{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:WCLRWF3TNYY4BMYWRWD3FGD5WI","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":"05fbe84141b8bc83059d43eff6cdeadc9aeea997389938814e26fb3ad47b3501","cross_cats_sorted":["cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-06T16:08:16Z","title_canon_sha256":"f64e2fed042bb8f343e7b5ee50dafe3e5c817dc0b61d028429005c24e6422a15"},"schema_version":"1.0","source":{"id":"2212.03099","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.03099","created_at":"2026-07-05T05:23:03Z"},{"alias_kind":"arxiv_version","alias_value":"2212.03099v1","created_at":"2026-07-05T05:23:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.03099","created_at":"2026-07-05T05:23:03Z"},{"alias_kind":"pith_short_12","alias_value":"WCLRWF3TNYY4","created_at":"2026-07-05T05:23:03Z"},{"alias_kind":"pith_short_16","alias_value":"WCLRWF3TNYY4BMYW","created_at":"2026-07-05T05:23:03Z"},{"alias_kind":"pith_short_8","alias_value":"WCLRWF3T","created_at":"2026-07-05T05:23:03Z"}],"graph_snapshots":[{"event_id":"sha256:5ec7de16b0feb7436a18ac25a98f3a2d6e4fa7d1781e0125c07401ce98ae3fdc","target":"graph","created_at":"2026-07-05T05:23:03Z","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/2212.03099/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances on text-to-image generation have witnessed the rise of diffusion models which act as powerful generative models. Nevertheless, it is not trivial to exploit such latent variable models to capture the dependency among discrete words and meanwhile pursue complex visual-language alignment in image captioning. In this paper, we break the deeply rooted conventions in learning Transformer-based encoder-decoder, and propose a new diffusion model based paradigm tailored for image captioning, namely Semantic-Conditional Diffusion Networks (SCD-Net). Technically, for each input image, we ","authors_text":"Hongyang Chao, Jianjie Luo, Jianlin Feng, Tao Mei, Ting Yao, Yehao Li, Yingwei Pan","cross_cats":["cs.CL","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-06T16:08:16Z","title":"Semantic-Conditional Diffusion Networks for Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.03099","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:c3fe46148834a7d604787e569582eb89f43f4877570cf7b478fecf01a5091d3b","target":"record","created_at":"2026-07-05T05:23:03Z","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":"05fbe84141b8bc83059d43eff6cdeadc9aeea997389938814e26fb3ad47b3501","cross_cats_sorted":["cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-06T16:08:16Z","title_canon_sha256":"f64e2fed042bb8f343e7b5ee50dafe3e5c817dc0b61d028429005c24e6422a15"},"schema_version":"1.0","source":{"id":"2212.03099","kind":"arxiv","version":1}},"canonical_sha256":"b0971b17736e31c0b3168d87b2987db202c432b33b66284c02836595212b21ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0971b17736e31c0b3168d87b2987db202c432b33b66284c02836595212b21ca","first_computed_at":"2026-07-05T05:23:03.784475Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:23:03.784475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BoCrEfoEVNbYCll5gcri0sCj6QjJew7972qBpG/uEZfhcTC/+MJkYpZHaqw/dbSTWM5dW7o0i9TmSjEqhG0PBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:23:03.785157Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.03099","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c3fe46148834a7d604787e569582eb89f43f4877570cf7b478fecf01a5091d3b","sha256:5ec7de16b0feb7436a18ac25a98f3a2d6e4fa7d1781e0125c07401ce98ae3fdc"],"state_sha256":"6d2dcf8b681554131130617a4aa59aa2def27b1d3cde8fd5815c178b7bcac7f0"}