{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:JNBF5X4EAVXNNL5JT5EYQFZE5I","short_pith_number":"pith:JNBF5X4E","canonical_record":{"source":{"id":"2208.11253","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-24T01:18:13Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"1612712787f780af5a840b6a32d56ec88274d3b033fe7aefcf3211c1dcdd9ffc","abstract_canon_sha256":"42186cedcf43537682bf8fb95cf815cd574952c59853387a26ff48cf3e48e60e"},"schema_version":"1.0"},"canonical_sha256":"4b425edf84056ed6afa99f49881724ea0f52d5a985163c6ae6fd27a4d234bf62","source":{"kind":"arxiv","id":"2208.11253","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.11253","created_at":"2026-07-05T04:51:12Z"},{"alias_kind":"arxiv_version","alias_value":"2208.11253v1","created_at":"2026-07-05T04:51:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.11253","created_at":"2026-07-05T04:51:12Z"},{"alias_kind":"pith_short_12","alias_value":"JNBF5X4EAVXN","created_at":"2026-07-05T04:51:12Z"},{"alias_kind":"pith_short_16","alias_value":"JNBF5X4EAVXNNL5J","created_at":"2026-07-05T04:51:12Z"},{"alias_kind":"pith_short_8","alias_value":"JNBF5X4E","created_at":"2026-07-05T04:51:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:JNBF5X4EAVXNNL5JT5EYQFZE5I","target":"record","payload":{"canonical_record":{"source":{"id":"2208.11253","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-24T01:18:13Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"1612712787f780af5a840b6a32d56ec88274d3b033fe7aefcf3211c1dcdd9ffc","abstract_canon_sha256":"42186cedcf43537682bf8fb95cf815cd574952c59853387a26ff48cf3e48e60e"},"schema_version":"1.0"},"canonical_sha256":"4b425edf84056ed6afa99f49881724ea0f52d5a985163c6ae6fd27a4d234bf62","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:51:12.970667Z","signature_b64":"cLj+fTf7gE9hx6AVOk22XVlMuSFr4BImMlgfTfX9BIBTDzrbGzgpeFSHeggT5HHsPKP9XCfsouQStwBBv5TjBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b425edf84056ed6afa99f49881724ea0f52d5a985163c6ae6fd27a4d234bf62","last_reissued_at":"2026-07-05T04:51:12.970241Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:51:12.970241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.11253","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":"2026-07-05T04:51:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WMBcpM1B9wItsc79eewTPLvff2JvM807IQJD6raHaGKrUDfz4T5zngHEWh/eSRUpUl+C8vG8MdGNnloP1w+fDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T06:38:24.898442Z"},"content_sha256":"82a88df355428c722d370b162cd8851c33ed91957ed57ecafcbc2bdca520b4bc","schema_version":"1.0","event_id":"sha256:82a88df355428c722d370b162cd8851c33ed91957ed57ecafcbc2bdca520b4bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:JNBF5X4EAVXNNL5JT5EYQFZE5I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FashionVQA: A Domain-Specific Visual Question Answering System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Anupama Joshi, Ata Mahjoubfar, Min Wang","submitted_at":"2022-08-24T01:18:13Z","abstract_excerpt":"Humans apprehend the world through various sensory modalities, yet language is their predominant communication channel. Machine learning systems need to draw on the same multimodal richness to have informed discourses with humans in natural language; this is particularly true for systems specialized in visually-dense information, such as dialogue, recommendation, and search engines for clothing. To this end, we train a visual question answering (VQA) system to answer complex natural language questions about apparel in fashion photoshoot images. The key to the successful training of our VQA mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.11253","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/2208.11253/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":"2026-07-05T04:51:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dqXhrwW4ekHM31cF9s2ObveTkqHaYWe7xO+hH2wSlMOsqCr82ck0Xlf2/2Fh/U2+116RnNd1r8HbTsdHuIVdAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T06:38:24.898985Z"},"content_sha256":"22ac05793897aa869207440bee00436faa90583a0b6d376d7c06fe907020fee9","schema_version":"1.0","event_id":"sha256:22ac05793897aa869207440bee00436faa90583a0b6d376d7c06fe907020fee9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JNBF5X4EAVXNNL5JT5EYQFZE5I/bundle.json","state_url":"https://pith