{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:44VOJFLHI5355IDH2E2UUB7W67","short_pith_number":"pith:44VOJFLH","canonical_record":{"source":{"id":"2212.01803","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-04T11:59:31Z","cross_cats_sorted":[],"title_canon_sha256":"843c0fed15cdfcd2f17350064d1f06e4e8f777cf06c5073aaf9d48df1bf2f8d7","abstract_canon_sha256":"026316a666db5efacd317a1486779b3acb1a831bd3ef3d4a642d77559953bccc"},"schema_version":"1.0"},"canonical_sha256":"e72ae495674777dea067d1354a07f6f7dd27ce7ed86880447c5f6a2c2fa518b5","source":{"kind":"arxiv","id":"2212.01803","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.01803","created_at":"2026-07-05T05:22:16Z"},{"alias_kind":"arxiv_version","alias_value":"2212.01803v1","created_at":"2026-07-05T05:22:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.01803","created_at":"2026-07-05T05:22:16Z"},{"alias_kind":"pith_short_12","alias_value":"44VOJFLHI535","created_at":"2026-07-05T05:22:16Z"},{"alias_kind":"pith_short_16","alias_value":"44VOJFLHI5355IDH","created_at":"2026-07-05T05:22:16Z"},{"alias_kind":"pith_short_8","alias_value":"44VOJFLH","created_at":"2026-07-05T05:22:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:44VOJFLHI5355IDH2E2UUB7W67","target":"record","payload":{"canonical_record":{"source":{"id":"2212.01803","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-04T11:59:31Z","cross_cats_sorted":[],"title_canon_sha256":"843c0fed15cdfcd2f17350064d1f06e4e8f777cf06c5073aaf9d48df1bf2f8d7","abstract_canon_sha256":"026316a666db5efacd317a1486779b3acb1a831bd3ef3d4a642d77559953bccc"},"schema_version":"1.0"},"canonical_sha256":"e72ae495674777dea067d1354a07f6f7dd27ce7ed86880447c5f6a2c2fa518b5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:22:16.880554Z","signature_b64":"fJ0dI5YY5DxLU0IL8K/fGFsxn6eb2Ce0mFvTtT9sRNF4TYgz9EsfcQ/LdapKSPV1MSpdtgLnENk675rHam6ZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e72ae495674777dea067d1354a07f6f7dd27ce7ed86880447c5f6a2c2fa518b5","last_reissued_at":"2026-07-05T05:22:16.880219Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:22:16.880219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.01803","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":"2026-07-05T05:22:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rOCfN1GfuCzZJEK1diP7LuI2Vmz979GSjLzqkQmE4yzfI7Nn7KYzSVMjnqHbPyzgtt6vQZ3azFYrKvM0EFBbCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:18:36.188443Z"},"content_sha256":"8deb18df8793e027fb3772dfcf48f061a092370975f249b15dbdfc1dba0936d1","schema_version":"1.0","event_id":"sha256:8deb18df8793e027fb3772dfcf48f061a092370975f249b15dbdfc1dba0936d1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:44VOJFLHI5355IDH2E2UUB7W67","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Controllable Image Captioning via Prompting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiahao Xie, Jihao Wu, Linlin Li, Mingbo Jia, Ning Wang","submitted_at":"2022-12-04T11:59:31Z","abstract_excerpt":"Despite the remarkable progress of image captioning, existing captioners typically lack the controllable capability to generate desired image captions, e.g., describing the image in a rough or detailed manner, in a factual or emotional view, etc. In this paper, we show that a unified model is qualified to perform well in diverse domains and freely switch among multiple styles. Such a controllable capability is achieved by embedding the prompt learning into the image captioning framework. To be specific, we design a set of prompts to fine-tune the pre-trained image captioner. These prompts allo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.01803","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/2212.01803/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":"2026-07-05T05:22:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OlFxfvhDKgWrpvV1U1uQalXRNkB5yWbOdrWGhvUnXsSUFHYs9pH8D4QlX3qf0dS30+xVo/393EEVqsjAjOEoAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:18:36.188812Z"},"content_sha256":"abf5265b0353091457dac4bcea3e92ed5ed4997292a3a0fafdc8e995851faed8","schema_version":"1.0","event_id":"sha256:abf5265b0353091457dac4bcea3e92ed5ed4997292a3a0fafdc8e995851faed8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/44VOJFLHI5355IDH2E2UUB7W67/bundle.json","state_url":"https://pith.science