{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:GK43VP2RM2QUUCDWM3VIH4Z6QP","short_pith_number":"pith:GK43VP2R","canonical_record":{"source":{"id":"1801.07853","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-01-24T03:58:51Z","cross_cats_sorted":[],"title_canon_sha256":"0fcce05340cc7b8174e5f900f856a54002b80737ae4c75615917cda73c8f26e7","abstract_canon_sha256":"10011ef3bf218fce7ce21486a1ebba73fccaee7c94f79dc6aaeb362b542ad953"},"schema_version":"1.0"},"canonical_sha256":"32b9babf5166a14a087666ea83f33e83e6e87d30bb97d11435a3189bbffc2c18","source":{"kind":"arxiv","id":"1801.07853","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.07853","created_at":"2026-05-18T00:25:10Z"},{"alias_kind":"arxiv_version","alias_value":"1801.07853v1","created_at":"2026-05-18T00:25:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.07853","created_at":"2026-05-18T00:25:10Z"},{"alias_kind":"pith_short_12","alias_value":"GK43VP2RM2QU","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GK43VP2RM2QUUCDW","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GK43VP2R","created_at":"2026-05-18T12:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:GK43VP2RM2QUUCDWM3VIH4Z6QP","target":"record","payload":{"canonical_record":{"source":{"id":"1801.07853","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-01-24T03:58:51Z","cross_cats_sorted":[],"title_canon_sha256":"0fcce05340cc7b8174e5f900f856a54002b80737ae4c75615917cda73c8f26e7","abstract_canon_sha256":"10011ef3bf218fce7ce21486a1ebba73fccaee7c94f79dc6aaeb362b542ad953"},"schema_version":"1.0"},"canonical_sha256":"32b9babf5166a14a087666ea83f33e83e6e87d30bb97d11435a3189bbffc2c18","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:25:10.674246Z","signature_b64":"OZF0j8GaX9lz4j0TX9C6hLcqfsk12AzjLJAn6ZumNNydbOkPRWxczgiZbV83GQLkUl3wtSKa+NUF//fykNS5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32b9babf5166a14a087666ea83f33e83e6e87d30bb97d11435a3189bbffc2c18","last_reissued_at":"2026-05-18T00:25:10.673760Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:25:10.673760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.07853","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":"2026-05-18T00:25:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bctXVotggADudlE+kcFrJVQEsMV+xIQWrypwTO0ar3M8Zt43PktJ/eNGFM1sVSnH1rjDsdUTiCvBgFreoRbAAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T11:04:39.126606Z"},"content_sha256":"62aabbc37fadd7e66c128c45c1e4459fcb4a5dac843c88f4efb8f9eec023e0bc","schema_version":"1.0","event_id":"sha256:62aabbc37fadd7e66c128c45c1e4459fcb4a5dac843c88f4efb8f9eec023e0bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:GK43VP2RM2QUUCDWM3VIH4Z6QP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Structured Triplet Learning with POS-tag Guided Attention for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Charless Fowlkes, Liangjian Chen, Limin Wang, Xiaohui Xie, Xiaoyi Liu, Yu Qiao, Zhe Wang","submitted_at":"2018-01-24T03:58:51Z","abstract_excerpt":"Visual question answering (VQA) is of significant interest due to its potential to be a strong test of image understanding systems and to probe the connection between language and vision. Despite much recent progress, general VQA is far from a solved problem. In this paper, we focus on the VQA multiple-choice task, and provide some good practices for designing an effective VQA model that can capture language-vision interactions and perform joint reasoning. We explore mechanisms of incorporating part-of-speech (POS) tag guided attention, convolutional n-grams, triplet attention interactions bet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.07853","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":"2026-05-18T00:25:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gZFwpWfQiEmlIpbY6gmHROvlQsAZoJOKdGD8ZuCla6rdI/ZHw0eCXSXZ3kI8trEQVjVWsmbxeMkzoIUSusJvCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T11:04:39.127223Z"},"content_sha256":"bfc2ba4ea31abce42777b5ac92bd10b324e82a9bb01b2b56a72c95656ae900c5","schema_version":"1.0","event_id":"sha256:bfc2ba4ea31abce42777b5ac92bd10b324e82a9bb01b2b56a72c95656ae900c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GK43VP2RM2QUUCDWM3VIH4Z6QP/bundle.json","state_