{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:UXVF35HNYLR3GHBJ4TD6GBJKCV","short_pith_number":"pith:UXVF35HN","canonical_record":{"source":{"id":"1805.07932","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-21T07:58:31Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"5a6de51a1fe0c5d2d00bf7c385af7deed4404a3b748cfc307b7aa3b85488bbeb","abstract_canon_sha256":"7ff5071328744c876a5892a59cfded478fdb93f8cc163c67713b93f09a0c8295"},"schema_version":"1.0"},"canonical_sha256":"a5ea5df4edc2e3b31c29e4c7e3052a155b23a5f3785ecd12d8a422f45aa39522","source":{"kind":"arxiv","id":"1805.07932","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.07932","created_at":"2026-05-18T00:02:49Z"},{"alias_kind":"arxiv_version","alias_value":"1805.07932v2","created_at":"2026-05-18T00:02:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07932","created_at":"2026-05-18T00:02:49Z"},{"alias_kind":"pith_short_12","alias_value":"UXVF35HNYLR3","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UXVF35HNYLR3GHBJ","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UXVF35HN","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:UXVF35HNYLR3GHBJ4TD6GBJKCV","target":"record","payload":{"canonical_record":{"source":{"id":"1805.07932","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-21T07:58:31Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"5a6de51a1fe0c5d2d00bf7c385af7deed4404a3b748cfc307b7aa3b85488bbeb","abstract_canon_sha256":"7ff5071328744c876a5892a59cfded478fdb93f8cc163c67713b93f09a0c8295"},"schema_version":"1.0"},"canonical_sha256":"a5ea5df4edc2e3b31c29e4c7e3052a155b23a5f3785ecd12d8a422f45aa39522","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:49.344780Z","signature_b64":"+V22Wm1aAOJgurW1QWW8scLHpEf9otBmKgdB+tO7Uju7aD7UfiDR7sbwQRjvVEgnWiqtZzBIjsScqEGp3/BKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5ea5df4edc2e3b31c29e4c7e3052a155b23a5f3785ecd12d8a422f45aa39522","last_reissued_at":"2026-05-18T00:02:49.343997Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:49.343997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.07932","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":"2026-05-18T00:02:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ImNLWlQWNzgl/1ArVZ+6QwtK9z5AkTV/i81HyPcSm+Xp0O92Dfr9i0L9Te7YBBwupnbMDU68x97ehSxFsmIyDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T02:09:04.977597Z"},"content_sha256":"a4c71e8858d409a9dd3ebf044e5c2ca48a7db47fd80c034007b68a751db3a7e9","schema_version":"1.0","event_id":"sha256:a4c71e8858d409a9dd3ebf044e5c2ca48a7db47fd80c034007b68a751db3a7e9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:UXVF35HNYLR3GHBJ4TD6GBJKCV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bilinear Attention Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Byoung-Tak Zhang, Jaehyun Jun, Jin-Hwa Kim","submitted_at":"2018-05-21T07:58:31Z","abstract_excerpt":"Attention networks in multimodal learning provide an efficient way to utilize given visual information selectively. However, the computational cost to learn attention distributions for every pair of multimodal input channels is prohibitively expensive. To solve this problem, co-attention builds two separate attention distributions for each modality neglecting the interaction between multimodal inputs. In this paper, we propose bilinear attention networks (BAN) that find bilinear attention distributions to utilize given vision-language information seamlessly. BAN considers bilinear interactions"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07932","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":"2026-05-18T00:02:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NRDALmrqlLgdeGrwZWycNPjDlesUwxi2isuWO+w43Tz07QGOWChNFmhMgT+WkOzwCQOUHbK2BqP+Z7HWJ09bCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T02:09:04.978305Z"},"content_sha256":"5675ce03dfaca3d7663de4d4df1b148cffe810491f6a9553b488563043d57f00","schema_version":"1.0","event_id":"sha256:5675ce03dfaca3d7663de4d4df1b148cffe810491f6a9553b488563043d57f00"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UXVF35HNYLR3GHBJ4TD6GBJKCV/bundle.json","state_url":"https://pith