{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:SM7GJ4CLRAQWDWN2FQ5Y7NE44F","short_pith_number":"pith:SM7GJ4CL","canonical_record":{"source":{"id":"1511.02274","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-07T00:43:32Z","cross_cats_sorted":["cs.CL","cs.CV","cs.NE"],"title_canon_sha256":"45297ebbf372e572406775eefa22de40d544d7c7f35589cc6189054f5541f54a","abstract_canon_sha256":"922536800aed304e7b011880cb8fc8290c579246e39f721b3d240268fd4deabf"},"schema_version":"1.0"},"canonical_sha256":"933e64f04b882161d9ba2c3b8fb49ce1551cd71cec9154c3115d63dfb5c20434","source":{"kind":"arxiv","id":"1511.02274","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.02274","created_at":"2026-05-18T01:22:00Z"},{"alias_kind":"arxiv_version","alias_value":"1511.02274v2","created_at":"2026-05-18T01:22:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.02274","created_at":"2026-05-18T01:22:00Z"},{"alias_kind":"pith_short_12","alias_value":"SM7GJ4CLRAQW","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_16","alias_value":"SM7GJ4CLRAQWDWN2","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_8","alias_value":"SM7GJ4CL","created_at":"2026-05-18T12:29:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:SM7GJ4CLRAQWDWN2FQ5Y7NE44F","target":"record","payload":{"canonical_record":{"source":{"id":"1511.02274","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-07T00:43:32Z","cross_cats_sorted":["cs.CL","cs.CV","cs.NE"],"title_canon_sha256":"45297ebbf372e572406775eefa22de40d544d7c7f35589cc6189054f5541f54a","abstract_canon_sha256":"922536800aed304e7b011880cb8fc8290c579246e39f721b3d240268fd4deabf"},"schema_version":"1.0"},"canonical_sha256":"933e64f04b882161d9ba2c3b8fb49ce1551cd71cec9154c3115d63dfb5c20434","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:22:00.604088Z","signature_b64":"BbbT4Ar54XxgVZRp5QI1vKGJKqxDd5IdVN9GLIQeOWjZBndX5ShisFaI0pC2Lq1Yp2aFoBlkjaSGdHAZQkI6Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"933e64f04b882161d9ba2c3b8fb49ce1551cd71cec9154c3115d63dfb5c20434","last_reissued_at":"2026-05-18T01:22:00.603542Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:22:00.603542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1511.02274","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":"2026-05-18T01:22:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"egB5qVwbEiV5LfsBzQRbaTLTVMfJ7JIyitNW0uG2TiuXKOuYW/FW9PPOZ5+BaootAYa6A/i1vaVKmAkyMF4xCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T10:06:21.952028Z"},"content_sha256":"64764450a2b87dee0e01f816880771f92e26d9c08a44544534ae08d145a25a7e","schema_version":"1.0","event_id":"sha256:64764450a2b87dee0e01f816880771f92e26d9c08a44544534ae08d145a25a7e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:SM7GJ4CLRAQWDWN2FQ5Y7NE44F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stacked Attention Networks for Image Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Alex Smola, Jianfeng Gao, Li Deng, Xiaodong He, Zichao Yang","submitted_at":"2015-11-07T00:43:32Z","abstract_excerpt":"This paper presents stacked attention networks (SANs) that learn to answer natural language questions from images. SANs use semantic representation of a question as query to search for the regions in an image that are related to the answer. We argue that image question answering (QA) often requires multiple steps of reasoning. Thus, we develop a multiple-layer SAN in which we query an image multiple times to infer the answer progressively. Experiments conducted on four image QA data sets demonstrate that the proposed SANs significantly outperform previous state-of-the-art approaches. The visua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.02274","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":""},"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":"2026-05-18T01:22:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B1jaduhTfSYNbbqoIdHb3nVZK+soGYVEcv7RCWU3xK6nKmGz8WQ1gvUYO/OlXELe0JjK3kALGOcamNAXei9AAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T10:06:21.952462Z"},"content_sha256":"cbd91f04d4854ffd6d7ecf6904564c673f619cf0011b5138455f455dbd630bd0","schema_version":"1.0","event_id":"sha256:cbd91f04d4854ffd6d7ecf6904564c673f619cf0011b5138455f455dbd630bd0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SM7GJ4CLRAQWDWN2FQ5Y7NE44F/bundle.json","state_url":"https://pith.science