/pith/44VOJFLHI5355IDH2E2UUB7W67/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/44VOJFLHI5355IDH2E2UUB7W67/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":"2026-08-14T08:18:36Z","links":{"resolver":"https://pith.science/pith/44VOJFLHI5355IDH2E2UUB7W67","bundle":"https://pith.science/pith/44VOJFLHI5355IDH2E2UUB7W67/bundle.json","state":"https://pith.science/pith/44VOJFLHI5355IDH2E2UUB7W67/state.json","well_known_bundle":"https://pith.science/.well-known/pith/44VOJFLHI5355IDH2E2UUB7W67/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:44VOJFLHI5355IDH2E2UUB7W67","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":"026316a666db5efacd317a1486779b3acb1a831bd3ef3d4a642d77559953bccc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-04T11:59:31Z","title_canon_sha256":"843c0fed15cdfcd2f17350064d1f06e4e8f777cf06c5073aaf9d48df1bf2f8d7"},"schema_version":"1.0","source":{"id":"2212.01803","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.01803","created_at":"2026-07-05T05:22:16Z"},{"alias_kind":"arxiv_version","alias_value":"2212.01803v1","created_at":"2026-07-05T05:22:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.01803","created_at":"2026-07-05T05:22:16Z"},{"alias_kind":"pith_short_12","alias_value":"44VOJFLHI535","created_at":"2026-07-05T05:22:16Z"},{"alias_kind":"pith_short_16","alias_value":"44VOJFLHI5355IDH","created_at":"2026-07-05T05:22:16Z"},{"alias_kind":"pith_short_8","alias_value":"44VOJFLH","created_at":"2026-07-05T05:22:16Z"}],"graph_snapshots":[{"event_id":"sha256:abf5265b0353091457dac4bcea3e92ed5ed4997292a3a0fafdc8e995851faed8","target":"graph","created_at":"2026-07-05T05:22:16Z","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/2212.01803/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the remarkable progress of image captioning, existing captioners typically lack the controllable capability to generate desired image captions, e.g., describing the image in a rough or detailed manner, in a factual or emotional view, etc. In this paper, we show that a unified model is qualified to perform well in diverse domains and freely switch among multiple styles. Such a controllable capability is achieved by embedding the prompt learning into the image captioning framework. To be specific, we design a set of prompts to fine-tune the pre-trained image captioner. These prompts allo","authors_text":"Jiahao Xie, Jihao Wu, Linlin Li, Mingbo Jia, Ning Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-04T11:59:31Z","title":"Controllable Image Captioning via Prompting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.01803","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":"sha256:8deb18df8793e027fb3772dfcf48f061a092370975f249b15dbdfc1dba0936d1","target":"record","created_at":"2026-07-05T05:22:16Z","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":"026316a666db5efacd317a1486779b3acb1a831bd3ef3d4a642d77559953bccc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-04T11:59:31Z","title_canon_sha256":"843c0fed15cdfcd2f17350064d1f06e4e8f777cf06c5073aaf9d48df1bf2f8d7"},"schema_version":"1.0","source":{"id":"2212.01803","kind":"arxiv","version":1}},"canonical_sha256":"e72ae495674777dea067d1354a07f6f7dd27ce7ed86880447c5f6a2c2fa518b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e72ae495674777dea067d1354a07f6f7dd27ce7ed86880447c5f6a2c2fa518b5","first_computed_at":"2026-07-05T05:22:16.880219Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:22:16.880219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fJ0dI5YY5DxLU0IL8K/fGFsxn6eb2Ce0mFvTtT9sRNF4TYgz9EsfcQ/LdapKSPV1MSpdtgLnENk675rHam6ZAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:22:16.880554Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.01803","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8deb18df8793e027fb3772dfcf48f061a092370975f249b15dbdfc1dba0936d1","sha256:abf5265b0353091457dac4bcea3e92ed5ed4997292a3a0fafdc8e995851faed8"],"state_sha256":"59ef263c6fd21fb5dc1ce70ec850c11dbb7660f4657bba8ad3b6abbec0c2407c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AfR9LUOKb8sWxB8CYQCjFEwLPoD3sBKff0nZdLTCCb0E5rYX13zxV+KKSVXib79W1YDZ51jj0HMWiZx3ZwPkCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T08:18:36.192030Z","bundle_sha256":"b3cdacd28574bba58210eea0e42da06a8d17b475e38a37146fb2a68cb809a1b1"}}