{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:GQWWUJOLTAAEDK5JGBWVX44PBN","short_pith_number":"pith:GQWWUJOL","canonical_record":{"source":{"id":"1906.05963","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-14T00:00:29Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c65b965d5edad040a27cbb8190fda40792fc2836dfc35b59400a1a08efbdfc32","abstract_canon_sha256":"eaa60a35fa661a81ec4d8e8d93d9f227b7662a73ce726fb8ec9809f0f01c17e2"},"schema_version":"1.0"},"canonical_sha256":"342d6a25cb980041aba9306d5bf38f0b6d63eb7a232a3de3040def63b4e92aa9","source":{"kind":"arxiv","id":"1906.05963","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.05963","created_at":"2026-07-05T00:32:50Z"},{"alias_kind":"arxiv_version","alias_value":"1906.05963v2","created_at":"2026-07-05T00:32:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05963","created_at":"2026-07-05T00:32:50Z"},{"alias_kind":"pith_short_12","alias_value":"GQWWUJOLTAAE","created_at":"2026-07-05T00:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"GQWWUJOLTAAEDK5J","created_at":"2026-07-05T00:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"GQWWUJOL","created_at":"2026-07-05T00:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:GQWWUJOLTAAEDK5JGBWVX44PBN","target":"record","payload":{"canonical_record":{"source":{"id":"1906.05963","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-14T00:00:29Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c65b965d5edad040a27cbb8190fda40792fc2836dfc35b59400a1a08efbdfc32","abstract_canon_sha256":"eaa60a35fa661a81ec4d8e8d93d9f227b7662a73ce726fb8ec9809f0f01c17e2"},"schema_version":"1.0"},"canonical_sha256":"342d6a25cb980041aba9306d5bf38f0b6d63eb7a232a3de3040def63b4e92aa9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:32:50.178610Z","signature_b64":"q0H03k5smVe1gTObe2FeLOWLvDVs865cfBBVW0yNZIpBo5G9KFXHZmV6i2qw/FmAd6b7MDEvFUDxyvYqKguBBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"342d6a25cb980041aba9306d5bf38f0b6d63eb7a232a3de3040def63b4e92aa9","last_reissued_at":"2026-07-05T00:32:50.178212Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:32:50.178212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.05963","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":"2026-07-05T00:32:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M+QPrQzCTfGjEopwHlOyJrdYi4zuV6n1d8ptCXbkWT2Cv83+F9H00NCtL4ms+vVTqbFD7xnOdtmcAxIjUUu9DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T13:30:04.605266Z"},"content_sha256":"49eac5abb6f19ab7df4716a9859df698c4741b82147fac87b1dda6ffab09fe5d","schema_version":"1.0","event_id":"sha256:49eac5abb6f19ab7df4716a9859df698c4741b82147fac87b1dda6ffab09fe5d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:GQWWUJOLTAAEDK5JGBWVX44PBN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Image Captioning: Transforming Objects into Words","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Armin Kappeler, Joao Soares, Kofi Boakye, Simao Herdade","submitted_at":"2019-06-14T00:00:29Z","abstract_excerpt":"Image captioning models typically follow an encoder-decoder architecture which uses abstract image feature vectors as input to the encoder. One of the most successful algorithms uses feature vectors extracted from the region proposals obtained from an object detector. In this work we introduce the Object Relation Transformer, that builds upon this approach by explicitly incorporating information about the spatial relationship between input detected objects through geometric attention. Quantitative and qualitative results demonstrate the importance of such geometric attention for image captioni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05963","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1906.05963/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T00:32:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nna4h861u0n77yeWD9jfUJbBqOrjt5KTeJ6cCGdyJ6ygLtbC5bpFQSBzoBW6miBy+uB/7g9aoGGflV7TaL2zDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T13:30:04.605955Z"},"content_sha256":"5875fd57a23ec09e009f6bdc2c5d0e6738d9d062fd75e73d3f0d79cb760f1468","schema_version":"1.0","event_id":"sha256:5875fd57a23ec09e009f6bdc2c5d0e6738d9d062fd75e73d3f0d79cb760f1468"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GQWWUJOLTAAEDK5JGBWVX44PBN/bundle.json","state_url":"https://pith.science/