.science/pith/JNBF5X4EAVXNNL5JT5EYQFZE5I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JNBF5X4EAVXNNL5JT5EYQFZE5I/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":"2026-08-12T06:38:24Z","links":{"resolver":"https://pith.science/pith/JNBF5X4EAVXNNL5JT5EYQFZE5I","bundle":"https://pith.science/pith/JNBF5X4EAVXNNL5JT5EYQFZE5I/bundle.json","state":"https://pith.science/pith/JNBF5X4EAVXNNL5JT5EYQFZE5I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JNBF5X4EAVXNNL5JT5EYQFZE5I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:JNBF5X4EAVXNNL5JT5EYQFZE5I","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":"42186cedcf43537682bf8fb95cf815cd574952c59853387a26ff48cf3e48e60e","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-24T01:18:13Z","title_canon_sha256":"1612712787f780af5a840b6a32d56ec88274d3b033fe7aefcf3211c1dcdd9ffc"},"schema_version":"1.0","source":{"id":"2208.11253","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.11253","created_at":"2026-07-05T04:51:12Z"},{"alias_kind":"arxiv_version","alias_value":"2208.11253v1","created_at":"2026-07-05T04:51:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.11253","created_at":"2026-07-05T04:51:12Z"},{"alias_kind":"pith_short_12","alias_value":"JNBF5X4EAVXN","created_at":"2026-07-05T04:51:12Z"},{"alias_kind":"pith_short_16","alias_value":"JNBF5X4EAVXNNL5J","created_at":"2026-07-05T04:51:12Z"},{"alias_kind":"pith_short_8","alias_value":"JNBF5X4E","created_at":"2026-07-05T04:51:12Z"}],"graph_snapshots":[{"event_id":"sha256:22ac05793897aa869207440bee00436faa90583a0b6d376d7c06fe907020fee9","target":"graph","created_at":"2026-07-05T04:51:12Z","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/2208.11253/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans apprehend the world through various sensory modalities, yet language is their predominant communication channel. Machine learning systems need to draw on the same multimodal richness to have informed discourses with humans in natural language; this is particularly true for systems specialized in visually-dense information, such as dialogue, recommendation, and search engines for clothing. To this end, we train a visual question answering (VQA) system to answer complex natural language questions about apparel in fashion photoshoot images. The key to the successful training of our VQA mod","authors_text":"Anupama Joshi, Ata Mahjoubfar, Min Wang","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-24T01:18:13Z","title":"FashionVQA: A Domain-Specific Visual Question Answering System"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.11253","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":"sha256:82a88df355428c722d370b162cd8851c33ed91957ed57ecafcbc2bdca520b4bc","target":"record","created_at":"2026-07-05T04:51:12Z","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":"42186cedcf43537682bf8fb95cf815cd574952c59853387a26ff48cf3e48e60e","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-24T01:18:13Z","title_canon_sha256":"1612712787f780af5a840b6a32d56ec88274d3b033fe7aefcf3211c1dcdd9ffc"},"schema_version":"1.0","source":{"id":"2208.11253","kind":"arxiv","version":1}},"canonical_sha256":"4b425edf84056ed6afa99f49881724ea0f52d5a985163c6ae6fd27a4d234bf62","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b425edf84056ed6afa99f49881724ea0f52d5a985163c6ae6fd27a4d234bf62","first_computed_at":"2026-07-05T04:51:12.970241Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:51:12.970241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cLj+fTf7gE9hx6AVOk22XVlMuSFr4BImMlgfTfX9BIBTDzrbGzgpeFSHeggT5HHsPKP9XCfsouQStwBBv5TjBw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:51:12.970667Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.11253","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82a88df355428c722d370b162cd8851c33ed91957ed57ecafcbc2bdca520b4bc","sha256:22ac05793897aa869207440bee00436faa90583a0b6d376d7c06fe907020fee9"],"state_sha256":"17328dbfdace5bde568b2bca0c36c461ae8cf896e87cb6fa80412511a1407326"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J9R91l7wj14GPWENRX7H4psJ9MCjZ5hXRP3vXQ0M38U5HJiIyZhKDNy3s/ab7QsBhNcX6sLnpiyUPU37WdJ0CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T06:38:24.904258Z","bundle_sha256":"39e88ac6a08c89a1ac6794dce6e70c511a2c446294593e08202cb4353db3b81f"}}