{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:GIOKCUSZJH2IB2KM24GMZTGHKB","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":"6045abced1d0e0ffc3a5a499a1d8de1d0f1f65d7a8f5f179f3a3e0d45bd9669e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-31T10:35:33Z","title_canon_sha256":"1a654adb6ab8096383eaba6e71265ff4ffc2cb2e9884c8d78e638edd8dfb0a8c"},"schema_version":"1.0","source":{"id":"2003.14080","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.14080","created_at":"2026-07-05T00:51:47Z"},{"alias_kind":"arxiv_version","alias_value":"2003.14080v1","created_at":"2026-07-05T00:51:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.14080","created_at":"2026-07-05T00:51:47Z"},{"alias_kind":"pith_short_12","alias_value":"GIOKCUSZJH2I","created_at":"2026-07-05T00:51:47Z"},{"alias_kind":"pith_short_16","alias_value":"GIOKCUSZJH2IB2KM","created_at":"2026-07-05T00:51:47Z"},{"alias_kind":"pith_short_8","alias_value":"GIOKCUSZ","created_at":"2026-07-05T00:51:47Z"}],"graph_snapshots":[{"event_id":"sha256:ad5da45083eadea77c11734b64f7f734debdcb1de0efdb13e229fbf22899ca6e","target":"graph","created_at":"2026-07-05T00:51:47Z","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/2003.14080/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent progress on fine-grained visual recognition and visual question answering has featured Bilinear Pooling, which effectively models the 2$^{nd}$ order interactions across multi-modal inputs. Nevertheless, there has not been evidence in support of building such interactions concurrently with attention mechanism for image captioning. In this paper, we introduce a unified attention block -- X-Linear attention block, that fully employs bilinear pooling to selectively capitalize on visual information or perform multi-modal reasoning. Technically, X-Linear attention block simultaneously exploit","authors_text":"Tao Mei, Ting Yao, Yehao Li, Yingwei Pan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-31T10:35:33Z","title":"X-Linear Attention Networks for Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.14080","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":"sha256:2bfa13a282a719a42b52280c4a5f2592e4a881154046d6164f95dde6423127f5","target":"record","created_at":"2026-07-05T00:51:47Z","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":"6045abced1d0e0ffc3a5a499a1d8de1d0f1f65d7a8f5f179f3a3e0d45bd9669e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-31T10:35:33Z","title_canon_sha256":"1a654adb6ab8096383eaba6e71265ff4ffc2cb2e9884c8d78e638edd8dfb0a8c"},"schema_version":"1.0","source":{"id":"2003.14080","kind":"arxiv","version":1}},"canonical_sha256":"321ca1525949f480e94cd70cccccc75067c4355cac528e88a0c7ed0c30a4fb07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"321ca1525949f480e94cd70cccccc75067c4355cac528e88a0c7ed0c30a4fb07","first_computed_at":"2026-07-05T00:51:47.771061Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:51:47.771061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5G34CjTfHxsV1C80x1UBwqsRxQ2sm3h4aKm4p9AlN8sXTqu3FQ4RMrW5WjOtMEd0vvBbw1Wg1fhsM8ozig7eCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:51:47.771438Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.14080","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2bfa13a282a719a42b52280c4a5f2592e4a881154046d6164f95dde6423127f5","sha256:ad5da45083eadea77c11734b64f7f734debdcb1de0efdb13e229fbf22899ca6e"],"state_sha256":"62498f8678e790929e6d143660fb161afbd3890a69f36c9ffb2a2c3570f8bcd8"}