{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RRWEQ4XPWZLJYPI4L4RIFYBDVC","short_pith_number":"pith:RRWEQ4XP","canonical_record":{"source":{"id":"2404.10763","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-04-16T17:47:16Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"be8ab47244617611ad35eadfc3f69fbea1ff82596a4aeadcc20a93f5d7f18364","abstract_canon_sha256":"9c6d0bdcad93472812011c6130dcedf06dfb2f650b9ac30a81c07464d90089bb"},"schema_version":"1.0"},"canonical_sha256":"8c6c4872efb6569c3d1c5f2282e023a891d3b52e682022d5cde4449300551859","source":{"kind":"arxiv","id":"2404.10763","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.10763","created_at":"2026-07-05T08:08:44Z"},{"alias_kind":"arxiv_version","alias_value":"2404.10763v1","created_at":"2026-07-05T08:08:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10763","created_at":"2026-07-05T08:08:44Z"},{"alias_kind":"pith_short_12","alias_value":"RRWEQ4XPWZLJ","created_at":"2026-07-05T08:08:44Z"},{"alias_kind":"pith_short_16","alias_value":"RRWEQ4XPWZLJYPI4","created_at":"2026-07-05T08:08:44Z"},{"alias_kind":"pith_short_8","alias_value":"RRWEQ4XP","created_at":"2026-07-05T08:08:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RRWEQ4XPWZLJYPI4L4RIFYBDVC","target":"record","payload":{"canonical_record":{"source":{"id":"2404.10763","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-04-16T17:47:16Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"be8ab47244617611ad35eadfc3f69fbea1ff82596a4aeadcc20a93f5d7f18364","abstract_canon_sha256":"9c6d0bdcad93472812011c6130dcedf06dfb2f650b9ac30a81c07464d90089bb"},"schema_version":"1.0"},"canonical_sha256":"8c6c4872efb6569c3d1c5f2282e023a891d3b52e682022d5cde4449300551859","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:44.857305Z","signature_b64":"S7oNb+T9yyjG9Rfpm0ysYazr2ErhKvblQZ7PSu/yidN0XIiyeHuZDske3BHIxla6Qksw4o6GNMABYcydPgcxCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c6c4872efb6569c3d1c5f2282e023a891d3b52e682022d5cde4449300551859","last_reissued_at":"2026-07-05T08:08:44.856789Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:44.856789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.10763","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":"2026-07-05T08:08:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FssGbmppyu1r6jQ3xm9m1/3swgEqsHeEzm3qGuFdI+2KXItuQ+GPH+SFX3MMsB4s9q4/87xAx3jcW7elkD5xCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T14:56:02.918292Z"},"content_sha256":"e3335fe5e4608ae96131e8bfefab4acb6f2834d73d9cd0368a6bbf65f8687da6","schema_version":"1.0","event_id":"sha256:e3335fe5e4608ae96131e8bfefab4acb6f2834d73d9cd0368a6bbf65f8687da6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RRWEQ4XPWZLJYPI4L4RIFYBDVC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LaDiC: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-Text Generation?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Jianhong Bai, Kaikai An, Linli Yao, Qingyan Guo, Rundong Gao, Shuhuai Ren, Xu Sun, Yuchi Wang","submitted_at":"2024-04-16T17:47:16Z","abstract_excerpt":"Diffusion models have exhibited remarkable capabilities in text-to-image generation. However, their performance in image-to-text generation, specifically image captioning, has lagged behind Auto-Regressive (AR) models, casting doubt on their applicability for such tasks. In this work, we revisit diffusion models, highlighting their capacity for holistic context modeling and parallel decoding. With these benefits, diffusion models can alleviate the inherent limitations of AR methods, including their slow inference speed, error propagation, and unidirectional constraints. Furthermore, we identif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10763","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/2404.10763/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":"2026-07-05T08:08:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BGnGX61MB95GfME6j6CHByFuhsqTCCGlLXX69x3hTRjPVFZ+3kAfqIs4MxA2IocjAhdkH3HVH9A7OGHHZ2bECg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T14:56:02.918678Z"},"content_sha256":"b3c3a259cc090f3659c28b37b0f822a03833c603e95350925c4b3083b17fb774","schema_version":"1.0","event_id":"sha256:b3c3a259cc090f3659c28b37b0f822a03833c603e95350925c4b3083b17fb774"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RRWEQ4XPWZLJYPI4L4RIFYBDVC/bundle.json","state_url":"https://