{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:GCWPP6CEFUCFI2IFJA6BCJ55XG","short_pith_number":"pith:GCWPP6CE","canonical_record":{"source":{"id":"1606.00061","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-31T22:02:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"3c52c8f4d62da9cb6b6f1f8321b3a02619d6744fa928ce5d75939d36aab3ca37","abstract_canon_sha256":"ce83d4432456578f1ee9c8ae706a4e46ee6e9a59cd581cfe79eefa08d1eb4581"},"schema_version":"1.0"},"canonical_sha256":"30acf7f8442d04546905483c1127bdb98ba91bb7323da1f21862686ae4b52ecd","source":{"kind":"arxiv","id":"1606.00061","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.00061","created_at":"2026-05-18T00:52:31Z"},{"alias_kind":"arxiv_version","alias_value":"1606.00061v5","created_at":"2026-05-18T00:52:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.00061","created_at":"2026-05-18T00:52:31Z"},{"alias_kind":"pith_short_12","alias_value":"GCWPP6CEFUCF","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"GCWPP6CEFUCFI2IF","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"GCWPP6CE","created_at":"2026-05-18T12:30:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:GCWPP6CEFUCFI2IFJA6BCJ55XG","target":"record","payload":{"canonical_record":{"source":{"id":"1606.00061","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-31T22:02:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"3c52c8f4d62da9cb6b6f1f8321b3a02619d6744fa928ce5d75939d36aab3ca37","abstract_canon_sha256":"ce83d4432456578f1ee9c8ae706a4e46ee6e9a59cd581cfe79eefa08d1eb4581"},"schema_version":"1.0"},"canonical_sha256":"30acf7f8442d04546905483c1127bdb98ba91bb7323da1f21862686ae4b52ecd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:52:31.028757Z","signature_b64":"LCmjIzvCzjSWVKlFQoHV/+F8RA6VQEbmyZG5x+GcnfS+auc7A6+MPjf3AXXkfFGnmXqRZCvL1eyl7cIezmUYBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30acf7f8442d04546905483c1127bdb98ba91bb7323da1f21862686ae4b52ecd","last_reissued_at":"2026-05-18T00:52:31.028346Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:52:31.028346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1606.00061","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:52:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KM0A3YiHmXCHDm3LwvmgIxvCB1dtmoqfxzIYdQXXrI+MwwFquQguKbgaKjPmU7tYnLrrg3IMfikqSMztc9nsCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T14:22:37.311572Z"},"content_sha256":"ff32ec9ea433a103494157748235131f962148617f0cbd9361a65900157e7e79","schema_version":"1.0","event_id":"sha256:ff32ec9ea433a103494157748235131f962148617f0cbd9361a65900157e7e79"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:GCWPP6CEFUCFI2IFJA6BCJ55XG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical Question-Image Co-Attention for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Devi Parikh, Dhruv Batra, Jianwei Yang, Jiasen Lu","submitted_at":"2016-05-31T22:02:01Z","abstract_excerpt":"A number of recent works have proposed attention models for Visual Question Answering (VQA) that generate spatial maps highlighting image regions relevant to answering the question. In this paper, we argue that in addition to modeling \"where to look\" or visual attention, it is equally important to model \"what words to listen to\" or question attention. We present a novel co-attention model for VQA that jointly reasons about image and question attention. In addition, our model reasons about the question (and consequently the image via the co-attention mechanism) in a hierarchical fashion via a n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.00061","kind":"arxiv","version":5},"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":"2026-05-18T00:52:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NWXN+MoRgCUV1ncfIss0rkiJoUBn8RcG2Iv3hOccWmEmE7Yiz/wbdk65i5zEW9mgy5LkfmzVY/PgnxR3t8m5DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T14:22:37.312240Z"},"content_sha256":"b52fd0339723dc6ae8da91b005fd0762e47515f24dbd20590db6285982466528","schema_version":"1.0","event_id":"sha256:b52fd0339723dc6ae8da91b005fd0762e47515f24dbd20590db6285982466528"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GCWPP6CEFUCFI2IFJA6BCJ55XG/bundle.json","state_url":"https://pith.science/pith/GCWPP6CEFUCFI2IFJA6BCJ55XG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GCWPP6CEFUCFI2IFJA6BCJ55XG/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":"2026-05-26T14:22:37Z","links":{"resolver":"https://pith.science/pith/GCWPP6CEFUCFI2IFJA6BCJ55XG","bundle":"https://pith.science/pith/GCWPP6CEFUCFI2IFJA6BCJ55XG/bundle.json","state":"https://pith.science/pith/GCWPP6CEFUCFI2IFJA6BCJ55XG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GCWPP6CEFUCFI2IFJA6BCJ55XG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:GCWPP6CEFUCFI2IFJA6BCJ55XG","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":"ce83d4432456578f1ee9c8ae706a4e46ee6e9a59cd581cfe79eefa08d1eb4581","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-31T22:02:01Z","title_canon_sha256":"3c52c8f4d62da9cb6b6f1f8321b3a02619d6744fa928ce5d75939d36aab3ca37"},"schema_version":"1.0","source":{"id":"1606.00061","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.00061","created_at":"2026-05-18T00:52:31Z"},{"alias_kind":"arxiv_version","alias_value":"1606.00061v5","created_at":"2026-05-18T00:52:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.00061","created_at":"2026-05-18T00:52:31Z"},{"alias_kind":"pith_short_12","alias_value":"GCWPP6CEFUCF","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"GCWPP6CEFUCFI2IF","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"GCWPP6CE","created_at":"2026-05-18T12:30:19Z"}],"graph_snapshots":[{"event_id":"sha256:b52fd0339723dc6ae8da91b005fd0762e47515f24dbd20590db6285982466528","target":"graph","created_at":"2026-05-18T00:52:31Z","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":"A number of recent works have proposed attention models for Visual Question Answering (VQA) that generate spatial maps highlighting image regions relevant to answering the question. In this paper, we argue that in addition to modeling \"where to look\" or visual attention, it is equally important to model \"what words to listen to\" or question attention. We present a novel co-attention model for VQA that jointly reasons about image and question attention. In addition, our model reasons about the question (and consequently the image via the co-attention mechanism) in a hierarchical fashion via a n","authors_text":"Devi Parikh, Dhruv Batra, Jianwei Yang, Jiasen Lu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-31T22:02:01Z","title":"Hierarchical Question-Image Co-Attention for Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.00061","kind":"arxiv","version":5},"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:ff32ec9ea433a103494157748235131f962148617f0cbd9361a65900157e7e79","target":"record","created_at":"2026-05-18T00:52:31Z","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":"ce83d4432456578f1ee9c8ae706a4e46ee6e9a59cd581cfe79eefa08d1eb4581","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-31T22:02:01Z","title_canon_sha256":"3c52c8f4d62da9cb6b6f1f8321b3a02619d6744fa928ce5d75939d36aab3ca37"},"schema_version":"1.0","source":{"id":"1606.00061","kind":"arxiv","version":5}},"canonical_sha256":"30acf7f8442d04546905483c1127bdb98ba91bb7323da1f21862686ae4b52ecd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30acf7f8442d04546905483c1127bdb98ba91bb7323da1f21862686ae4b52ecd","first_computed_at":"2026-05-18T00:52:31.028346Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:52:31.028346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LCmjIzvCzjSWVKlFQoHV/+F8RA6VQEbmyZG5x+GcnfS+auc7A6+MPjf3AXXkfFGnmXqRZCvL1eyl7cIezmUYBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:52:31.028757Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.00061","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff32ec9ea433a103494157748235131f962148617f0cbd9361a65900157e7e79","sha256:b52fd0339723dc6ae8da91b005fd0762e47515f24dbd20590db6285982466528"],"state_sha256":"710f261f770d0e398ed19a98bb4670a0a1a4e82630ce75fe9686501ee1cc900f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"59cR2Ds3sLClerbaJWwmXwLMRoDBG38If2iNcgtiEBaZCYRRHYVvmQ4o2SaktwbgtN2yHKDKjFCN47wBUIMxCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T14:22:37.315884Z","bundle_sha256":"98767951e022f1c74260e8335f28e8322eb1e537907ddb72549e0f75d0938d08"}}