{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XBM6R44V7G2RRF4V3WNVYE7HMG","short_pith_number":"pith:XBM6R44V","canonical_record":{"source":{"id":"2501.01424","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-02T18:59:44Z","cross_cats_sorted":["cs.AI","cs.GR"],"title_canon_sha256":"a8c4323958171d98ada042345e0bbb1b91a32e7e0b0182fd20efed13dbf505e5","abstract_canon_sha256":"572a0b514dbdac31349481316388acdd3d400a996198fe94effe756a23d8df51"},"schema_version":"1.0"},"canonical_sha256":"b859e8f395f9b5189795dd9b5c13e76198b37abbc5c675a0e97677d17348e101","source":{"kind":"arxiv","id":"2501.01424","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01424","created_at":"2026-07-05T09:56:19Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01424v1","created_at":"2026-07-05T09:56:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01424","created_at":"2026-07-05T09:56:19Z"},{"alias_kind":"pith_short_12","alias_value":"XBM6R44V7G2R","created_at":"2026-07-05T09:56:19Z"},{"alias_kind":"pith_short_16","alias_value":"XBM6R44V7G2RRF4V","created_at":"2026-07-05T09:56:19Z"},{"alias_kind":"pith_short_8","alias_value":"XBM6R44V","created_at":"2026-07-05T09:56:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XBM6R44V7G2RRF4V3WNVYE7HMG","target":"record","payload":{"canonical_record":{"source":{"id":"2501.01424","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-02T18:59:44Z","cross_cats_sorted":["cs.AI","cs.GR"],"title_canon_sha256":"a8c4323958171d98ada042345e0bbb1b91a32e7e0b0182fd20efed13dbf505e5","abstract_canon_sha256":"572a0b514dbdac31349481316388acdd3d400a996198fe94effe756a23d8df51"},"schema_version":"1.0"},"canonical_sha256":"b859e8f395f9b5189795dd9b5c13e76198b37abbc5c675a0e97677d17348e101","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:19.595439Z","signature_b64":"ftqE/khnFBCmWzDzpX/A5lTrg2HEmi5ZQQRI4Qz1I6r/IsF7H/aQLVepK8uZyf8+VTT9nJFXkTjmSy/kNRvSAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b859e8f395f9b5189795dd9b5c13e76198b37abbc5c675a0e97677d17348e101","last_reissued_at":"2026-07-05T09:56:19.594960Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:19.594960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.01424","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:56:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xu9HOaF7SnfGiBcND4MZjT6eK7cdLKNsKRM+gLdfHu9HrPZdDx+gcxTGB0+sfTvEpvyyOTT41yD1FEbwUfj0CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T18:27:43.462696Z"},"content_sha256":"49fc091d4cb41bcf6de1d83e458c9e8c2ca5f1cbee19ee7fd7a32e378d51f908","schema_version":"1.0","event_id":"sha256:49fc091d4cb41bcf6de1d83e458c9e8c2ca5f1cbee19ee7fd7a32e378d51f908"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XBM6R44V7G2RRF4V3WNVYE7HMG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Object-level Visual Prompts for Compositional Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Daniel Cohen-Or, Daniil Ostashev, Gaurav Parmar, Jun-Yan Zhu, Kfir Aberman, Kuan-Chieh Wang, Or Patashnik, Srinivasa Narasimhan","submitted_at":"2025-01-02T18:59:44Z","abstract_excerpt":"We introduce a method for composing object-level visual prompts within a text-to-image diffusion model. Our approach addresses the task of generating semantically coherent compositions across diverse scenes and styles, similar to the versatility and expressiveness offered by text prompts. A key challenge in this task is to preserve the identity of the objects depicted in the input visual prompts, while also generating diverse compositions across different images. To address this challenge, we introduce a new KV-mixed cross-attention mechanism, in which keys and values are learned from distinct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01424","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/2501.01424/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":"2026-07-05T09:56:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GdyTSI0L1LHGSdZCIw98BzG/PMCbTyyivdoVB+RnHLgp7tMBcCDL/BJ+ZuIUVLvjQR5nzv3BLUc0Z7en+WmoBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T18:27:43.463208Z"},"content_sha256":"e79a00d6dc93b407cfc5a7c65f6487629207caa013e3c67f0f9490b0b42bbd31","schema_version":"1.0","event_id":"sha256:e79a00d6dc93b407cfc5a7c65f6487629207caa013e3c67f0f9490b0b42bbd31"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XBM6R44V7G2RRF4V3WNVYE7HMG/bundle.json","state_url":"https://pith.science/pith/XBM6R44V7G2RRF4V3WNVYE7HMG