pith.science/pith/RRWEQ4XPWZLJYPI4L4RIFYBDVC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RRWEQ4XPWZLJYPI4L4RIFYBDVC/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":"2026-07-18T14:56:02Z","links":{"resolver":"https://pith.science/pith/RRWEQ4XPWZLJYPI4L4RIFYBDVC","bundle":"https://pith.science/pith/RRWEQ4XPWZLJYPI4L4RIFYBDVC/bundle.json","state":"https://pith.science/pith/RRWEQ4XPWZLJYPI4L4RIFYBDVC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RRWEQ4XPWZLJYPI4L4RIFYBDVC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RRWEQ4XPWZLJYPI4L4RIFYBDVC","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":"9c6d0bdcad93472812011c6130dcedf06dfb2f650b9ac30a81c07464d90089bb","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-04-16T17:47:16Z","title_canon_sha256":"be8ab47244617611ad35eadfc3f69fbea1ff82596a4aeadcc20a93f5d7f18364"},"schema_version":"1.0","source":{"id":"2404.10763","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.10763","created_at":"2026-07-05T08:08:44Z"},{"alias_kind":"arxiv_version","alias_value":"2404.10763v1","created_at":"2026-07-05T08:08:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10763","created_at":"2026-07-05T08:08:44Z"},{"alias_kind":"pith_short_12","alias_value":"RRWEQ4XPWZLJ","created_at":"2026-07-05T08:08:44Z"},{"alias_kind":"pith_short_16","alias_value":"RRWEQ4XPWZLJYPI4","created_at":"2026-07-05T08:08:44Z"},{"alias_kind":"pith_short_8","alias_value":"RRWEQ4XP","created_at":"2026-07-05T08:08:44Z"}],"graph_snapshots":[{"event_id":"sha256:b3c3a259cc090f3659c28b37b0f822a03833c603e95350925c4b3083b17fb774","target":"graph","created_at":"2026-07-05T08:08:44Z","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/2404.10763/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models have exhibited remarkable capabilities in text-to-image generation. However, their performance in image-to-text generation, specifically image captioning, has lagged behind Auto-Regressive (AR) models, casting doubt on their applicability for such tasks. In this work, we revisit diffusion models, highlighting their capacity for holistic context modeling and parallel decoding. With these benefits, diffusion models can alleviate the inherent limitations of AR methods, including their slow inference speed, error propagation, and unidirectional constraints. Furthermore, we identif","authors_text":"Jianhong Bai, Kaikai An, Linli Yao, Qingyan Guo, Rundong Gao, Shuhuai Ren, Xu Sun, Yuchi Wang","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-04-16T17:47:16Z","title":"LaDiC: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-Text Generation?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10763","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:e3335fe5e4608ae96131e8bfefab4acb6f2834d73d9cd0368a6bbf65f8687da6","target":"record","created_at":"2026-07-05T08:08:44Z","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":"9c6d0bdcad93472812011c6130dcedf06dfb2f650b9ac30a81c07464d90089bb","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-04-16T17:47:16Z","title_canon_sha256":"be8ab47244617611ad35eadfc3f69fbea1ff82596a4aeadcc20a93f5d7f18364"},"schema_version":"1.0","source":{"id":"2404.10763","kind":"arxiv","version":1}},"canonical_sha256":"8c6c4872efb6569c3d1c5f2282e023a891d3b52e682022d5cde4449300551859","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c6c4872efb6569c3d1c5f2282e023a891d3b52e682022d5cde4449300551859","first_computed_at":"2026-07-05T08:08:44.856789Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:08:44.856789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S7oNb+T9yyjG9Rfpm0ysYazr2ErhKvblQZ7PSu/yidN0XIiyeHuZDske3BHIxla6Qksw4o6GNMABYcydPgcxCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:08:44.857305Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.10763","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3335fe5e4608ae96131e8bfefab4acb6f2834d73d9cd0368a6bbf65f8687da6","sha256:b3c3a259cc090f3659c28b37b0f822a03833c603e95350925c4b3083b17fb774"],"state_sha256":"df3677eb8c8465adadd992a1474e5a8a9b24dd217b75e07173a2fc745c97ef76"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xbvxdSGnSc5IVeXBMZOcb2mInk2PR5RNOol2X76FJlxkaFPMdnwfsIlM3s4fJ//nHvOBvgEca8hqehPWnXK9AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-18T14:56:02.921234Z","bundle_sha256":"b04c090c11f826a00d4e5c6885fa262c31bb5e49be1cf34bd7f5654df5909de8"}}