{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:LQO4VHO4WEWS3DZTTIUF473IB4","short_pith_number":"pith:LQO4VHO4","canonical_record":{"source":{"id":"2006.11807","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-21T14:10:47Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8b9639ee570d375ebf4db78f6ee1918cf89bd93ec3e1663045078ce31a749b7f","abstract_canon_sha256":"770d0ade54377d1e15b43162a739ce10c9f983804c82bb4cbf7c2502a3829a3b"},"schema_version":"1.0"},"canonical_sha256":"5c1dca9ddcb12d2d8f339a285e7f680f2b015708bd79bf47f9a215f107bd2d24","source":{"kind":"arxiv","id":"2006.11807","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.11807","created_at":"2026-07-05T01:11:53Z"},{"alias_kind":"arxiv_version","alias_value":"2006.11807v1","created_at":"2026-07-05T01:11:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.11807","created_at":"2026-07-05T01:11:53Z"},{"alias_kind":"pith_short_12","alias_value":"LQO4VHO4WEWS","created_at":"2026-07-05T01:11:53Z"},{"alias_kind":"pith_short_16","alias_value":"LQO4VHO4WEWS3DZT","created_at":"2026-07-05T01:11:53Z"},{"alias_kind":"pith_short_8","alias_value":"LQO4VHO4","created_at":"2026-07-05T01:11:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:LQO4VHO4WEWS3DZTTIUF473IB4","target":"record","payload":{"canonical_record":{"source":{"id":"2006.11807","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-21T14:10:47Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8b9639ee570d375ebf4db78f6ee1918cf89bd93ec3e1663045078ce31a749b7f","abstract_canon_sha256":"770d0ade54377d1e15b43162a739ce10c9f983804c82bb4cbf7c2502a3829a3b"},"schema_version":"1.0"},"canonical_sha256":"5c1dca9ddcb12d2d8f339a285e7f680f2b015708bd79bf47f9a215f107bd2d24","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:11:53.990500Z","signature_b64":"2CgW13v5mjsktCMd0ywncC/w5C7jfbg8XA0toKoSR/PF+NH+UlR7zPsF5srqMNSJI8CdMk75Es7F7NPOsHOWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c1dca9ddcb12d2d8f339a285e7f680f2b015708bd79bf47f9a215f107bd2d24","last_reissued_at":"2026-07-05T01:11:53.990017Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:11:53.990017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.11807","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":"2026-07-05T01:11:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UoufErtXBgxyW/MP2eDoaiFub++y8kqHFB+AulzsjrzvaU1kyCP2uihGFmMgtt3sibvgYHkGg7X/NgHGx1VyBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:01:23.888357Z"},"content_sha256":"6606fcac8fec734b8822227e0986f4910857bbf3a0946585d6ad73af711e022b","schema_version":"1.0","event_id":"sha256:6606fcac8fec734b8822227e0986f4910857bbf3a0946585d6ad73af711e022b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:LQO4VHO4WEWS3DZTTIUF473IB4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Image Captioning with Better Use of Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Xiaodan Zhu, Xipeng Qiu, Xu Zhou, Zhan Shi","submitted_at":"2020-06-21T14:10:47Z","abstract_excerpt":"Image captioning is a multimodal problem that has drawn extensive attention in both the natural language processing and computer vision community. In this paper, we present a novel image captioning architecture to better explore semantics available in captions and leverage that to enhance both image representation and caption generation. Our models first construct caption-guided visual relationship graphs that introduce beneficial inductive bias using weakly supervised multi-instance learning. The representation is then enhanced with neighbouring and contextual nodes with their textual and vis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.11807","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.11807/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":"2026-07-05T01:11:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sAphQUXu1JL+q7FeS0qFNzoUOa5iBVMErI5R9NPi2Gn4ZW1DfBEcVKGNFYLA7cRS+/7gOXLZLEfJ+dIWLXqXAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:01:23.888946Z"},"content_sha256":"fb1d7d81c6ac66799fb1aea8e6dff179fd532fd301c0d516d3893818a16ab49f","schema_version":"1.0","event_id":"sha256:fb1d7d81c6ac66799fb1aea8e6dff179fd532fd301c0d516d3893818a16ab49f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LQO4VHO4WEWS3DZTTIUF473IB4/bundle.json","state_url":"https://pith.science