{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NPUJ5WYE3ABCTZRSVWELEXWGKE","short_pith_number":"pith:NPUJ5WYE","schema_version":"1.0","canonical_sha256":"6be89edb04d80229e632ad88b25ec651054b617257989ff6315d5624f84d2f29","source":{"kind":"arxiv","id":"2408.11721","version":2},"attestation_state":"computed","paper":{"title":"Detection-Driven Object Count Optimization for Text-to-Image Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Idan Schwartz, Lior Wolf, Oz Zafar, Yuval Cohen","submitted_at":"2024-08-21T15:51:46Z","abstract_excerpt":"Accurately controlling object count in text-to-image generation remains a key challenge. Supervised methods often fail, as training data rarely covers all count variations. Methods that manipulate the denoising process to add or remove objects can help; however, they still require labeled data, limit robustness and image quality, and rely on a slow, iterative process.\n  Pre-trained differentiable counting models that rely on soft object density summation exist and could steer generation, but employing them presents three main challenges: (i) they are pre-trained on clean images, making them le"},"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":"2408.11721","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-21T15:51:46Z","cross_cats_sorted":["cs.AI","cs.GR","cs.LG"],"title_canon_sha256":"6fe6ef00bf9aca6db21e1c6e9527a9d6db59e94c7d4e907e2b7c2b90463efe14","abstract_canon_sha256":"bb8eb460db011583cc196087e71edbf437d549a5757cb11af4096c1ae609f178"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:29.101024Z","signature_b64":"++fg2GrIlKiKycpqvoQlB3wnICgtRCyBeRheL+KCyE4BtUydpMSw05Lt0FWIsYxvf15wE8UdWx5gtBG2HR8QDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6be89edb04d80229e632ad88b25ec651054b617257989ff6315d5624f84d2f29","last_reissued_at":"2026-07-05T11:16:29.100443Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:29.100443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detection-Driven Object Count Optimization for Text-to-Image Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Idan Schwartz, Lior Wolf, Oz Zafar, Yuval Cohen","submitted_at":"2024-08-21T15:51:46Z","abstract_excerpt":"Accurately controlling object count in text-to-image generation remains a key challenge. Supervised methods often fail, as training data rarely covers all count variations. Methods that manipulate the denoising process to add or remove objects can help; however, they still require labeled data, limit robustness and image quality, and rely on a slow, iterative process.\n  Pre-trained differentiable counting models that rely on soft object density summation exist and could steer generation, but employing them presents three main challenges: (i) they are pre-trained on clean images, making them le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11721","kind":"arxiv","version":2},"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/2408.11721/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":"2408.11721","created_at":"2026-07-05T11:16:29.100512+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.11721v2","created_at":"2026-07-05T11:16:29.100512+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11721","created_at":"2026-07-05T11:16:29.100512+00:00"},{"alias_kind":"pith_short_12","alias_value":"NPUJ5WYE3ABC","created_at":"2026-07-05T11:16:29.100512+00:00"},{"alias_kind":"pith_short_16","alias_value":"NPUJ5WYE3ABCTZRS","created_at":"2026-07-05T11:16:29.100512+00:00"},{"alias_kind":"pith_short_8","alias_value":"NPUJ5WYE","created_at":"2026-07-05T11:16:29.100512+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.17458","citing_title":"CARINOX: Inference-time Scaling with Category-Aware Reward-based Initial Noise Optimization and Exploration","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NPUJ5WYE3ABCTZRSVWELEXWGKE","json":"https://pith.science/pith/NPUJ5WYE3ABCTZRSVWELEXWGKE.json","graph_json":"https://pith.science/api/pith-number/NPUJ5WYE3ABCTZRSVWELEXWGKE/graph.json","events_json":"https://pith.science/api/pith-number/NPUJ5WYE3ABCTZRSVWELEXWGKE/events.json","paper":"https://pith.science/paper/NPUJ5WYE"},"agent_actions":{"view_html":"https://pith.science/pith/NPUJ5WYE3ABCTZRSVWELEXWGKE","download_json":"https://pith.science/pith/NPUJ5WYE3ABCTZRSVWELEXWGKE.json","view_paper":"https://pith.science/paper/NPUJ5WYE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.11721&json=true","fetch_graph":"https://pith.science/api/pith-number/NPUJ5WYE3ABCTZRSVWELEXWGKE/graph.json","fetch_events":"https://pith.science/api/pith-number/NPUJ5WYE3ABCTZRSVWELEXWGKE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NPUJ5WYE3ABCTZRSVWELEXWGKE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NPUJ5WYE3ABCTZRSVWELEXWGKE/action/storage_attestation","attest_author":"https://pith.science/pith/NPUJ5WYE3ABCTZRSVWELEXWGKE/action/author_attestation","sign_citation":"https://pith.science/pith/NPUJ5WYE3ABCTZRSVWELEXWGKE/action/citation_signature","submit_replication":"https://pith.science/pith/NPUJ5WYE3ABCTZRSVWELEXWGKE/action/replication_record"}},"created_at":"2026-07-05T11:16:29.100512+00:00","updated_at":"2026-07-05T11:16:29.100512+00:00"}