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XBM6R44V7G2RRF4V3WNVYE7HMG/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":"2026-08-22T18:27:43Z","links":{"resolver":"https://pith.science/pith/XBM6R44V7G2RRF4V3WNVYE7HMG","bundle":"https://pith.science/pith/XBM6R44V7G2RRF4V3WNVYE7HMG/bundle.json","state":"https://pith.science/pith/XBM6R44V7G2RRF4V3WNVYE7HMG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XBM6R44V7G2RRF4V3WNVYE7HMG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XBM6R44V7G2RRF4V3WNVYE7HMG","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":"572a0b514dbdac31349481316388acdd3d400a996198fe94effe756a23d8df51","cross_cats_sorted":["cs.AI","cs.GR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-02T18:59:44Z","title_canon_sha256":"a8c4323958171d98ada042345e0bbb1b91a32e7e0b0182fd20efed13dbf505e5"},"schema_version":"1.0","source":{"id":"2501.01424","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01424","created_at":"2026-07-05T09:56:19Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01424v1","created_at":"2026-07-05T09:56:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01424","created_at":"2026-07-05T09:56:19Z"},{"alias_kind":"pith_short_12","alias_value":"XBM6R44V7G2R","created_at":"2026-07-05T09:56:19Z"},{"alias_kind":"pith_short_16","alias_value":"XBM6R44V7G2RRF4V","created_at":"2026-07-05T09:56:19Z"},{"alias_kind":"pith_short_8","alias_value":"XBM6R44V","created_at":"2026-07-05T09:56:19Z"}],"graph_snapshots":[{"event_id":"sha256:e79a00d6dc93b407cfc5a7c65f6487629207caa013e3c67f0f9490b0b42bbd31","target":"graph","created_at":"2026-07-05T09:56:19Z","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/2501.01424/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a method for composing object-level visual prompts within a text-to-image diffusion model. Our approach addresses the task of generating semantically coherent compositions across diverse scenes and styles, similar to the versatility and expressiveness offered by text prompts. A key challenge in this task is to preserve the identity of the objects depicted in the input visual prompts, while also generating diverse compositions across different images. To address this challenge, we introduce a new KV-mixed cross-attention mechanism, in which keys and values are learned from distinct","authors_text":"Daniel Cohen-Or, Daniil Ostashev, Gaurav Parmar, Jun-Yan Zhu, Kfir Aberman, Kuan-Chieh Wang, Or Patashnik, Srinivasa Narasimhan","cross_cats":["cs.AI","cs.GR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-02T18:59:44Z","title":"Object-level Visual Prompts for Compositional Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01424","kind":"arxiv","version":1},"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":"sha256:49fc091d4cb41bcf6de1d83e458c9e8c2ca5f1cbee19ee7fd7a32e378d51f908","target":"record","created_at":"2026-07-05T09:56:19Z","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":"572a0b514dbdac31349481316388acdd3d400a996198fe94effe756a23d8df51","cross_cats_sorted":["cs.AI","cs.GR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-02T18:59:44Z","title_canon_sha256":"a8c4323958171d98ada042345e0bbb1b91a32e7e0b0182fd20efed13dbf505e5"},"schema_version":"1.0","source":{"id":"2501.01424","kind":"arxiv","version":1}},"canonical_sha256":"b859e8f395f9b5189795dd9b5c13e76198b37abbc5c675a0e97677d17348e101","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b859e8f395f9b5189795dd9b5c13e76198b37abbc5c675a0e97677d17348e101","first_computed_at":"2026-07-05T09:56:19.594960Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:56:19.594960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ftqE/khnFBCmWzDzpX/A5lTrg2HEmi5ZQQRI4Qz1I6r/IsF7H/aQLVepK8uZyf8+VTT9nJFXkTjmSy/kNRvSAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:56:19.595439Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.01424","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49fc091d4cb41bcf6de1d83e458c9e8c2ca5f1cbee19ee7fd7a32e378d51f908","sha256:e79a00d6dc93b407cfc5a7c65f6487629207caa013e3c67f0f9490b0b42bbd31"],"state_sha256":"143b66327c3bee539ffb4ff154bc4f0ea4d46cb688acf69a548ff357d68e6ca2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wSN3HVjnriRmec/9x5xEovsFNukbr7VkKdYgOdcAJ0GXQ/SRmdRLVS8jdkLavKwuAoIB1p+LQYIkjhzcaT7rAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T18:27:43.467959Z","bundle_sha256":"9eb79a451d43a7eb761155fa3702b7e8e50f25edf55e502c67bf040671715bef"}}