{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:GYGNJHS3RRNVP35EK3JVM6GKNY","short_pith_number":"pith:GYGNJHS3","canonical_record":{"source":{"id":"2210.04559","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-10T10:55:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"044abb9b951a330db6c6c856499c32858d5ff4f3419a44db71df86cfeb994667","abstract_canon_sha256":"b2bd47c59a1d2cc2479b3db517bd9cea856e4c5d1ec95076fa02d668842c63b3"},"schema_version":"1.0"},"canonical_sha256":"360cd49e5b8c5b57efa456d35678ca6e35ae81ba78e58ded635e78985e05d3bc","source":{"kind":"arxiv","id":"2210.04559","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.04559","created_at":"2026-07-05T05:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2210.04559v1","created_at":"2026-07-05T05:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04559","created_at":"2026-07-05T05:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"GYGNJHS3RRNV","created_at":"2026-07-05T05:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"GYGNJHS3RRNVP35E","created_at":"2026-07-05T05:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"GYGNJHS3","created_at":"2026-07-05T05:04:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:GYGNJHS3RRNVP35EK3JVM6GKNY","target":"record","payload":{"canonical_record":{"source":{"id":"2210.04559","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-10T10:55:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"044abb9b951a330db6c6c856499c32858d5ff4f3419a44db71df86cfeb994667","abstract_canon_sha256":"b2bd47c59a1d2cc2479b3db517bd9cea856e4c5d1ec95076fa02d668842c63b3"},"schema_version":"1.0"},"canonical_sha256":"360cd49e5b8c5b57efa456d35678ca6e35ae81ba78e58ded635e78985e05d3bc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:54.726337Z","signature_b64":"OdBcgWpbS6jG/mRZ1mHKqsvQqZtxY+jCMpC1zI9Q4p7hIKXPUz87PkTaRHYf+55UitOmQfQK7yhz56hsa7kkDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"360cd49e5b8c5b57efa456d35678ca6e35ae81ba78e58ded635e78985e05d3bc","last_reissued_at":"2026-07-05T05:04:54.725971Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:54.725971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.04559","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":"2026-07-05T05:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b4Qs8kWWLdi4JZlIwKIdvA1LEKlF3noyD7GDAbSA+aNryVHKmIs7F+uZTKfxkPonJgmSKQ+pcKHzQdlrEA2oBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T11:51:44.484552Z"},"content_sha256":"bebd0f642e5851f72d41911edfb4e8a47b63abf9134a2b97d20a0fa4994000f7","schema_version":"1.0","event_id":"sha256:bebd0f642e5851f72d41911edfb4e8a47b63abf9134a2b97d20a0fa4994000f7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:GYGNJHS3RRNVP35EK3JVM6GKNY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CLIP-Diffusion-LM: Apply Diffusion Model on Image Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Shitong Xu","submitted_at":"2022-10-10T10:55:53Z","abstract_excerpt":"Image captioning task has been extensively researched by previous work. However, limited experiments focus on generating captions based on non-autoregressive text decoder. Inspired by the recent success of the denoising diffusion model on image synthesis tasks, we apply denoising diffusion probabilistic models to text generation in image captioning tasks. We show that our CLIP-Diffusion-LM is capable of generating image captions using significantly fewer inference steps than autoregressive models. On the Flickr8k dataset, the model achieves 0.1876 BLEU-4 score. By training on the combined Flic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04559","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/2210.04559/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":"2026-07-05T05:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vjr6TyYpVtJ+ROM2LeRxjsGPYvO3tPoAvJ+3viHylmkqpJsA948LleNTtTNU3rEcfCg/1NMTY35kUFfS2PSnDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T11:51:44.485766Z"},"content_sha256":"0a7ccd8badc4259c87dc94d529da0670c3d54f39780aff47ac7c3f316f76a137","schema_version":"1.0","event_id":"sha256:0a7ccd8badc4259c87dc94d529da0670c3d54f39780aff47ac7c3f316f76a137"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GYGNJHS3RRNVP35EK3JVM6GKNY/bundle.json","state_url":"https://