{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AMGTRCT5GMIK56A5OXKQ6OPVPS","short_pith_number":"pith:AMGTRCT5","schema_version":"1.0","canonical_sha256":"030d388a7d3310aef81d75d50f39f57cb289346073a658f2e6f411b64a0e6df9","source":{"kind":"arxiv","id":"2411.16783","version":1},"attestation_state":"computed","paper":{"title":"CoCoNO: Attention Contrast-and-Complete for Initial Noise Optimization in Text-to-Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhimanyu Chauhan, Aishwarya Agarwal, Aravindan Sundaram, Srikrishna Karanam, Ujjayan Pal","submitted_at":"2024-11-25T08:20:14Z","abstract_excerpt":"Despite recent advancements in text-to-image models, achieving semantically accurate images in text-to-image diffusion models is a persistent challenge. While existing initial latent optimization methods have demonstrated impressive performance, we identify two key limitations: (a) attention neglect, where the synthesized image omits certain subjects from the input prompt because they do not have a designated segment in the self-attention map despite despite having a high-response cross-attention, and (b) attention interference, where the generated image has mixed-up properties of multiple sub"},"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":"2411.16783","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T08:20:14Z","cross_cats_sorted":[],"title_canon_sha256":"bdb3f1028f6e224f8dc5b4d25ad79d499153132bf9c1d714d50f5226bbd9a939","abstract_canon_sha256":"aeb8f5575cd723ea3ab41e1e868c9c4104832b87f33a47a3e926ac5e4a7b58c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:23.064964Z","signature_b64":"7DX7bUq9+qnA9QIpGvpnclI6lh84Gnl0jhJEehc87RM84JhzJ/TZfoVLxnCLw/dHcDBMPRhVIVVcz/tSVDkCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"030d388a7d3310aef81d75d50f39f57cb289346073a658f2e6f411b64a0e6df9","last_reissued_at":"2026-07-05T09:40:23.064537Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:23.064537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoCoNO: Attention Contrast-and-Complete for Initial Noise Optimization in Text-to-Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhimanyu Chauhan, Aishwarya Agarwal, Aravindan Sundaram, Srikrishna Karanam, Ujjayan Pal","submitted_at":"2024-11-25T08:20:14Z","abstract_excerpt":"Despite recent advancements in text-to-image models, achieving semantically accurate images in text-to-image diffusion models is a persistent challenge. While existing initial latent optimization methods have demonstrated impressive performance, we identify two key limitations: (a) attention neglect, where the synthesized image omits certain subjects from the input prompt because they do not have a designated segment in the self-attention map despite despite having a high-response cross-attention, and (b) attention interference, where the generated image has mixed-up properties of multiple sub"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16783","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/2411.16783/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":"2411.16783","created_at":"2026-07-05T09:40:23.064594+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16783v1","created_at":"2026-07-05T09:40:23.064594+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16783","created_at":"2026-07-05T09:40:23.064594+00:00"},{"alias_kind":"pith_short_12","alias_value":"AMGTRCT5GMIK","created_at":"2026-07-05T09:40:23.064594+00:00"},{"alias_kind":"pith_short_16","alias_value":"AMGTRCT5GMIK56A5","created_at":"2026-07-05T09:40:23.064594+00:00"},{"alias_kind":"pith_short_8","alias_value":"AMGTRCT5","created_at":"2026-07-05T09:40:23.064594+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.00090","citing_title":"It's Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Models","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AMGTRCT5GMIK56A5OXKQ6OPVPS","json":"https://pith.science/pith/AMGTRCT5GMIK56A5OXKQ6OPVPS.json","graph_json":"https://pith.science/api/pith-number/AMGTRCT5GMIK56A5OXKQ6OPVPS/graph.json","events_json":"https://pith.science/api/pith-number/AMGTRCT5GMIK56A5OXKQ6OPVPS/events.json","paper":"https://pith.science/paper/AMGTRCT5"},"agent_actions":{"view_html":"https://pith.science/pith/AMGTRCT5GMIK56A5OXKQ6OPVPS","download_json":"https://pith.science/pith/AMGTRCT5GMIK56A5OXKQ6OPVPS.json","view_paper":"https://pith.science/paper/AMGTRCT5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16783&json=true","fetch_graph":"https://pith.science/api/pith-number/AMGTRCT5GMIK56A5OXKQ6OPVPS/graph.json","fetch_events":"https://pith.science/api/pith-number/AMGTRCT5GMIK56A5OXKQ6OPVPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AMGTRCT5GMIK56A5OXKQ6OPVPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AMGTRCT5GMIK56A5OXKQ6OPVPS/action/storage_attestation","attest_author":"https://pith.science/pith/AMGTRCT5GMIK56A5OXKQ6OPVPS/action/author_attestation","sign_citation":"https://pith.science/pith/AMGTRCT5GMIK56A5OXKQ6OPVPS/action/citation_signature","submit_replication":"https://pith.science/pith/AMGTRCT5GMIK56A5OXKQ6OPVPS/action/replication_record"}},"created_at":"2026-07-05T09:40:23.064594+00:00","updated_at":"2026-07-05T09:40:23.064594+00:00"}