pith/GQWWUJOLTAAEDK5JGBWVX44PBN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GQWWUJOLTAAEDK5JGBWVX44PBN/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":"2026-08-19T13:30:04Z","links":{"resolver":"https://pith.science/pith/GQWWUJOLTAAEDK5JGBWVX44PBN","bundle":"https://pith.science/pith/GQWWUJOLTAAEDK5JGBWVX44PBN/bundle.json","state":"https://pith.science/pith/GQWWUJOLTAAEDK5JGBWVX44PBN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GQWWUJOLTAAEDK5JGBWVX44PBN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:GQWWUJOLTAAEDK5JGBWVX44PBN","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":"eaa60a35fa661a81ec4d8e8d93d9f227b7662a73ce726fb8ec9809f0f01c17e2","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-14T00:00:29Z","title_canon_sha256":"c65b965d5edad040a27cbb8190fda40792fc2836dfc35b59400a1a08efbdfc32"},"schema_version":"1.0","source":{"id":"1906.05963","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.05963","created_at":"2026-07-05T00:32:50Z"},{"alias_kind":"arxiv_version","alias_value":"1906.05963v2","created_at":"2026-07-05T00:32:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05963","created_at":"2026-07-05T00:32:50Z"},{"alias_kind":"pith_short_12","alias_value":"GQWWUJOLTAAE","created_at":"2026-07-05T00:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"GQWWUJOLTAAEDK5J","created_at":"2026-07-05T00:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"GQWWUJOL","created_at":"2026-07-05T00:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:5875fd57a23ec09e009f6bdc2c5d0e6738d9d062fd75e73d3f0d79cb760f1468","target":"graph","created_at":"2026-07-05T00:32:50Z","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/1906.05963/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image captioning models typically follow an encoder-decoder architecture which uses abstract image feature vectors as input to the encoder. One of the most successful algorithms uses feature vectors extracted from the region proposals obtained from an object detector. In this work we introduce the Object Relation Transformer, that builds upon this approach by explicitly incorporating information about the spatial relationship between input detected objects through geometric attention. Quantitative and qualitative results demonstrate the importance of such geometric attention for image captioni","authors_text":"Armin Kappeler, Joao Soares, Kofi Boakye, Simao Herdade","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-14T00:00:29Z","title":"Image Captioning: Transforming Objects into Words"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05963","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":"sha256:49eac5abb6f19ab7df4716a9859df698c4741b82147fac87b1dda6ffab09fe5d","target":"record","created_at":"2026-07-05T00:32:50Z","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":"eaa60a35fa661a81ec4d8e8d93d9f227b7662a73ce726fb8ec9809f0f01c17e2","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-14T00:00:29Z","title_canon_sha256":"c65b965d5edad040a27cbb8190fda40792fc2836dfc35b59400a1a08efbdfc32"},"schema_version":"1.0","source":{"id":"1906.05963","kind":"arxiv","version":2}},"canonical_sha256":"342d6a25cb980041aba9306d5bf38f0b6d63eb7a232a3de3040def63b4e92aa9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"342d6a25cb980041aba9306d5bf38f0b6d63eb7a232a3de3040def63b4e92aa9","first_computed_at":"2026-07-05T00:32:50.178212Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:32:50.178212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q0H03k5smVe1gTObe2FeLOWLvDVs865cfBBVW0yNZIpBo5G9KFXHZmV6i2qw/FmAd6b7MDEvFUDxyvYqKguBBA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:32:50.178610Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.05963","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49eac5abb6f19ab7df4716a9859df698c4741b82147fac87b1dda6ffab09fe5d","sha256:5875fd57a23ec09e009f6bdc2c5d0e6738d9d062fd75e73d3f0d79cb760f1468"],"state_sha256":"762388733dac5fdd8bc6832120c6eede38cefa6d9f9105c9fa33a3a8e870e55e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UJW/8OU3TYQRq0FNbUXSOhZTW4NglbtMYBp6/7TMwVIxXCVgtwoRvDG0WxGbQUJ++kvLHM545ZcmOd67XnHxAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T13:30:04.612065Z","bundle_sha256":"84f13d937a3a0d0b4aecc5caa31963ad5f1b534defccf7a4a9583cf2829ae29b"}}