/pith/SM7GJ4CLRAQWDWN2FQ5Y7NE44F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SM7GJ4CLRAQWDWN2FQ5Y7NE44F/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":"2026-05-25T10:06:21Z","links":{"resolver":"https://pith.science/pith/SM7GJ4CLRAQWDWN2FQ5Y7NE44F","bundle":"https://pith.science/pith/SM7GJ4CLRAQWDWN2FQ5Y7NE44F/bundle.json","state":"https://pith.science/pith/SM7GJ4CLRAQWDWN2FQ5Y7NE44F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SM7GJ4CLRAQWDWN2FQ5Y7NE44F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:SM7GJ4CLRAQWDWN2FQ5Y7NE44F","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":"922536800aed304e7b011880cb8fc8290c579246e39f721b3d240268fd4deabf","cross_cats_sorted":["cs.CL","cs.CV","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-07T00:43:32Z","title_canon_sha256":"45297ebbf372e572406775eefa22de40d544d7c7f35589cc6189054f5541f54a"},"schema_version":"1.0","source":{"id":"1511.02274","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.02274","created_at":"2026-05-18T01:22:00Z"},{"alias_kind":"arxiv_version","alias_value":"1511.02274v2","created_at":"2026-05-18T01:22:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.02274","created_at":"2026-05-18T01:22:00Z"},{"alias_kind":"pith_short_12","alias_value":"SM7GJ4CLRAQW","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_16","alias_value":"SM7GJ4CLRAQWDWN2","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_8","alias_value":"SM7GJ4CL","created_at":"2026-05-18T12:29:42Z"}],"graph_snapshots":[{"event_id":"sha256:cbd91f04d4854ffd6d7ecf6904564c673f619cf0011b5138455f455dbd630bd0","target":"graph","created_at":"2026-05-18T01:22:00Z","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":"This paper presents stacked attention networks (SANs) that learn to answer natural language questions from images. SANs use semantic representation of a question as query to search for the regions in an image that are related to the answer. We argue that image question answering (QA) often requires multiple steps of reasoning. Thus, we develop a multiple-layer SAN in which we query an image multiple times to infer the answer progressively. Experiments conducted on four image QA data sets demonstrate that the proposed SANs significantly outperform previous state-of-the-art approaches. The visua","authors_text":"Alex Smola, Jianfeng Gao, Li Deng, Xiaodong He, Zichao Yang","cross_cats":["cs.CL","cs.CV","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-07T00:43:32Z","title":"Stacked Attention Networks for Image Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.02274","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":"sha256:64764450a2b87dee0e01f816880771f92e26d9c08a44544534ae08d145a25a7e","target":"record","created_at":"2026-05-18T01:22:00Z","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":"922536800aed304e7b011880cb8fc8290c579246e39f721b3d240268fd4deabf","cross_cats_sorted":["cs.CL","cs.CV","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-07T00:43:32Z","title_canon_sha256":"45297ebbf372e572406775eefa22de40d544d7c7f35589cc6189054f5541f54a"},"schema_version":"1.0","source":{"id":"1511.02274","kind":"arxiv","version":2}},"canonical_sha256":"933e64f04b882161d9ba2c3b8fb49ce1551cd71cec9154c3115d63dfb5c20434","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"933e64f04b882161d9ba2c3b8fb49ce1551cd71cec9154c3115d63dfb5c20434","first_computed_at":"2026-05-18T01:22:00.603542Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:22:00.603542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BbbT4Ar54XxgVZRp5QI1vKGJKqxDd5IdVN9GLIQeOWjZBndX5ShisFaI0pC2Lq1Yp2aFoBlkjaSGdHAZQkI6Cw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:22:00.604088Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.02274","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64764450a2b87dee0e01f816880771f92e26d9c08a44544534ae08d145a25a7e","sha256:cbd91f04d4854ffd6d7ecf6904564c673f619cf0011b5138455f455dbd630bd0"],"state_sha256":"3638cb5f8f054f6a68a4ff844cefc36aa345d336fb88092fe66038cd8d33e9cd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F5N44kRNODa/6Z0ZfQWgMJXXIlxOtDVI2xENTYp9fajNF0GWxBbA4YemjfEGiS7csrHTjLtLIn2bCuTPNLaUDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T10:06:21.955836Z","bundle_sha256":"548b281b697e1bfc3ddf3041b9467c02b1aa3b316630d8cd0a589c0e8509f5ec"}}