{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PYDMUMQT6E3WSEIYH7WB7GXUZA","short_pith_number":"pith:PYDMUMQT","canonical_record":{"source":{"id":"2305.19599","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-31T06:59:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4b2801c474e7949e3b6470aedc2cce6c5bed37ecaaed475aee8e95a531783304","abstract_canon_sha256":"825faa410a922f94caac6d353851725275047daca8e4e8c15eeb7ca02961141e"},"schema_version":"1.0"},"canonical_sha256":"7e06ca3213f1376911183fec1f9af4c81987cdc3b5804c34b717be9b136c6187","source":{"kind":"arxiv","id":"2305.19599","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.19599","created_at":"2026-07-05T09:24:51Z"},{"alias_kind":"arxiv_version","alias_value":"2305.19599v5","created_at":"2026-07-05T09:24:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19599","created_at":"2026-07-05T09:24:51Z"},{"alias_kind":"pith_short_12","alias_value":"PYDMUMQT6E3W","created_at":"2026-07-05T09:24:51Z"},{"alias_kind":"pith_short_16","alias_value":"PYDMUMQT6E3WSEIY","created_at":"2026-07-05T09:24:51Z"},{"alias_kind":"pith_short_8","alias_value":"PYDMUMQT","created_at":"2026-07-05T09:24:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PYDMUMQT6E3WSEIYH7WB7GXUZA","target":"record","payload":{"canonical_record":{"source":{"id":"2305.19599","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-31T06:59:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4b2801c474e7949e3b6470aedc2cce6c5bed37ecaaed475aee8e95a531783304","abstract_canon_sha256":"825faa410a922f94caac6d353851725275047daca8e4e8c15eeb7ca02961141e"},"schema_version":"1.0"},"canonical_sha256":"7e06ca3213f1376911183fec1f9af4c81987cdc3b5804c34b717be9b136c6187","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:51.137433Z","signature_b64":"HCn1TQykSahBtI8kCydX9sVLbNbvFLei7XhZL1bM7Sp9+IaOJfH2gclNc7fPB+Dq9uJdQcl9mB091NqJxolGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e06ca3213f1376911183fec1f9af4c81987cdc3b5804c34b717be9b136c6187","last_reissued_at":"2026-07-05T09:24:51.136932Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:51.136932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.19599","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:24:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3rTKDC28UtRI2CIOUQX4SM67sYiHom6wVw6FRQoH7t9s/DAzy+Y5a0StgtRwdOmkxc+OtyHekuh7CuU6cDHcDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T19:55:25.054106Z"},"content_sha256":"eff56113e7978e300f6ed6c493f9bf9897db07d14e16fa997b82d2bf9258fc3c","schema_version":"1.0","event_id":"sha256:eff56113e7978e300f6ed6c493f9bf9897db07d14e16fa997b82d2bf9258fc3c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PYDMUMQT6E3WSEIYH7WB7GXUZA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RealignDiff: Boosting Text-to-Image Diffusion Model with Coarse-to-fine Semantic Re-alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guansong Lu, Guian Fang, Hang Xu, Jianhua Han, Shengcai Liao, Xiaodan Liang, Xiaojun Chang, Zutao Jiang","submitted_at":"2023-05-31T06:59:21Z","abstract_excerpt":"Recent advances in text-to-image diffusion models have achieved remarkable success in generating high-quality, realistic images from textual descriptions. However, these approaches have faced challenges in precisely aligning the generated visual content with the textual concepts described in the prompts. In this paper, we propose a two-stage coarse-to-fine semantic re-alignment method, named RealignDiff, aimed at improving the alignment between text and images in text-to-image diffusion models. In the coarse semantic re-alignment phase, a novel caption reward, leveraging the BLIP-2 model, is p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19599","kind":"arxiv","version":5},"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/2305.19599/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":"2026-07-05T09:24:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z2SYnfWEMYiVk2/2jUFUuVAIv4pC+wlFMBcLNgWRNfEwJeVLPa5IOj9PfeQL2/lnJfvjenCVEeCHbfxAk7PfDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T19:55:25.055093Z"},"content_sha256":"a4dc65c8374787b72dde29db852933df3eb3f700aa1ccf4dbc959a55fdac54ad","schema_version":"1.0","event_id":"sha256:a4dc65c8374787b72dde29db852933df3eb3f700aa1ccf4dbc959a55fdac54ad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PYDMUMQT6E3WSEIYH7WB7GXUZA/bundle.json","state_url":"https://pith.science/pith/PYDMUMQT6E3WSEIYH7WB7GXUZA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PYDMUMQT6E3WSEIYH7WB7GXUZA/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":"2026-08-12T19:55:25Z","links":{"resolver":"https://pith.science/pith/PYDMUMQT6E3WSEIYH7WB7GXUZA","bundle":"https://pith.science/pith/PYDMUMQT6E3WSEIYH7WB7GXUZA/bundle.json","state":"https://pith.science/pith/PYDMUMQT6E3WSEIYH7WB7GXUZA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PYDMUMQT6E3WSEIYH7WB7GXUZA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PYDMUMQT6E3WSEIYH7WB7GXUZA","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":"825faa410a922f94caac6d353851725275047daca8e4e8c15eeb7ca02961141e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-31T06:59:21Z","title_canon_sha256":"4b2801c474e7949e3b6470aedc2cce6c5bed37ecaaed475aee8e95a531783304"},"schema_version":"1.0","source":{"id":"2305.19599","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.19599","created_at":"2026-07-05T09:24:51Z"},{"alias_kind":"arxiv_version","alias_value":"2305.19599v5","created_at":"2026-07-05T09:24:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19599","created_at":"2026-07-05T09:24:51Z"},{"alias_kind":"pith_short_12","alias_value":"PYDMUMQT6E3W","created_at":"2026-07-05T09:24:51Z"},{"alias_kind":"pith_short_16","alias_value":"PYDMUMQT6E3WSEIY","created_at":"2026-07-05T09:24:51Z"},{"alias_kind":"pith_short_8","alias_value":"PYDMUMQT","created_at":"2026-07-05T09:24:51Z"}],"graph_snapshots":[{"event_id":"sha256:a4dc65c8374787b72dde29db852933df3eb3f700aa1ccf4dbc959a55fdac54ad","target":"graph","created_at":"2026-07-05T09:24:51Z","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/2305.19599/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in text-to-image diffusion models have achieved remarkable success in generating high-quality, realistic images from textual descriptions. However, these approaches have faced challenges in precisely aligning the generated visual content with the textual concepts described in the prompts. In this paper, we propose a two-stage coarse-to-fine semantic re-alignment method, named RealignDiff, aimed at improving the alignment between text and images in text-to-image diffusion models. In the coarse semantic re-alignment phase, a novel caption reward, leveraging the BLIP-2 model, is p","authors_text":"Guansong Lu, Guian Fang, Hang Xu, Jianhua Han, Shengcai Liao, Xiaodan Liang, Xiaojun Chang, Zutao Jiang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-31T06:59:21Z","title":"RealignDiff: Boosting Text-to-Image Diffusion Model with Coarse-to-fine Semantic Re-alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19599","kind":"arxiv","version":5},"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:eff56113e7978e300f6ed6c493f9bf9897db07d14e16fa997b82d2bf9258fc3c","target":"record","created_at":"2026-07-05T09:24:51Z","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":"825faa410a922f94caac6d353851725275047daca8e4e8c15eeb7ca02961141e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-31T06:59:21Z","title_canon_sha256":"4b2801c474e7949e3b6470aedc2cce6c5bed37ecaaed475aee8e95a531783304"},"schema_version":"1.0","source":{"id":"2305.19599","kind":"arxiv","version":5}},"canonical_sha256":"7e06ca3213f1376911183fec1f9af4c81987cdc3b5804c34b717be9b136c6187","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e06ca3213f1376911183fec1f9af4c81987cdc3b5804c34b717be9b136c6187","first_computed_at":"2026-07-05T09:24:51.136932Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:24:51.136932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HCn1TQykSahBtI8kCydX9sVLbNbvFLei7XhZL1bM7Sp9+IaOJfH2gclNc7fPB+Dq9uJdQcl9mB091NqJxolGBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:24:51.137433Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.19599","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eff56113e7978e300f6ed6c493f9bf9897db07d14e16fa997b82d2bf9258fc3c","sha256:a4dc65c8374787b72dde29db852933df3eb3f700aa1ccf4dbc959a55fdac54ad"],"state_sha256":"3e4d93cb7b6e8ad8c172bad85f3e2dc1b250bb46015ca7266fac60d5e4106d05"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/UV7LNlov2b7AYjc3+SiV/zasqRzl28Y/x+VHCFX66lXX5RCiThxoTeVgXTZO6BxcQFjgZIzyQ9POIIz4QFbBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T19:55:25.062729Z","bundle_sha256":"f69ace3f3a9ea6a6e8c39ca92cf50d11c4063d8ff3720fdcec05f67e0091af66"}}