{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:TI2QP5OTIAMGZVCZX3XWS52D3D","short_pith_number":"pith:TI2QP5OT","canonical_record":{"source":{"id":"2110.09756","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-19T06:10:42Z","cross_cats_sorted":["cs.CL","cs.MM"],"title_canon_sha256":"83aa36b7c7d1b4310631b7cef4884c33367cd8db4855273b7196db2fb128d616","abstract_canon_sha256":"94dd005540e0eef64389ed99319ac91400e6de3cc81774993db818193dd9885c"},"schema_version":"1.0"},"canonical_sha256":"9a3507f5d340186cd459beef697743d8ec912728ad63997c8b56d75e7fa52d47","source":{"kind":"arxiv","id":"2110.09756","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.09756","created_at":"2026-07-05T03:23:58Z"},{"alias_kind":"arxiv_version","alias_value":"2110.09756v1","created_at":"2026-07-05T03:23:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.09756","created_at":"2026-07-05T03:23:58Z"},{"alias_kind":"pith_short_12","alias_value":"TI2QP5OTIAMG","created_at":"2026-07-05T03:23:58Z"},{"alias_kind":"pith_short_16","alias_value":"TI2QP5OTIAMGZVCZ","created_at":"2026-07-05T03:23:58Z"},{"alias_kind":"pith_short_8","alias_value":"TI2QP5OT","created_at":"2026-07-05T03:23:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:TI2QP5OTIAMGZVCZX3XWS52D3D","target":"record","payload":{"canonical_record":{"source":{"id":"2110.09756","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-19T06:10:42Z","cross_cats_sorted":["cs.CL","cs.MM"],"title_canon_sha256":"83aa36b7c7d1b4310631b7cef4884c33367cd8db4855273b7196db2fb128d616","abstract_canon_sha256":"94dd005540e0eef64389ed99319ac91400e6de3cc81774993db818193dd9885c"},"schema_version":"1.0"},"canonical_sha256":"9a3507f5d340186cd459beef697743d8ec912728ad63997c8b56d75e7fa52d47","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:23:58.610032Z","signature_b64":"UEYeOhqc4Shm9VBAXdi6O3YIcY0EBpvKVhHBsWstiSKGNf7ghiUdNG03d34AI/SHy1FnherXJpoc7QdIqGHsCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a3507f5d340186cd459beef697743d8ec912728ad63997c8b56d75e7fa52d47","last_reissued_at":"2026-07-05T03:23:58.609608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:23:58.609608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.09756","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":"2026-07-05T03:23:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"edwsNAp55f/f80mMOl5rrry5hHP9xZV2gpeU7hj1PHaoSnRhMgWYGiWHjnsfGlQ3ObUsP5e2fB6gm3LP7w82Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:00:21.438477Z"},"content_sha256":"14572dab08af0ae4b75b2ff60ffb91e559aa4bf65f1e968ccdca0ea7c0c6bbe0","schema_version":"1.0","event_id":"sha256:14572dab08af0ae4b75b2ff60ffb91e559aa4bf65f1e968ccdca0ea7c0c6bbe0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:TI2QP5OTIAMGZVCZX3XWS52D3D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Picture is Worth a Thousand Words: A Unified System for Diverse Captions and Rich Images Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Bei Liu, Jianlong Fu, Yupan Huang, Yutong Lu","submitted_at":"2021-10-19T06:10:42Z","abstract_excerpt":"A creative image-and-text generative AI system mimics humans' extraordinary abilities to provide users with diverse and comprehensive caption suggestions, as well as rich image creations. In this work, we demonstrate such an AI creation system to produce both diverse captions and rich images. When users imagine an image and associate it with multiple captions, our system paints a rich image to reflect all captions faithfully. Likewise, when users upload an image, our system depicts it with multiple diverse captions. We propose a unified multi-modal framework to achieve this goal. Specifically,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.09756","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/2110.09756/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":"2026-07-05T03:23:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B5ml3toQB4OxGrG2nab5lyWUCxiExg9s8pZrxTY4FG4KDtUO4fx/vK2/hIqnNKy6wq54vFI27umQ8od8pObfCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:00:21.439563Z"},"content_sha256":"99f028899a6597029b9013231c2fa6cbaca56d804466a1bfcb12c0c604e19f2e","schema_version":"1.0","event_id":"sha256:99f028899a6597029b9013231c2fa6cbaca56d804466a1bfcb12c0c604e19f2e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TI2QP5OTIAMGZVCZX3XWS52D3D/bundle.json","state_url":"https://pith.science/pith/TI2QP5OTIAMGZVCZX3XWS52D3D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TI2QP5OTIAMGZVCZX3XWS52D3D/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":"2026-08-04T23:00:21Z","links":{"resolver":"https://pith.science/pith/TI2QP5OTIAMGZVCZX3XWS52D3D","bundle":"https://pith.science/pith/TI2QP5OTIAMGZVCZX3XWS52D3D/bundle.json","state":"https://pith.science/pith/TI2QP5OTIAMGZVCZX3XWS52D3D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TI2QP5OTIAMGZVCZX3XWS52D3D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TI2QP5OTIAMGZVCZX3XWS52D3D","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":"94dd005540e0eef64389ed99319ac91400e6de3cc81774993db818193dd9885c","cross_cats_sorted":["cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-19T06:10:42Z","title_canon_sha256":"83aa36b7c7d1b4310631b7cef4884c33367cd8db4855273b7196db2fb128d616"},"schema_version":"1.0","source":{"id":"2110.09756","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.09756","created_at":"2026-07-05T03:23:58Z"},{"alias_kind":"arxiv_version","alias_value":"2110.09756v1","created_at":"2026-07-05T03:23:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.09756","created_at":"2026-07-05T03:23:58Z"},{"alias_kind":"pith_short_12","alias_value":"TI2QP5OTIAMG","created_at":"2026-07-05T03:23:58Z"},{"alias_kind":"pith_short_16","alias_value":"TI2QP5OTIAMGZVCZ","created_at":"2026-07-05T03:23:58Z"},{"alias_kind":"pith_short_8","alias_value":"TI2QP5OT","created_at":"2026-07-05T03:23:58Z"}],"graph_snapshots":[{"event_id":"sha256:99f028899a6597029b9013231c2fa6cbaca56d804466a1bfcb12c0c604e19f2e","target":"graph","created_at":"2026-07-05T03:23:58Z","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/2110.09756/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A creative image-and-text generative AI system mimics humans' extraordinary abilities to provide users with diverse and comprehensive caption suggestions, as well as rich image creations. In this work, we demonstrate such an AI creation system to produce both diverse captions and rich images. When users imagine an image and associate it with multiple captions, our system paints a rich image to reflect all captions faithfully. Likewise, when users upload an image, our system depicts it with multiple diverse captions. We propose a unified multi-modal framework to achieve this goal. Specifically,","authors_text":"Bei Liu, Jianlong Fu, Yupan Huang, Yutong Lu","cross_cats":["cs.CL","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-19T06:10:42Z","title":"A Picture is Worth a Thousand Words: A Unified System for Diverse Captions and Rich Images Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.09756","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":"sha256:14572dab08af0ae4b75b2ff60ffb91e559aa4bf65f1e968ccdca0ea7c0c6bbe0","target":"record","created_at":"2026-07-05T03:23:58Z","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":"94dd005540e0eef64389ed99319ac91400e6de3cc81774993db818193dd9885c","cross_cats_sorted":["cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-19T06:10:42Z","title_canon_sha256":"83aa36b7c7d1b4310631b7cef4884c33367cd8db4855273b7196db2fb128d616"},"schema_version":"1.0","source":{"id":"2110.09756","kind":"arxiv","version":1}},"canonical_sha256":"9a3507f5d340186cd459beef697743d8ec912728ad63997c8b56d75e7fa52d47","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a3507f5d340186cd459beef697743d8ec912728ad63997c8b56d75e7fa52d47","first_computed_at":"2026-07-05T03:23:58.609608Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:23:58.609608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UEYeOhqc4Shm9VBAXdi6O3YIcY0EBpvKVhHBsWstiSKGNf7ghiUdNG03d34AI/SHy1FnherXJpoc7QdIqGHsCg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:23:58.610032Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.09756","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14572dab08af0ae4b75b2ff60ffb91e559aa4bf65f1e968ccdca0ea7c0c6bbe0","sha256:99f028899a6597029b9013231c2fa6cbaca56d804466a1bfcb12c0c604e19f2e"],"state_sha256":"ea7e202c2daff48be1e00a3e5e864ece0bd7f4cc0ad91987152dccbf505d426f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qlRElkuwrlH/Z38henOHJ9z6lFLAUm1nkYNWp621mElzzzetqJRRMYAQ8Qq6OVfdcB6JfCW/otMWDr4IDjqUCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T23:00:21.445179Z","bundle_sha256":"407c2c5cdc404e3dfd81ed41401a07346899d3c9c31d8813549eb20aaa7b319b"}}