{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ZSL7SNG3MOLROCREOL2CZ54PSX","short_pith_number":"pith:ZSL7SNG3","canonical_record":{"source":{"id":"1904.01410","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-04-02T13:45:57Z","cross_cats_sorted":[],"title_canon_sha256":"3477abaf97a2ee4aa6c35dc6cc83316cb97a1c47a2be1b38da4160b25b6ea1f9","abstract_canon_sha256":"356f085d1be50b08ca90121e1ecb977d95686510065c9792b18f8d9d232eeb34"},"schema_version":"1.0"},"canonical_sha256":"cc97f934db6397170a2472f42cf78f95dfe644800a216cb3f48b17f0db2432be","source":{"kind":"arxiv","id":"1904.01410","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.01410","created_at":"2026-05-17T23:49:34Z"},{"alias_kind":"arxiv_version","alias_value":"1904.01410v1","created_at":"2026-05-17T23:49:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.01410","created_at":"2026-05-17T23:49:34Z"},{"alias_kind":"pith_short_12","alias_value":"ZSL7SNG3MOLR","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZSL7SNG3MOLROCRE","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZSL7SNG3","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ZSL7SNG3MOLROCREOL2CZ54PSX","target":"record","payload":{"canonical_record":{"source":{"id":"1904.01410","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-04-02T13:45:57Z","cross_cats_sorted":[],"title_canon_sha256":"3477abaf97a2ee4aa6c35dc6cc83316cb97a1c47a2be1b38da4160b25b6ea1f9","abstract_canon_sha256":"356f085d1be50b08ca90121e1ecb977d95686510065c9792b18f8d9d232eeb34"},"schema_version":"1.0"},"canonical_sha256":"cc97f934db6397170a2472f42cf78f95dfe644800a216cb3f48b17f0db2432be","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:34.723148Z","signature_b64":"DSN/EpUGcKxiSgsfHi8tvHssfpC/cpfAGj50acj0zC05OxlIXai27bhu5M71NaX20SmNHe+hEOxw2KyKnecrDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc97f934db6397170a2472f42cf78f95dfe644800a216cb3f48b17f0db2432be","last_reissued_at":"2026-05-17T23:49:34.722632Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:34.722632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.01410","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":"2026-05-17T23:49:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wKwD7KKTLAUmf0xLGRlKYjuYQD+ua62VxxVhpJnzRvhIwG1C/eZOKgtosVgcvn06P+RyvSDMEe2h097/KNO4BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T09:39:08.907740Z"},"content_sha256":"bcfd934d4aff2990f41f7db0b390b51108de123548f621fb5dec1115befb3be6","schema_version":"1.0","event_id":"sha256:bcfd934d4aff2990f41f7db0b390b51108de123548f621fb5dec1115befb3be6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ZSL7SNG3MOLROCREOL2CZ54PSX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Context and Attribute Grounded Dense Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Liu, Guojun Yin, Jing Shao, Lu Sheng, Nenghai Yu, Xiaogang Wang","submitted_at":"2019-04-02T13:45:57Z","abstract_excerpt":"Dense captioning aims at simultaneously localizing semantic regions and describing these regions-of-interest (ROIs) with short phrases or sentences in natural language. Previous studies have shown remarkable progresses, but they are often vulnerable to the aperture problem that a caption generated by the features inside one ROI lacks contextual coherence with its surrounding context in the input image. In this work, we investigate contextual reasoning based on multi-scale message propagations from the neighboring contents to the target ROIs. To this end, we design a novel end-to-end context an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.01410","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":"2026-05-17T23:49:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tbCglQF2es5hqeNEjR7/JIqZmfJM7j/SoW5OTRzRQfiBxHeIIGWZQPN877OCodR4eZxzRYAYrZOLMRAhF1rDAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T09:39:08.908460Z"},"content_sha256":"2d6adbf11d4c7ec9bd55149282c9eba04b7b4f93fcad50258cb570ce1854de58","schema_version":"1.0","event_id":"sha256:2d6adbf11d4c7ec9bd55149282c9eba04b7b4f93fcad50258cb570ce1854de58"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZSL7SNG3MOLROCREOL2CZ54PSX/bundle.json","state_url":"https://pith.science