url":"https://pith.science/pith/GK43VP2RM2QUUCDWM3VIH4Z6QP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GK43VP2RM2QUUCDWM3VIH4Z6QP/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":"2026-05-26T11:04:39Z","links":{"resolver":"https://pith.science/pith/GK43VP2RM2QUUCDWM3VIH4Z6QP","bundle":"https://pith.science/pith/GK43VP2RM2QUUCDWM3VIH4Z6QP/bundle.json","state":"https://pith.science/pith/GK43VP2RM2QUUCDWM3VIH4Z6QP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GK43VP2RM2QUUCDWM3VIH4Z6QP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:GK43VP2RM2QUUCDWM3VIH4Z6QP","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":"10011ef3bf218fce7ce21486a1ebba73fccaee7c94f79dc6aaeb362b542ad953","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-01-24T03:58:51Z","title_canon_sha256":"0fcce05340cc7b8174e5f900f856a54002b80737ae4c75615917cda73c8f26e7"},"schema_version":"1.0","source":{"id":"1801.07853","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.07853","created_at":"2026-05-18T00:25:10Z"},{"alias_kind":"arxiv_version","alias_value":"1801.07853v1","created_at":"2026-05-18T00:25:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.07853","created_at":"2026-05-18T00:25:10Z"},{"alias_kind":"pith_short_12","alias_value":"GK43VP2RM2QU","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GK43VP2RM2QUUCDW","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GK43VP2R","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:bfc2ba4ea31abce42777b5ac92bd10b324e82a9bb01b2b56a72c95656ae900c5","target":"graph","created_at":"2026-05-18T00:25:10Z","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 (VQA) is of significant interest due to its potential to be a strong test of image understanding systems and to probe the connection between language and vision. Despite much recent progress, general VQA is far from a solved problem. In this paper, we focus on the VQA multiple-choice task, and provide some good practices for designing an effective VQA model that can capture language-vision interactions and perform joint reasoning. We explore mechanisms of incorporating part-of-speech (POS) tag guided attention, convolutional n-grams, triplet attention interactions bet","authors_text":"Charless Fowlkes, Liangjian Chen, Limin Wang, Xiaohui Xie, Xiaoyi Liu, Yu Qiao, Zhe Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-01-24T03:58:51Z","title":"Structured Triplet Learning with POS-tag Guided Attention for Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.07853","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":"sha256:62aabbc37fadd7e66c128c45c1e4459fcb4a5dac843c88f4efb8f9eec023e0bc","target":"record","created_at":"2026-05-18T00:25:10Z","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":"10011ef3bf218fce7ce21486a1ebba73fccaee7c94f79dc6aaeb362b542ad953","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-01-24T03:58:51Z","title_canon_sha256":"0fcce05340cc7b8174e5f900f856a54002b80737ae4c75615917cda73c8f26e7"},"schema_version":"1.0","source":{"id":"1801.07853","kind":"arxiv","version":1}},"canonical_sha256":"32b9babf5166a14a087666ea83f33e83e6e87d30bb97d11435a3189bbffc2c18","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32b9babf5166a14a087666ea83f33e83e6e87d30bb97d11435a3189bbffc2c18","first_computed_at":"2026-05-18T00:25:10.673760Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:25:10.673760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OZF0j8GaX9lz4j0TX9C6hLcqfsk12AzjLJAn6ZumNNydbOkPRWxczgiZbV83GQLkUl3wtSKa+NUF//fykNS5Bw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:25:10.674246Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.07853","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62aabbc37fadd7e66c128c45c1e4459fcb4a5dac843c88f4efb8f9eec023e0bc","sha256:bfc2ba4ea31abce42777b5ac92bd10b324e82a9bb01b2b56a72c95656ae900c5"],"state_sha256":"dbc402dc124c141326328650e28ea1e97684036953364a3085e87a20343ede71"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y1Qn2FX9idLKwuWSkcB64AIRT3PnBs3Z0T8p1FGSrfvjznKH+sellXAkekc/v+rE04emm9EVu0Alvnu35ZIxCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T11:04:39.130270Z","bundle_sha256":"b98ac5291ecb0df9a772000dedad971f514916f04807ec4b471f3881eb96b999"}}