{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UCSO7U3QHZ7YSPXQTSL5XZJ2VK","short_pith_number":"pith:UCSO7U3Q","schema_version":"1.0","canonical_sha256":"a0a4efd3703e7f893ef09c97dbe53aaa9629d8c0a9a1cf569d3614c98c8d4fa1","source":{"kind":"arxiv","id":"2411.07132","version":1},"attestation_state":"computed","paper":{"title":"Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Hongcheng Gao, Jian Yang, Joost Van De Weijer, Kai Wang, Linxuan Li, Ming-Ming Cheng, Taihang Hu, Yaxing Wang","submitted_at":"2024-11-11T17:05:15Z","abstract_excerpt":"Although text-to-image (T2I) models exhibit remarkable generation capabilities, they frequently fail to accurately bind semantically related objects or attributes in the input prompts; a challenge termed semantic binding. Previous approaches either involve intensive fine-tuning of the entire T2I model or require users or large language models to specify generation layouts, adding complexity. In this paper, we define semantic binding as the task of associating a given object with its attribute, termed attribute binding, or linking it to other related sub-objects, referred to as object binding. "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2411.07132","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-11T17:05:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e66188df1e8ba644eb2a5a000dde76b351fc6acaeaaad3fe1ea62dfd26da24bc","abstract_canon_sha256":"b2a99abde7b6842e8e8328ad1366fe9825bff1b0dac4740626c451cacbe8fb25"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:57.187370Z","signature_b64":"I5PfbsR6EDq/cDY6fGvcq46laPN0aBw7gGjy7cayQjht21+8nHPhkLnjNUwXxJien5VsN0gSyt3UXJCRycW+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0a4efd3703e7f893ef09c97dbe53aaa9629d8c0a9a1cf569d3614c98c8d4fa1","last_reissued_at":"2026-07-05T09:33:57.186876Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:57.186876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Hongcheng Gao, Jian Yang, Joost Van De Weijer, Kai Wang, Linxuan Li, Ming-Ming Cheng, Taihang Hu, Yaxing Wang","submitted_at":"2024-11-11T17:05:15Z","abstract_excerpt":"Although text-to-image (T2I) models exhibit remarkable generation capabilities, they frequently fail to accurately bind semantically related objects or attributes in the input prompts; a challenge termed semantic binding. Previous approaches either involve intensive fine-tuning of the entire T2I model or require users or large language models to specify generation layouts, adding complexity. In this paper, we define semantic binding as the task of associating a given object with its attribute, termed attribute binding, or linking it to other related sub-objects, referred to as object binding. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07132","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/2411.07132/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.07132","created_at":"2026-07-05T09:33:57.186944+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.07132v1","created_at":"2026-07-05T09:33:57.186944+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07132","created_at":"2026-07-05T09:33:57.186944+00:00"},{"alias_kind":"pith_short_12","alias_value":"UCSO7U3QHZ7Y","created_at":"2026-07-05T09:33:57.186944+00:00"},{"alias_kind":"pith_short_16","alias_value":"UCSO7U3QHZ7YSPXQ","created_at":"2026-07-05T09:33:57.186944+00:00"},{"alias_kind":"pith_short_8","alias_value":"UCSO7U3Q","created_at":"2026-07-05T09:33:57.186944+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23245","citing_title":"SimInsert: Seamless Video Object Insertion via Regional Sparse Attention Fusion","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UCSO7U3QHZ7YSPXQTSL5XZJ2VK","json":"https://pith.science/pith/UCSO7U3QHZ7YSPXQTSL5XZJ2VK.json","graph_json":"https://pith.science/api/pith-number/UCSO7U3QHZ7YSPXQTSL5XZJ2VK/graph.json","events_json":"https://pith.science/api/pith-number/UCSO7U3QHZ7YSPXQTSL5XZJ2VK/events.json","paper":"https://pith.science/paper/UCSO7U3Q"},"agent_actions":{"view_html":"https://pith.science/pith/UCSO7U3QHZ7YSPXQTSL5XZJ2VK","download_json":"https://pith.science/pith/UCSO7U3QHZ7YSPXQTSL5XZJ2VK.json","view_paper":"https://pith.science/paper/UCSO7U3Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.07132&json=true","fetch_graph":"https://pith.science/api/pith-number/UCSO7U3QHZ7YSPXQTSL5XZJ2VK/graph.json","fetch_events":"https://pith.science/api/pith-number/UCSO7U3QHZ7YSPXQTSL5XZJ2VK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UCSO7U3QHZ7YSPXQTSL5XZJ2VK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UCSO7U3QHZ7YSPXQTSL5XZJ2VK/action/storage_attestation","attest_author":"https://pith.science/pith/UCSO7U3QHZ7YSPXQTSL5XZJ2VK/action/author_attestation","sign_citation":"https://pith.science/pith/UCSO7U3QHZ7YSPXQTSL5XZJ2VK/action/citation_signature","submit_replication":"https://pith.science/pith/UCSO7U3QHZ7YSPXQTSL5XZJ2VK/action/replication_record"}},"created_at":"2026-07-05T09:33:57.186944+00:00","updated_at":"2026-07-05T09:33:57.186944+00:00"}