pith.science/pith/GYGNJHS3RRNVP35EK3JVM6GKNY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GYGNJHS3RRNVP35EK3JVM6GKNY/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":"2026-08-20T11:51:44Z","links":{"resolver":"https://pith.science/pith/GYGNJHS3RRNVP35EK3JVM6GKNY","bundle":"https://pith.science/pith/GYGNJHS3RRNVP35EK3JVM6GKNY/bundle.json","state":"https://pith.science/pith/GYGNJHS3RRNVP35EK3JVM6GKNY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GYGNJHS3RRNVP35EK3JVM6GKNY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GYGNJHS3RRNVP35EK3JVM6GKNY","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":"b2bd47c59a1d2cc2479b3db517bd9cea856e4c5d1ec95076fa02d668842c63b3","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-10T10:55:53Z","title_canon_sha256":"044abb9b951a330db6c6c856499c32858d5ff4f3419a44db71df86cfeb994667"},"schema_version":"1.0","source":{"id":"2210.04559","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.04559","created_at":"2026-07-05T05:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2210.04559v1","created_at":"2026-07-05T05:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04559","created_at":"2026-07-05T05:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"GYGNJHS3RRNV","created_at":"2026-07-05T05:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"GYGNJHS3RRNVP35E","created_at":"2026-07-05T05:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"GYGNJHS3","created_at":"2026-07-05T05:04:54Z"}],"graph_snapshots":[{"event_id":"sha256:0a7ccd8badc4259c87dc94d529da0670c3d54f39780aff47ac7c3f316f76a137","target":"graph","created_at":"2026-07-05T05:04:54Z","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/2210.04559/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image captioning task has been extensively researched by previous work. However, limited experiments focus on generating captions based on non-autoregressive text decoder. Inspired by the recent success of the denoising diffusion model on image synthesis tasks, we apply denoising diffusion probabilistic models to text generation in image captioning tasks. We show that our CLIP-Diffusion-LM is capable of generating image captions using significantly fewer inference steps than autoregressive models. On the Flickr8k dataset, the model achieves 0.1876 BLEU-4 score. By training on the combined Flic","authors_text":"Shitong Xu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-10T10:55:53Z","title":"CLIP-Diffusion-LM: Apply Diffusion Model on Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04559","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:bebd0f642e5851f72d41911edfb4e8a47b63abf9134a2b97d20a0fa4994000f7","target":"record","created_at":"2026-07-05T05:04:54Z","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":"b2bd47c59a1d2cc2479b3db517bd9cea856e4c5d1ec95076fa02d668842c63b3","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-10T10:55:53Z","title_canon_sha256":"044abb9b951a330db6c6c856499c32858d5ff4f3419a44db71df86cfeb994667"},"schema_version":"1.0","source":{"id":"2210.04559","kind":"arxiv","version":1}},"canonical_sha256":"360cd49e5b8c5b57efa456d35678ca6e35ae81ba78e58ded635e78985e05d3bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"360cd49e5b8c5b57efa456d35678ca6e35ae81ba78e58ded635e78985e05d3bc","first_computed_at":"2026-07-05T05:04:54.725971Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:04:54.725971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OdBcgWpbS6jG/mRZ1mHKqsvQqZtxY+jCMpC1zI9Q4p7hIKXPUz87PkTaRHYf+55UitOmQfQK7yhz56hsa7kkDw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:04:54.726337Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.04559","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bebd0f642e5851f72d41911edfb4e8a47b63abf9134a2b97d20a0fa4994000f7","sha256:0a7ccd8badc4259c87dc94d529da0670c3d54f39780aff47ac7c3f316f76a137"],"state_sha256":"4d83f0ce9ee4ff3288165a7257a85210dc5b7e83b3e8d3806fb939f7d403a295"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dlS8MIq32P+aCPRjisqkIlf1hHJFWwlZKMKaKPNNSNrvCckWcuSfElwKr8He5iX1y9VRI/+fVQW5x/h06KP/Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T11:51:44.493397Z","bundle_sha256":"302ff60a12e69aa861d3ebdb4727530474d2c5268f5e38eb9c93f69829d20734"}}