/pith/LQO4VHO4WEWS3DZTTIUF473IB4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LQO4VHO4WEWS3DZTTIUF473IB4/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":"2026-08-06T07:01:23Z","links":{"resolver":"https://pith.science/pith/LQO4VHO4WEWS3DZTTIUF473IB4","bundle":"https://pith.science/pith/LQO4VHO4WEWS3DZTTIUF473IB4/bundle.json","state":"https://pith.science/pith/LQO4VHO4WEWS3DZTTIUF473IB4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LQO4VHO4WEWS3DZTTIUF473IB4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LQO4VHO4WEWS3DZTTIUF473IB4","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":"770d0ade54377d1e15b43162a739ce10c9f983804c82bb4cbf7c2502a3829a3b","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-21T14:10:47Z","title_canon_sha256":"8b9639ee570d375ebf4db78f6ee1918cf89bd93ec3e1663045078ce31a749b7f"},"schema_version":"1.0","source":{"id":"2006.11807","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.11807","created_at":"2026-07-05T01:11:53Z"},{"alias_kind":"arxiv_version","alias_value":"2006.11807v1","created_at":"2026-07-05T01:11:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.11807","created_at":"2026-07-05T01:11:53Z"},{"alias_kind":"pith_short_12","alias_value":"LQO4VHO4WEWS","created_at":"2026-07-05T01:11:53Z"},{"alias_kind":"pith_short_16","alias_value":"LQO4VHO4WEWS3DZT","created_at":"2026-07-05T01:11:53Z"},{"alias_kind":"pith_short_8","alias_value":"LQO4VHO4","created_at":"2026-07-05T01:11:53Z"}],"graph_snapshots":[{"event_id":"sha256:fb1d7d81c6ac66799fb1aea8e6dff179fd532fd301c0d516d3893818a16ab49f","target":"graph","created_at":"2026-07-05T01:11:53Z","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/2006.11807/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image captioning is a multimodal problem that has drawn extensive attention in both the natural language processing and computer vision community. In this paper, we present a novel image captioning architecture to better explore semantics available in captions and leverage that to enhance both image representation and caption generation. Our models first construct caption-guided visual relationship graphs that introduce beneficial inductive bias using weakly supervised multi-instance learning. The representation is then enhanced with neighbouring and contextual nodes with their textual and vis","authors_text":"Xiaodan Zhu, Xipeng Qiu, Xu Zhou, Zhan Shi","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-21T14:10:47Z","title":"Improving Image Captioning with Better Use of Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.11807","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":"sha256:6606fcac8fec734b8822227e0986f4910857bbf3a0946585d6ad73af711e022b","target":"record","created_at":"2026-07-05T01:11:53Z","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":"770d0ade54377d1e15b43162a739ce10c9f983804c82bb4cbf7c2502a3829a3b","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-21T14:10:47Z","title_canon_sha256":"8b9639ee570d375ebf4db78f6ee1918cf89bd93ec3e1663045078ce31a749b7f"},"schema_version":"1.0","source":{"id":"2006.11807","kind":"arxiv","version":1}},"canonical_sha256":"5c1dca9ddcb12d2d8f339a285e7f680f2b015708bd79bf47f9a215f107bd2d24","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c1dca9ddcb12d2d8f339a285e7f680f2b015708bd79bf47f9a215f107bd2d24","first_computed_at":"2026-07-05T01:11:53.990017Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:11:53.990017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2CgW13v5mjsktCMd0ywncC/w5C7jfbg8XA0toKoSR/PF+NH+UlR7zPsF5srqMNSJI8CdMk75Es7F7NPOsHOWBg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:11:53.990500Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.11807","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6606fcac8fec734b8822227e0986f4910857bbf3a0946585d6ad73af711e022b","sha256:fb1d7d81c6ac66799fb1aea8e6dff179fd532fd301c0d516d3893818a16ab49f"],"state_sha256":"9db140d8509ab2a51ab9455ca9907e2be2e4d3b5ae50ca8d3a9f49b0bd897fac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YvyxOJRgCDWzqHM1AYKkL3lhjbY/cBpvIicypB1zwy7TQAaqjGNSaV8A+RW/iOJ+c2mHAgeG8P8uhRzVc13LAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:01:23.892377Z","bundle_sha256":"93d307fbf51b625d59467c2fbe5ffac2d076223aecbfb3fb66ed4298a7c88761"}}