{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UT7D7AIHD5MKYHXRRKHW27AUCR","short_pith_number":"pith:UT7D7AIH","schema_version":"1.0","canonical_sha256":"a4fe3f81071f58ac1ef18a8f6d7c141453ef7fecdc2bddb78ea6962b9cc84667","source":{"kind":"arxiv","id":"2507.00789","version":1},"attestation_state":"computed","paper":{"title":"OptiPrune: Boosting Prompt-Image Consistency with Attention-Guided Noise and Dynamic Token Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ziji Lu","submitted_at":"2025-07-01T14:24:40Z","abstract_excerpt":"Text-to-image diffusion models often struggle to achieve accurate semantic alignment between generated images and text prompts while maintaining efficiency for deployment on resource-constrained hardware. Existing approaches either incur substantial computational overhead through noise optimization or compromise semantic fidelity by aggressively pruning tokens. In this work, we propose OptiPrune, a unified framework that combines distribution-aware initial noise optimization with similarity-based token pruning to address both challenges simultaneously. Specifically, (1) we introduce a distribu"},"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":"2507.00789","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T14:24:40Z","cross_cats_sorted":[],"title_canon_sha256":"dad2c08920d127d932f3ec5cfae3a0c39043c142703358026f6dc5e71a9e005b","abstract_canon_sha256":"9c0e3bd1d2103e5792bea9921caabce4f877f874e7baeafb38cd94d26c24ac9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:14.467161Z","signature_b64":"AHlUFVsHh8gG44TvwcUBxoL32xt19kLvaZeak0g9nXiyRKls/9B1uNmF6xzS2wR0DjYSPH0H5GCDdqXG4nraAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4fe3f81071f58ac1ef18a8f6d7c141453ef7fecdc2bddb78ea6962b9cc84667","last_reissued_at":"2026-07-05T11:30:14.466021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:14.466021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OptiPrune: Boosting Prompt-Image Consistency with Attention-Guided Noise and Dynamic Token Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ziji Lu","submitted_at":"2025-07-01T14:24:40Z","abstract_excerpt":"Text-to-image diffusion models often struggle to achieve accurate semantic alignment between generated images and text prompts while maintaining efficiency for deployment on resource-constrained hardware. Existing approaches either incur substantial computational overhead through noise optimization or compromise semantic fidelity by aggressively pruning tokens. In this work, we propose OptiPrune, a unified framework that combines distribution-aware initial noise optimization with similarity-based token pruning to address both challenges simultaneously. Specifically, (1) we introduce a distribu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00789","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/2507.00789/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":"2507.00789","created_at":"2026-07-05T11:30:14.466493+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00789v1","created_at":"2026-07-05T11:30:14.466493+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00789","created_at":"2026-07-05T11:30:14.466493+00:00"},{"alias_kind":"pith_short_12","alias_value":"UT7D7AIHD5MK","created_at":"2026-07-05T11:30:14.466493+00:00"},{"alias_kind":"pith_short_16","alias_value":"UT7D7AIHD5MKYHXR","created_at":"2026-07-05T11:30:14.466493+00:00"},{"alias_kind":"pith_short_8","alias_value":"UT7D7AIH","created_at":"2026-07-05T11:30:14.466493+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UT7D7AIHD5MKYHXRRKHW27AUCR","json":"https://pith.science/pith/UT7D7AIHD5MKYHXRRKHW27AUCR.json","graph_json":"https://pith.science/api/pith-number/UT7D7AIHD5MKYHXRRKHW27AUCR/graph.json","events_json":"https://pith.science/api/pith-number/UT7D7AIHD5MKYHXRRKHW27AUCR/events.json","paper":"https://pith.science/paper/UT7D7AIH"},"agent_actions":{"view_html":"https://pith.science/pith/UT7D7AIHD5MKYHXRRKHW27AUCR","download_json":"https://pith.science/pith/UT7D7AIHD5MKYHXRRKHW27AUCR.json","view_paper":"https://pith.science/paper/UT7D7AIH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00789&json=true","fetch_graph":"https://pith.science/api/pith-number/UT7D7AIHD5MKYHXRRKHW27AUCR/graph.json","fetch_events":"https://pith.science/api/pith-number/UT7D7AIHD5MKYHXRRKHW27AUCR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UT7D7AIHD5MKYHXRRKHW27AUCR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UT7D7AIHD5MKYHXRRKHW27AUCR/action/storage_attestation","attest_author":"https://pith.science/pith/UT7D7AIHD5MKYHXRRKHW27AUCR/action/author_attestation","sign_citation":"https://pith.science/pith/UT7D7AIHD5MKYHXRRKHW27AUCR/action/citation_signature","submit_replication":"https://pith.science/pith/UT7D7AIHD5MKYHXRRKHW27AUCR/action/replication_record"}},"created_at":"2026-07-05T11:30:14.466493+00:00","updated_at":"2026-07-05T11:30:14.466493+00:00"}