{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XR7ZCHU7NJYIB5QTNHFSMXCTF3","short_pith_number":"pith:XR7ZCHU7","canonical_record":{"source":{"id":"2305.13655","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T03:59:06Z","cross_cats_sorted":[],"title_canon_sha256":"68552a17253802c6156292939388ab77b27675e3e2c0c721408a6d7db74de4aa","abstract_canon_sha256":"d06de464760dac2b53953b10a3b5deec725c0a5d3514651c193d3baaa0844df2"},"schema_version":"1.0"},"canonical_sha256":"bc7f911e9f6a7080f61369cb265c532eceb220f0038ff2204061a95740d63b19","source":{"kind":"arxiv","id":"2305.13655","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13655","created_at":"2026-07-05T07:51:28Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13655v3","created_at":"2026-07-05T07:51:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13655","created_at":"2026-07-05T07:51:28Z"},{"alias_kind":"pith_short_12","alias_value":"XR7ZCHU7NJYI","created_at":"2026-07-05T07:51:28Z"},{"alias_kind":"pith_short_16","alias_value":"XR7ZCHU7NJYIB5QT","created_at":"2026-07-05T07:51:28Z"},{"alias_kind":"pith_short_8","alias_value":"XR7ZCHU7","created_at":"2026-07-05T07:51:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XR7ZCHU7NJYIB5QTNHFSMXCTF3","target":"record","payload":{"canonical_record":{"source":{"id":"2305.13655","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T03:59:06Z","cross_cats_sorted":[],"title_canon_sha256":"68552a17253802c6156292939388ab77b27675e3e2c0c721408a6d7db74de4aa","abstract_canon_sha256":"d06de464760dac2b53953b10a3b5deec725c0a5d3514651c193d3baaa0844df2"},"schema_version":"1.0"},"canonical_sha256":"bc7f911e9f6a7080f61369cb265c532eceb220f0038ff2204061a95740d63b19","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:28.392105Z","signature_b64":"yst0BS06z+FQiFx8BpDfFBX6RilqTB5QJYqGs7Co10CUx8caYO5VoWFUl4C5NwctwDNdyMqIiQRajhLdiOsCCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc7f911e9f6a7080f61369cb265c532eceb220f0038ff2204061a95740d63b19","last_reissued_at":"2026-07-05T07:51:28.391570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:28.391570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.13655","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:51:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SIiYF9gULvtNLddxPS/+nQDx5I8d5+RCmDS8TzVMfD3xymaNATb1SjNdOoXEi11JjsvSAs6JPwfsxJvLKQIRAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:45:57.064248Z"},"content_sha256":"d488ede400ba63e18d28d7e2d7918f29cabdf46026db53e2a0f932140f46909b","schema_version":"1.0","event_id":"sha256:d488ede400ba63e18d28d7e2d7918f29cabdf46026db53e2a0f932140f46909b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XR7ZCHU7NJYIB5QTNHFSMXCTF3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adam Yala, Boyi Li, Long Lian, Trevor Darrell","submitted_at":"2023-05-23T03:59:06Z","abstract_excerpt":"Recent advancements in text-to-image diffusion models have yielded impressive results in generating realistic and diverse images. However, these models still struggle with complex prompts, such as those that involve numeracy and spatial reasoning. This work proposes to enhance prompt understanding capabilities in diffusion models. Our method leverages a pretrained large language model (LLM) for grounded generation in a novel two-stage process. In the first stage, the LLM generates a scene layout that comprises captioned bounding boxes from a given prompt describing the desired image. In the se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13655","kind":"arxiv","version":3},"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/2305.13655/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":"2026-07-05T07:51:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3CUNDPhpASXREkU77Ha57u34y04bo9jJPIrRTLPSCDKudl/BEl5Ansvo+2p3V43hdZ8s5AfTuLJi6p5rtYA4Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:45:57.064868Z"},"content_sha256":"da35a9efd35d5163b668a85f9f9665a0d9c001cd630c4fce608833806d88e4e7","schema_version":"1.0","event_id":"sha256:da35a9efd35d5163b668a85f9f9665a0d9c001cd630c4fce608833806d88e4e7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XR7ZCHU7NJYIB5QTNHFSMXCTF3/bundle.json","state_url":"https://pith.science/pith/XR7ZCHU7NJYIB5QTNHFSMXCTF3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XR7ZCHU7NJYIB5QTNHFSMXCTF3/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":"2026-07-09T06:45:57Z","links":{"resolver":"https://pith.science/pith/XR7ZCHU7NJYIB5QTNHFSMXCTF3","bundle":"https://pith.science/pith/XR7ZCHU7NJYIB5QTNHFSMXCTF3/bundle.json","state":"https://pith.science/pith/XR7ZCHU7NJYIB5QTNHFSMXCTF3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XR7ZCHU7NJYIB5QTNHFSMXCTF3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XR7ZCHU7NJYIB5QTNHFSMXCTF3","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":"d06de464760dac2b53953b10a3b5deec725c0a5d3514651c193d3baaa0844df2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T03:59:06Z","title_canon_sha256":"68552a17253802c6156292939388ab77b27675e3e2c0c721408a6d7db74de4aa"},"schema_version":"1.0","source":{"id":"2305.13655","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13655","created_at":"2026-07-05T07:51:28Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13655v3","created_at":"2026-07-05T07:51:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13655","created_at":"2026-07-05T07:51:28Z"},{"alias_kind":"pith_short_12","alias_value":"XR7ZCHU7NJYI","created_at":"2026-07-05T07:51:28Z"},{"alias_kind":"pith_short_16","alias_value":"XR7ZCHU7NJYIB5QT","created_at":"2026-07-05T07:51:28Z"},{"alias_kind":"pith_short_8","alias_value":"XR7ZCHU7","created_at":"2026-07-05T07:51:28Z"}],"graph_snapshots":[{"event_id":"sha256:da35a9efd35d5163b668a85f9f9665a0d9c001cd630c4fce608833806d88e4e7","target":"graph","created_at":"2026-07-05T07:51:28Z","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/2305.13655/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in text-to-image diffusion models have yielded impressive results in generating realistic and diverse images. However, these models still struggle with complex prompts, such as those that involve numeracy and spatial reasoning. This work proposes to enhance prompt understanding capabilities in diffusion models. Our method leverages a pretrained large language model (LLM) for grounded generation in a novel two-stage process. In the first stage, the LLM generates a scene layout that comprises captioned bounding boxes from a given prompt describing the desired image. In the se","authors_text":"Adam Yala, Boyi Li, Long Lian, Trevor Darrell","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T03:59:06Z","title":"LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13655","kind":"arxiv","version":3},"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:d488ede400ba63e18d28d7e2d7918f29cabdf46026db53e2a0f932140f46909b","target":"record","created_at":"2026-07-05T07:51:28Z","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":"d06de464760dac2b53953b10a3b5deec725c0a5d3514651c193d3baaa0844df2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T03:59:06Z","title_canon_sha256":"68552a17253802c6156292939388ab77b27675e3e2c0c721408a6d7db74de4aa"},"schema_version":"1.0","source":{"id":"2305.13655","kind":"arxiv","version":3}},"canonical_sha256":"bc7f911e9f6a7080f61369cb265c532eceb220f0038ff2204061a95740d63b19","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc7f911e9f6a7080f61369cb265c532eceb220f0038ff2204061a95740d63b19","first_computed_at":"2026-07-05T07:51:28.391570Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:51:28.391570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yst0BS06z+FQiFx8BpDfFBX6RilqTB5QJYqGs7Co10CUx8caYO5VoWFUl4C5NwctwDNdyMqIiQRajhLdiOsCCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:51:28.392105Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13655","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d488ede400ba63e18d28d7e2d7918f29cabdf46026db53e2a0f932140f46909b","sha256:da35a9efd35d5163b668a85f9f9665a0d9c001cd630c4fce608833806d88e4e7"],"state_sha256":"30a0a984107c8542bdda89542a0fec20e4b6a9a1e7884063ef6dab5f482e26c5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7DRTQzVaTNTgtr0XmYy3k8n9QqL4bwHBJG8VHiWSggCGc07pXe2iKsS1aeAbrHh2wfClvkVg353QqshlHAZ2DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T06:45:57.067920Z","bundle_sha256":"5a32216b275624f17df4c22772cb695ff876d803c681cba96a87e349d9ec6301"}}