{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:2O32EMSEZUUT27ITRYOSBJZ43C","short_pith_number":"pith:2O32EMSE","canonical_record":{"source":{"id":"1912.03098","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-06T13:21:16Z","cross_cats_sorted":[],"title_canon_sha256":"2f6e809da8321448b7a672f9d5769b58a4bcad2fc5bc8b62ecb18a188b497a19","abstract_canon_sha256":"e796e08638f4372e2590aa57a5f95ad47a9f4b7defd84feeadec07c3354c8ad8"},"schema_version":"1.0"},"canonical_sha256":"d3b7a23244cd293d7d138e1d20a73cd8910a0c178516ceff897c6c6ff80b44d5","source":{"kind":"arxiv","id":"1912.03098","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.03098","created_at":"2026-07-05T01:20:13Z"},{"alias_kind":"arxiv_version","alias_value":"1912.03098v4","created_at":"2026-07-05T01:20:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.03098","created_at":"2026-07-05T01:20:13Z"},{"alias_kind":"pith_short_12","alias_value":"2O32EMSEZUUT","created_at":"2026-07-05T01:20:13Z"},{"alias_kind":"pith_short_16","alias_value":"2O32EMSEZUUT27IT","created_at":"2026-07-05T01:20:13Z"},{"alias_kind":"pith_short_8","alias_value":"2O32EMSE","created_at":"2026-07-05T01:20:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:2O32EMSEZUUT27ITRYOSBJZ43C","target":"record","payload":{"canonical_record":{"source":{"id":"1912.03098","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-06T13:21:16Z","cross_cats_sorted":[],"title_canon_sha256":"2f6e809da8321448b7a672f9d5769b58a4bcad2fc5bc8b62ecb18a188b497a19","abstract_canon_sha256":"e796e08638f4372e2590aa57a5f95ad47a9f4b7defd84feeadec07c3354c8ad8"},"schema_version":"1.0"},"canonical_sha256":"d3b7a23244cd293d7d138e1d20a73cd8910a0c178516ceff897c6c6ff80b44d5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:20:13.857947Z","signature_b64":"44qbR6ErDxlznN9rMIWCsU1bjwPYBbsfxG2otNjFvNvG3fl3XhqzfbP8y4qOppjy/xif9uc6MzYSKb7qgatZAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3b7a23244cd293d7d138e1d20a73cd8910a0c178516ceff897c6c6ff80b44d5","last_reissued_at":"2026-07-05T01:20:13.857499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:20:13.857499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.03098","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:20:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qYoX96vFI9/J+RxzHRIoWDhJp4d5aDVWqrFAuhEpnJ/5XkU2EFPYyJINScyqhYucS9acpRv279BD15cuQ7jcAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T10:13:09.828881Z"},"content_sha256":"234b987d19eced0f666f4996f2d5259f22114f13f05e6d07fefea45dbabf1318","schema_version":"1.0","event_id":"sha256:234b987d19eced0f666f4996f2d5259f22114f13f05e6d07fefea45dbabf1318"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:2O32EMSEZUUT27ITRYOSBJZ43C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Connecting Vision and Language with Localized Narratives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jasper Uijlings, Jordi Pont-Tuset, Radu Soricut, Soravit Changpinyo, Vittorio Ferrari","submitted_at":"2019-12-06T13:21:16Z","abstract_excerpt":"We propose Localized Narratives, a new form of multimodal image annotations connecting vision and language. We ask annotators to describe an image with their voice while simultaneously hovering their mouse over the region they are describing. Since the voice and the mouse pointer are synchronized, we can localize every single word in the description. This dense visual grounding takes the form of a mouse trace segment per word and is unique to our data. We annotated 849k images with Localized Narratives: the whole COCO, Flickr30k, and ADE20K datasets, and 671k images of Open Images, all of whic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.03098","kind":"arxiv","version":4},"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/1912.03098/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":"2026-07-05T01:20:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yn0J1UBlJOMRpgwocjAQGcVu7WXLM6qKfVkzilgnpKSTLvSt85pzKpKwANwoh7d9lZ+5HpRNEWlF6Q+3gjH0DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T10:13:09.829274Z"},"content_sha256":"145704571e724716065846122ef8cc047b863a4f461a2dd35371b0c6e3179eea","schema_version":"1.0","event_id":"sha256:145704571e724716065846122ef8cc047b863a4f461a2dd35371b0c6e3179eea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2O32EMSEZUUT27ITRYOSBJZ43C/bundle.json","state_url":"https://pith.science