{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:E7BF56GVFXDYFRLD6ZSO2NIQCO","short_pith_number":"pith:E7BF56GV","canonical_record":{"source":{"id":"2303.02437","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-04T14:59:25Z","cross_cats_sorted":[],"title_canon_sha256":"937c3b841cf06939036e760422e1f9126f76f749b7be2d73c199b984b4bc8ba8","abstract_canon_sha256":"510025edb8ba4897261f3d2d6b3b88f06025eccd427df365c3cb147b540d2b3f"},"schema_version":"1.0"},"canonical_sha256":"27c25ef8d52dc782c563f664ed3510139432f24be60b36e9d40278800af9ffd4","source":{"kind":"arxiv","id":"2303.02437","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.02437","created_at":"2026-07-05T05:49:33Z"},{"alias_kind":"arxiv_version","alias_value":"2303.02437v2","created_at":"2026-07-05T05:49:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.02437","created_at":"2026-07-05T05:49:33Z"},{"alias_kind":"pith_short_12","alias_value":"E7BF56GVFXDY","created_at":"2026-07-05T05:49:33Z"},{"alias_kind":"pith_short_16","alias_value":"E7BF56GVFXDYFRLD","created_at":"2026-07-05T05:49:33Z"},{"alias_kind":"pith_short_8","alias_value":"E7BF56GV","created_at":"2026-07-05T05:49:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:E7BF56GVFXDYFRLD6ZSO2NIQCO","target":"record","payload":{"canonical_record":{"source":{"id":"2303.02437","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-04T14:59:25Z","cross_cats_sorted":[],"title_canon_sha256":"937c3b841cf06939036e760422e1f9126f76f749b7be2d73c199b984b4bc8ba8","abstract_canon_sha256":"510025edb8ba4897261f3d2d6b3b88f06025eccd427df365c3cb147b540d2b3f"},"schema_version":"1.0"},"canonical_sha256":"27c25ef8d52dc782c563f664ed3510139432f24be60b36e9d40278800af9ffd4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:33.634902Z","signature_b64":"rCFExD5I+LOoNPMaahnDoB8/F8siIlTLFVzIzaGcT7XBUCAqtH8fVOb1LtYuTwMtw2KyHRSQUxAm1dsKnxXoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27c25ef8d52dc782c563f664ed3510139432f24be60b36e9d40278800af9ffd4","last_reissued_at":"2026-07-05T05:49:33.634438Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:33.634438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.02437","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:49:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NisYHhl0vTbYcijrnIhP/DH/+IvbG0J2i7/NwOwFh4f/GMWbk7g13wZhoGgvBXxfRQYBY2ON42+aE8TWLULbDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:19:46.185540Z"},"content_sha256":"9e27e701f3c9c23baf40978ce69efe13d1d3ef8b98adb1ead8222170a34257b7","schema_version":"1.0","event_id":"sha256:9e27e701f3c9c23baf40978ce69efe13d1d3ef8b98adb1ead8222170a34257b7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:E7BF56GVFXDYFRLD6ZSO2NIQCO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ConZIC: Controllable Zero-shot Image Captioning by Sampling-Based Polishing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Chen, Dongsheng Wang, Hao Zhang, Ruiying Lu, Zequn Zeng, Zhengjue Wang","submitted_at":"2023-03-04T14:59:25Z","abstract_excerpt":"Zero-shot capability has been considered as a new revolution of deep learning, letting machines work on tasks without curated training data. As a good start and the only existing outcome of zero-shot image captioning (IC), ZeroCap abandons supervised training and sequentially searches every word in the caption using the knowledge of large-scale pretrained models. Though effective, its autoregressive generation and gradient-directed searching mechanism limit the diversity of captions and inference speed, respectively. Moreover, ZeroCap does not consider the controllability issue of zero-shot IC"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.02437","kind":"arxiv","version":2},"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/2303.02437/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":"2026-07-05T05:49:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hr1ujmzCNEj6GwfmkwBMSx2BNy8XjlHw5ixeRuCZZAcWLaBT6cs53YNxCD70l3K/pUbVQbp/FrxcPK7wXk5FCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:19:46.185933Z"},"content_sha256":"e413cd904a1d79cb15b8c7005c99171984ddfccd84ebb005e2ed3d73f78f8824","schema_version":"1.0","event_id":"sha256:e413cd904a1d79cb15b8c7005c99171984ddfccd84ebb005e2ed3d73f78f8824"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E7BF56GVFXDYFRLD6ZSO2NIQCO/bundle.json","state_url":"https://pith.science/pith/E7BF56GVFXDYFRLD6ZSO2NIQCO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E7BF56GVFXDYFRLD6ZSO2NIQCO/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":"2026-07-07T08:19:46Z","links":{"resolver":"https://pith.science/pith/E7BF56GVFXDYFRLD6ZSO2NIQCO","bundle":"https://pith.science/pith/E7BF56GVFXDYFRLD6ZSO2NIQCO/bundle.json","state":"https://pith.science/pith/E7BF56GVFXDYFRLD6ZSO2NIQCO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E7BF56GVFXDYFRLD6ZSO2NIQCO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:E7BF56GVFXDYFRLD6ZSO2NIQCO","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":"510025edb8ba4897261f3d2d6b3b88f06025eccd427df365c3cb147b540d2b3f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-04T14:59:25Z","title_canon_sha256":"937c3b841cf06939036e760422e1f9126f76f749b7be2d73c199b984b4bc8ba8"},"schema_version":"1.0","source":{"id":"2303.02437","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.02437","created_at":"2026-07-05T05:49:33Z"},{"alias_kind":"arxiv_version","alias_value":"2303.02437v2","created_at":"2026-07-05T05:49:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.02437","created_at":"2026-07-05T05:49:33Z"},{"alias_kind":"pith_short_12","alias_value":"E7BF56GVFXDY","created_at":"2026-07-05T05:49:33Z"},{"alias_kind":"pith_short_16","alias_value":"E7BF56GVFXDYFRLD","created_at":"2026-07-05T05:49:33Z"},{"alias_kind":"pith_short_8","alias_value":"E7BF56GV","created_at":"2026-07-05T05:49:33Z"}],"graph_snapshots":[{"event_id":"sha256:e413cd904a1d79cb15b8c7005c99171984ddfccd84ebb005e2ed3d73f78f8824","target":"graph","created_at":"2026-07-05T05:49:33Z","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/2303.02437/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Zero-shot capability has been considered as a new revolution of deep learning, letting machines work on tasks without curated training data. As a good start and the only existing outcome of zero-shot image captioning (IC), ZeroCap abandons supervised training and sequentially searches every word in the caption using the knowledge of large-scale pretrained models. Though effective, its autoregressive generation and gradient-directed searching mechanism limit the diversity of captions and inference speed, respectively. Moreover, ZeroCap does not consider the controllability issue of zero-shot IC","authors_text":"Bo Chen, Dongsheng Wang, Hao Zhang, Ruiying Lu, Zequn Zeng, Zhengjue Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-04T14:59:25Z","title":"ConZIC: Controllable Zero-shot Image Captioning by Sampling-Based Polishing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.02437","kind":"arxiv","version":2},"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":"sha256:9e27e701f3c9c23baf40978ce69efe13d1d3ef8b98adb1ead8222170a34257b7","target":"record","created_at":"2026-07-05T05:49:33Z","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":"510025edb8ba4897261f3d2d6b3b88f06025eccd427df365c3cb147b540d2b3f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-04T14:59:25Z","title_canon_sha256":"937c3b841cf06939036e760422e1f9126f76f749b7be2d73c199b984b4bc8ba8"},"schema_version":"1.0","source":{"id":"2303.02437","kind":"arxiv","version":2}},"canonical_sha256":"27c25ef8d52dc782c563f664ed3510139432f24be60b36e9d40278800af9ffd4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27c25ef8d52dc782c563f664ed3510139432f24be60b36e9d40278800af9ffd4","first_computed_at":"2026-07-05T05:49:33.634438Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:49:33.634438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rCFExD5I+LOoNPMaahnDoB8/F8siIlTLFVzIzaGcT7XBUCAqtH8fVOb1LtYuTwMtw2KyHRSQUxAm1dsKnxXoBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:49:33.634902Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.02437","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e27e701f3c9c23baf40978ce69efe13d1d3ef8b98adb1ead8222170a34257b7","sha256:e413cd904a1d79cb15b8c7005c99171984ddfccd84ebb005e2ed3d73f78f8824"],"state_sha256":"1241a75869bb3c525fa265b72a6fdfb9fe4c53f3c1db8fd046c7667fb5804114"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/16+HO8xVUN4tC3dVqsvSvw6k+JVsqEU4AQfIsvMXWLJ/ofX63lNsNGD7J0PB0/WcgxIK0Vhk2CK5ceqvTh5Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:19:46.187932Z","bundle_sha256":"5f170d84f22e63f9fa4bd60957d0f0898264c2344a2569d4bb019aaae965aa40"}}