.science/pith/UXVF35HNYLR3GHBJ4TD6GBJKCV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UXVF35HNYLR3GHBJ4TD6GBJKCV/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":"2026-06-08T02:09:04Z","links":{"resolver":"https://pith.science/pith/UXVF35HNYLR3GHBJ4TD6GBJKCV","bundle":"https://pith.science/pith/UXVF35HNYLR3GHBJ4TD6GBJKCV/bundle.json","state":"https://pith.science/pith/UXVF35HNYLR3GHBJ4TD6GBJKCV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UXVF35HNYLR3GHBJ4TD6GBJKCV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:UXVF35HNYLR3GHBJ4TD6GBJKCV","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":"7ff5071328744c876a5892a59cfded478fdb93f8cc163c67713b93f09a0c8295","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-21T07:58:31Z","title_canon_sha256":"5a6de51a1fe0c5d2d00bf7c385af7deed4404a3b748cfc307b7aa3b85488bbeb"},"schema_version":"1.0","source":{"id":"1805.07932","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.07932","created_at":"2026-05-18T00:02:49Z"},{"alias_kind":"arxiv_version","alias_value":"1805.07932v2","created_at":"2026-05-18T00:02:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07932","created_at":"2026-05-18T00:02:49Z"},{"alias_kind":"pith_short_12","alias_value":"UXVF35HNYLR3","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UXVF35HNYLR3GHBJ","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UXVF35HN","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:5675ce03dfaca3d7663de4d4df1b148cffe810491f6a9553b488563043d57f00","target":"graph","created_at":"2026-05-18T00:02:49Z","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":"Attention networks in multimodal learning provide an efficient way to utilize given visual information selectively. However, the computational cost to learn attention distributions for every pair of multimodal input channels is prohibitively expensive. To solve this problem, co-attention builds two separate attention distributions for each modality neglecting the interaction between multimodal inputs. In this paper, we propose bilinear attention networks (BAN) that find bilinear attention distributions to utilize given vision-language information seamlessly. BAN considers bilinear interactions","authors_text":"Byoung-Tak Zhang, Jaehyun Jun, Jin-Hwa Kim","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-21T07:58:31Z","title":"Bilinear Attention Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07932","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:a4c71e8858d409a9dd3ebf044e5c2ca48a7db47fd80c034007b68a751db3a7e9","target":"record","created_at":"2026-05-18T00:02:49Z","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":"7ff5071328744c876a5892a59cfded478fdb93f8cc163c67713b93f09a0c8295","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-21T07:58:31Z","title_canon_sha256":"5a6de51a1fe0c5d2d00bf7c385af7deed4404a3b748cfc307b7aa3b85488bbeb"},"schema_version":"1.0","source":{"id":"1805.07932","kind":"arxiv","version":2}},"canonical_sha256":"a5ea5df4edc2e3b31c29e4c7e3052a155b23a5f3785ecd12d8a422f45aa39522","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a5ea5df4edc2e3b31c29e4c7e3052a155b23a5f3785ecd12d8a422f45aa39522","first_computed_at":"2026-05-18T00:02:49.343997Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:49.343997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+V22Wm1aAOJgurW1QWW8scLHpEf9otBmKgdB+tO7Uju7aD7UfiDR7sbwQRjvVEgnWiqtZzBIjsScqEGp3/BKAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:49.344780Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.07932","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4c71e8858d409a9dd3ebf044e5c2ca48a7db47fd80c034007b68a751db3a7e9","sha256:5675ce03dfaca3d7663de4d4df1b148cffe810491f6a9553b488563043d57f00"],"state_sha256":"b8624624e6f971839567cb54ccb97e0a549e46724a594e335075fa9d0acc2112"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aphsh2+n9tDt5ljuK6UnUnPxSd+8sQOqG/05fNH27RzdlbB/IeWCoHlbPYKiE7B7+Zz0BV8Q4pUWatPvX6CiBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T02:09:04.981933Z","bundle_sha256":"4891ad89868d222dea96264691186b42cb8383a9f6b2c33afd2a32b1737e9546"}}