060017b252c21a647","schema_version":"1.0","event_id":"sha256:b4b47053c137a9a23fd28f0d20b8353edf7a5169f3ec321060017b252c21a647"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:QP2OG3GZNGKCJJAUD2KN7KIOEJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Question-Agnostic Attention for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Moshiur R Farazi, Nick Barnes, Salman H Khan","submitted_at":"2019-08-09T03:03:23Z","abstract_excerpt":"Visual Question Answering (VQA) models employ attention mechanisms to discover image locations that are most relevant for answering a specific question. For this purpose, several multimodal fusion strategies have been proposed, ranging from relatively simple operations (e.g., linear sum) to more complex ones (e.g., Block). The resulting multimodal representations define an intermediate feature space for capturing the interplay between visual and semantic features, that is helpful in selectively focusing on image content. In this paper, we propose a question-agnostic attention mechanism that is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.03289","kind":"arxiv","version":2},"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/1908.03289/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":"2026-07-05T03:08:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PyPcnQ1DoFdxGG/oCQM4Pvkglj2NZo8tGaleY5PguO27VqqUdHyPCUasB8HlAEHgTCYupMaU8PTXO406L8qmBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:38:47.341222Z"},"content_sha256":"4ac4f443d59172adca128cc83544e2821cc795c5a5affc327445a9e7b4cbda7b","schema_version":"1.0","event_id":"sha256:4ac4f443d59172adca128cc83544e2821cc795c5a5affc327445a9e7b4cbda7b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QP2OG3GZNGKCJJAUD2KN7KIOEJ/bundle.json","state_url":"https://pith.science/pith/QP2OG3GZNGKCJJAUD2KN7KIOEJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QP2OG3GZNGKCJJAUD2KN7KIOEJ/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":"2026-07-07T02:38:47Z","links":{"resolver":"https://pith.science/pith/QP2OG3GZNGKCJJAUD2KN7KIOEJ","bundle":"https://pith.science/pith/QP2OG3GZNGKCJJAUD2KN7KIOEJ/bundle.json","state":"https://pith.science/pith/QP2OG3GZNGKCJJAUD2KN7KIOEJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QP2OG3GZNGKCJJAUD2KN7KIOEJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QP2OG3GZNGKCJJAUD2KN7KIOEJ","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":"fcca8892eea3f3edfbaf5f526f1151e5a28e3ce32fe6e580d04e451dac9d3ea3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-09T03:03:23Z","title_canon_sha256":"86a60722e70303d79fab3752d8a14c7d01cf903408cffbbef3a44cd114649336"},"schema_version":"1.0","source":{"id":"1908.03289","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.03289","created_at":"2026-07-05T03:08:41Z"},{"alias_kind":"arxiv_version","alias_value":"1908.03289v2","created_at":"2026-07-05T03:08:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.03289","created_at":"2026-07-05T03:08:41Z"},{"alias_kind":"pith_short_12","alias_value":"QP2OG3GZNGKC","created_at":"2026-07-05T03:08:41Z"},{"alias_kind":"pith_short_16","alias_value":"QP2OG3GZNGKCJJAU","created_at":"2026-07-05T03:08:41Z"},{"alias_kind":"pith_short_8","alias_value":"QP2OG3GZ","created_at":"2026-07-05T03:08:41Z"}],"graph_snapshots":[{"event_id":"sha256:4ac4f443d59172adca128cc83544e2821cc795c5a5affc327445a9e7b4cbda7b","target":"graph","created_at":"2026-07-05T03:08:41Z","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/1908.03289/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Question Answering (VQA) models employ attention mechanisms to discover image locations that are most relevant for answering a specific question. For this purpose, several multimodal fusion strategies have been proposed, ranging from relatively simple operations (e.g., linear sum) to more complex ones (e.g., Block). The resulting multimodal representations define an intermediate feature space for capturing the interplay between visual and semantic features, that is helpful in selectively focusing on image content. In this paper, we propose a question-agnostic attention mechanism that is","authors_text":"Moshiur R Farazi, Nick Barnes, Salman H Khan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-09T03:03:23Z","title":"Question-Agnostic Attention for Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.03289","kind":"arxiv","version":2},"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:b4b47053c137a9a23fd28f0d20b8353edf7a5169f3ec321060017b252c21a647","target":"record","created_at":"2026-07-05T03:08:41Z","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":"fcca8892eea3f3edfbaf5f526f1151e5a28e3ce32fe6e580d04e451dac9d3ea3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-09T03:03:23Z","title_canon_sha256":"86a60722e70303d79fab3752d8a14c7d01cf903408cffbbef3a44cd114649336"},"schema_version":"1.0","source":{"id":"1908.03289","kind":"arxiv","version":2}},"canonical_sha256":"83f4e36cd9699424a4141e94dfa90e22590132f3218b20e4bd1af16ff8a19cac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83f4e36cd9699424a4141e94dfa90e22590132f3218b20e4bd1af16ff8a19cac","first_computed_at":"2026-07-05T03:08:41.515232Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:08:41.515232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QnbIAPG5cWHK1Jmr9LFILEfhgmIm4eOF9duifXmJc7rp8YA3j1tdEPifVYGcoI3b+t9LmlHkTi7sIvx0Gup1Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:08:41.515600Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.03289","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4b47053c137a9a23fd28f0d20b8353edf7a5169f3ec321060017b252c21a647","sha256:4ac4f443d59172adca128cc83544e2821cc795c5a5affc327445a9e7b4cbda7b"],"state_sha256":"580492fba83f3a39b2dd4d262f0a16b003dbcb096133908a89f9edb098cfb505"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/xjfcgrLZGJhH3s/DUKifWJTqnpt8Q+Ll/x2/Mdi9gu3rQaPX1OQZf3kpSVwZPQmjiE+uL6j8L5mSSBXk7zzBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T02:38:47.345005Z","bundle_sha256":"d208919a08e3adff1b05bf8f2eac2a3619040c6b1adacb9f468832800f5b88ba"}}