/pith/ZSL7SNG3MOLROCREOL2CZ54PSX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZSL7SNG3MOLROCREOL2CZ54PSX/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":"2026-05-26T09:39:08Z","links":{"resolver":"https://pith.science/pith/ZSL7SNG3MOLROCREOL2CZ54PSX","bundle":"https://pith.science/pith/ZSL7SNG3MOLROCREOL2CZ54PSX/bundle.json","state":"https://pith.science/pith/ZSL7SNG3MOLROCREOL2CZ54PSX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZSL7SNG3MOLROCREOL2CZ54PSX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZSL7SNG3MOLROCREOL2CZ54PSX","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":"356f085d1be50b08ca90121e1ecb977d95686510065c9792b18f8d9d232eeb34","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-04-02T13:45:57Z","title_canon_sha256":"3477abaf97a2ee4aa6c35dc6cc83316cb97a1c47a2be1b38da4160b25b6ea1f9"},"schema_version":"1.0","source":{"id":"1904.01410","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.01410","created_at":"2026-05-17T23:49:34Z"},{"alias_kind":"arxiv_version","alias_value":"1904.01410v1","created_at":"2026-05-17T23:49:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.01410","created_at":"2026-05-17T23:49:34Z"},{"alias_kind":"pith_short_12","alias_value":"ZSL7SNG3MOLR","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZSL7SNG3MOLROCRE","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZSL7SNG3","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:2d6adbf11d4c7ec9bd55149282c9eba04b7b4f93fcad50258cb570ce1854de58","target":"graph","created_at":"2026-05-17T23:49:34Z","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":"Dense captioning aims at simultaneously localizing semantic regions and describing these regions-of-interest (ROIs) with short phrases or sentences in natural language. Previous studies have shown remarkable progresses, but they are often vulnerable to the aperture problem that a caption generated by the features inside one ROI lacks contextual coherence with its surrounding context in the input image. In this work, we investigate contextual reasoning based on multi-scale message propagations from the neighboring contents to the target ROIs. To this end, we design a novel end-to-end context an","authors_text":"Bin Liu, Guojun Yin, Jing Shao, Lu Sheng, Nenghai Yu, Xiaogang Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-04-02T13:45:57Z","title":"Context and Attribute Grounded Dense Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.01410","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:bcfd934d4aff2990f41f7db0b390b51108de123548f621fb5dec1115befb3be6","target":"record","created_at":"2026-05-17T23:49:34Z","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":"356f085d1be50b08ca90121e1ecb977d95686510065c9792b18f8d9d232eeb34","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-04-02T13:45:57Z","title_canon_sha256":"3477abaf97a2ee4aa6c35dc6cc83316cb97a1c47a2be1b38da4160b25b6ea1f9"},"schema_version":"1.0","source":{"id":"1904.01410","kind":"arxiv","version":1}},"canonical_sha256":"cc97f934db6397170a2472f42cf78f95dfe644800a216cb3f48b17f0db2432be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc97f934db6397170a2472f42cf78f95dfe644800a216cb3f48b17f0db2432be","first_computed_at":"2026-05-17T23:49:34.722632Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:34.722632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DSN/EpUGcKxiSgsfHi8tvHssfpC/cpfAGj50acj0zC05OxlIXai27bhu5M71NaX20SmNHe+hEOxw2KyKnecrDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:34.723148Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.01410","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bcfd934d4aff2990f41f7db0b390b51108de123548f621fb5dec1115befb3be6","sha256:2d6adbf11d4c7ec9bd55149282c9eba04b7b4f93fcad50258cb570ce1854de58"],"state_sha256":"7086cd32ce109924e2b761e9b2a17f7bf158740ce32297987cadb969a3ae98f7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lUhe7vr9ewl3jln3s1YeM35i0R9R3utl35bMDGLjd77Rmo8E8VPj7x5tDCbIr0zdsIdXCnl1EmQkDmFxvxVnDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T09:39:08.912409Z","bundle_sha256":"f56be6b297e994d92b2034595907c26b80f3f4684087108d1b021118441dc0b7"}}