/pith/2O32EMSEZUUT27ITRYOSBJZ43C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2O32EMSEZUUT27ITRYOSBJZ43C/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":"2026-07-19T10:13:09Z","links":{"resolver":"https://pith.science/pith/2O32EMSEZUUT27ITRYOSBJZ43C","bundle":"https://pith.science/pith/2O32EMSEZUUT27ITRYOSBJZ43C/bundle.json","state":"https://pith.science/pith/2O32EMSEZUUT27ITRYOSBJZ43C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2O32EMSEZUUT27ITRYOSBJZ43C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:2O32EMSEZUUT27ITRYOSBJZ43C","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":"e796e08638f4372e2590aa57a5f95ad47a9f4b7defd84feeadec07c3354c8ad8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-06T13:21:16Z","title_canon_sha256":"2f6e809da8321448b7a672f9d5769b58a4bcad2fc5bc8b62ecb18a188b497a19"},"schema_version":"1.0","source":{"id":"1912.03098","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.03098","created_at":"2026-07-05T01:20:13Z"},{"alias_kind":"arxiv_version","alias_value":"1912.03098v4","created_at":"2026-07-05T01:20:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.03098","created_at":"2026-07-05T01:20:13Z"},{"alias_kind":"pith_short_12","alias_value":"2O32EMSEZUUT","created_at":"2026-07-05T01:20:13Z"},{"alias_kind":"pith_short_16","alias_value":"2O32EMSEZUUT27IT","created_at":"2026-07-05T01:20:13Z"},{"alias_kind":"pith_short_8","alias_value":"2O32EMSE","created_at":"2026-07-05T01:20:13Z"}],"graph_snapshots":[{"event_id":"sha256:145704571e724716065846122ef8cc047b863a4f461a2dd35371b0c6e3179eea","target":"graph","created_at":"2026-07-05T01:20:13Z","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/1912.03098/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Localized Narratives, a new form of multimodal image annotations connecting vision and language. We ask annotators to describe an image with their voice while simultaneously hovering their mouse over the region they are describing. Since the voice and the mouse pointer are synchronized, we can localize every single word in the description. This dense visual grounding takes the form of a mouse trace segment per word and is unique to our data. We annotated 849k images with Localized Narratives: the whole COCO, Flickr30k, and ADE20K datasets, and 671k images of Open Images, all of whic","authors_text":"Jasper Uijlings, Jordi Pont-Tuset, Radu Soricut, Soravit Changpinyo, Vittorio Ferrari","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-06T13:21:16Z","title":"Connecting Vision and Language with Localized Narratives"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.03098","kind":"arxiv","version":4},"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":"sha256:234b987d19eced0f666f4996f2d5259f22114f13f05e6d07fefea45dbabf1318","target":"record","created_at":"2026-07-05T01:20:13Z","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":"e796e08638f4372e2590aa57a5f95ad47a9f4b7defd84feeadec07c3354c8ad8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-06T13:21:16Z","title_canon_sha256":"2f6e809da8321448b7a672f9d5769b58a4bcad2fc5bc8b62ecb18a188b497a19"},"schema_version":"1.0","source":{"id":"1912.03098","kind":"arxiv","version":4}},"canonical_sha256":"d3b7a23244cd293d7d138e1d20a73cd8910a0c178516ceff897c6c6ff80b44d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3b7a23244cd293d7d138e1d20a73cd8910a0c178516ceff897c6c6ff80b44d5","first_computed_at":"2026-07-05T01:20:13.857499Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:20:13.857499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"44qbR6ErDxlznN9rMIWCsU1bjwPYBbsfxG2otNjFvNvG3fl3XhqzfbP8y4qOppjy/xif9uc6MzYSKb7qgatZAA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:20:13.857947Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.03098","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:234b987d19eced0f666f4996f2d5259f22114f13f05e6d07fefea45dbabf1318","sha256:145704571e724716065846122ef8cc047b863a4f461a2dd35371b0c6e3179eea"],"state_sha256":"99fe8dd79c78f5a90fd5020c185ffd1a9b70aef45ead16d92f6469a162e4449f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7nn9yLERt0O0HHAljvA+dv7+YeDWLohidiYrAQw+ZF/ZMZZv1WAKIfksfCULOuP5y0OpLimaXVwA0SzJd9b9Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-19T10:13:09.831526Z","bundle_sha256":"5448807159371fa5fce03a7041dc1b82448752d9f41758eff497bb03e33ce5d1"}}