{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:3SJZ45X2UCLY445FEYNGWLMNQM","short_pith_number":"pith:3SJZ45X2","canonical_record":{"source":{"id":"1905.07841","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-20T01:56:06Z","cross_cats_sorted":[],"title_canon_sha256":"ea22c16804b133e556e3bc0691fc24377772874bca707e891d0bc70fe935d410","abstract_canon_sha256":"ea75bb97eedceed96f80c00d72908290e704a03e1506a3ae88db33f90f5fc32e"},"schema_version":"1.0"},"canonical_sha256":"dc939e76faa0978e73a5261a6b2d8d831a695f7913d3d88940617a64af80dc2a","source":{"kind":"arxiv","id":"1905.07841","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.07841","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"arxiv_version","alias_value":"1905.07841v1","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07841","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"pith_short_12","alias_value":"3SJZ45X2UCLY","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"3SJZ45X2UCLY445F","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"3SJZ45X2","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:3SJZ45X2UCLY445FEYNGWLMNQM","target":"record","payload":{"canonical_record":{"source":{"id":"1905.07841","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-20T01:56:06Z","cross_cats_sorted":[],"title_canon_sha256":"ea22c16804b133e556e3bc0691fc24377772874bca707e891d0bc70fe935d410","abstract_canon_sha256":"ea75bb97eedceed96f80c00d72908290e704a03e1506a3ae88db33f90f5fc32e"},"schema_version":"1.0"},"canonical_sha256":"dc939e76faa0978e73a5261a6b2d8d831a695f7913d3d88940617a64af80dc2a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:48.368616Z","signature_b64":"l8kePOkpRPFppyS/X9fz3VFdDtUmnJ21BHxPH322dONAXCI7b7ajTKnkG0G9dYFaPpp1L5MVBiRMuNi7HIrPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc939e76faa0978e73a5261a6b2d8d831a695f7913d3d88940617a64af80dc2a","last_reissued_at":"2026-05-17T23:45:48.368104Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:48.368104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.07841","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":"2026-05-17T23:45:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+7v7FMledAHdEsTZ7WSEnIWzrHZq0Z92QtEVibPZbukDfKym0sSwWTE1MLwb/Qs48iFujcTmy+eMcEO0rZeWCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T15:04:13.844910Z"},"content_sha256":"3ab3778d41da75911607143af2ab515e29c32bdae84390e7d17dfa9c05f28c40","schema_version":"1.0","event_id":"sha256:3ab3778d41da75911607143af2ab515e29c32bdae84390e7d17dfa9c05f28c40"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:3SJZ45X2UCLY445FEYNGWLMNQM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal Transformer with Multi-View Visual Representation for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Li, Jun Yu, Qingming Huang, Zhou Yu","submitted_at":"2019-05-20T01:56:06Z","abstract_excerpt":"Image captioning aims to automatically generate a natural language description of a given image, and most state-of-the-art models have adopted an encoder-decoder framework. The framework consists of a convolution neural network (CNN)-based image encoder that extracts region-based visual features from the input image, and an recurrent neural network (RNN)-based caption decoder that generates the output caption words based on the visual features with the attention mechanism. Despite the success of existing studies, current methods only model the co-attention that characterizes the inter-modal in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07841","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":""},"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":"2026-05-17T23:45:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yjfb87NFbGpRlg6sMr+5Ood6YzP+PnLe1XF24t7wJ3qPChxN3M8O7XDW1b6gqvWOgGdPDM08NtotcmfIS9PeDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T15:04:13.845593Z"},"content_sha256":"3311b0cdbe5071be3225ec516b48fc0e9cba6ef06fd796f203aa7ca0922e7f73","schema_version":"1.0","event_id":"sha256:3311b0cdbe5071be3225ec516b48fc0e9cba6ef06fd796f203aa7ca0922e7f73"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3SJZ45X2UCLY445FEYNGWLMNQM/bundle.json","state_url":"https://pith.science/pith/3SJZ45X2UCLY445FEYNGWLMNQM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3SJZ45X2UCLY445FEYNGWLMNQM/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":"2026-05-26T15:04:13Z","links":{"resolver":"https://pith.science/pith/3SJZ45X2UCLY445FEYNGWLMNQM","bundle":"https://pith.science/pith/3SJZ45X2UCLY445FEYNGWLMNQM/bundle.json","state":"https://pith.science/pith/3SJZ45X2UCLY445FEYNGWLMNQM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3SJZ45X2UCLY445FEYNGWLMNQM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:3SJZ45X2UCLY445FEYNGWLMNQM","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":"ea75bb97eedceed96f80c00d72908290e704a03e1506a3ae88db33f90f5fc32e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-20T01:56:06Z","title_canon_sha256":"ea22c16804b133e556e3bc0691fc24377772874bca707e891d0bc70fe935d410"},"schema_version":"1.0","source":{"id":"1905.07841","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.07841","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"arxiv_version","alias_value":"1905.07841v1","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07841","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"pith_short_12","alias_value":"3SJZ45X2UCLY","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"3SJZ45X2UCLY445F","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"3SJZ45X2","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:3311b0cdbe5071be3225ec516b48fc0e9cba6ef06fd796f203aa7ca0922e7f73","target":"graph","created_at":"2026-05-17T23:45:48Z","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":"Image captioning aims to automatically generate a natural language description of a given image, and most state-of-the-art models have adopted an encoder-decoder framework. The framework consists of a convolution neural network (CNN)-based image encoder that extracts region-based visual features from the input image, and an recurrent neural network (RNN)-based caption decoder that generates the output caption words based on the visual features with the attention mechanism. Despite the success of existing studies, current methods only model the co-attention that characterizes the inter-modal in","authors_text":"Jing Li, Jun Yu, Qingming Huang, Zhou Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-20T01:56:06Z","title":"Multimodal Transformer with Multi-View Visual Representation for Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07841","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":"sha256:3ab3778d41da75911607143af2ab515e29c32bdae84390e7d17dfa9c05f28c40","target":"record","created_at":"2026-05-17T23:45:48Z","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":"ea75bb97eedceed96f80c00d72908290e704a03e1506a3ae88db33f90f5fc32e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-20T01:56:06Z","title_canon_sha256":"ea22c16804b133e556e3bc0691fc24377772874bca707e891d0bc70fe935d410"},"schema_version":"1.0","source":{"id":"1905.07841","kind":"arxiv","version":1}},"canonical_sha256":"dc939e76faa0978e73a5261a6b2d8d831a695f7913d3d88940617a64af80dc2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc939e76faa0978e73a5261a6b2d8d831a695f7913d3d88940617a64af80dc2a","first_computed_at":"2026-05-17T23:45:48.368104Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:48.368104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l8kePOkpRPFppyS/X9fz3VFdDtUmnJ21BHxPH322dONAXCI7b7ajTKnkG0G9dYFaPpp1L5MVBiRMuNi7HIrPCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:48.368616Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.07841","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ab3778d41da75911607143af2ab515e29c32bdae84390e7d17dfa9c05f28c40","sha256:3311b0cdbe5071be3225ec516b48fc0e9cba6ef06fd796f203aa7ca0922e7f73"],"state_sha256":"0ecef7b484b98466877f4859bdbc51122fbfdb23967227667ae445b98cc3f3fa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pe1BivicWWqd9qTijVvZuoapbgkmFqoDF7sy7tepsYwPcaqQdQ4VkMRwbSQuBqrHr4gxIVjT5dJJWIfH212gBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T15:04:13.848998Z","bundle_sha256":"99235b0d71ddc28d08323aefd9ff82aa3ffd102a4e60123dd98958c0ec08e04a"}}