{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3OPTKOC2IMGX3UNRM2VSTF4Z4P","short_pith_number":"pith:3OPTKOC2","canonical_record":{"source":{"id":"2503.16406","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2025-03-20T17:56:20Z","cross_cats_sorted":["cs.CV","cs.MM"],"title_canon_sha256":"cd489a0d8fbf7f359ee971fa1d658113da2f051e1cb186a972050587877d642e","abstract_canon_sha256":"6c4a617ee58039f8dab3c23ebb8801eb568ab7c573a26f2cf1a74ce617f90584"},"schema_version":"1.0"},"canonical_sha256":"db9f35385a430d7dd1b166ab299799e3ead1bfd5e204291be9007d00643429e9","source":{"kind":"arxiv","id":"2503.16406","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.16406","created_at":"2026-07-05T10:36:18Z"},{"alias_kind":"arxiv_version","alias_value":"2503.16406v1","created_at":"2026-07-05T10:36:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16406","created_at":"2026-07-05T10:36:18Z"},{"alias_kind":"pith_short_12","alias_value":"3OPTKOC2IMGX","created_at":"2026-07-05T10:36:18Z"},{"alias_kind":"pith_short_16","alias_value":"3OPTKOC2IMGX3UNR","created_at":"2026-07-05T10:36:18Z"},{"alias_kind":"pith_short_8","alias_value":"3OPTKOC2","created_at":"2026-07-05T10:36:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3OPTKOC2IMGX3UNRM2VSTF4Z4P","target":"record","payload":{"canonical_record":{"source":{"id":"2503.16406","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2025-03-20T17:56:20Z","cross_cats_sorted":["cs.CV","cs.MM"],"title_canon_sha256":"cd489a0d8fbf7f359ee971fa1d658113da2f051e1cb186a972050587877d642e","abstract_canon_sha256":"6c4a617ee58039f8dab3c23ebb8801eb568ab7c573a26f2cf1a74ce617f90584"},"schema_version":"1.0"},"canonical_sha256":"db9f35385a430d7dd1b166ab299799e3ead1bfd5e204291be9007d00643429e9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:18.772358Z","signature_b64":"88LPRjBMnEBkDCrOktoqgQAO6XS/rekhJ6QofcK3Z9d40u4NRfsbjQWgodNyyCut1hKX6zlSOwwZwtdDm8KQAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db9f35385a430d7dd1b166ab299799e3ead1bfd5e204291be9007d00643429e9","last_reissued_at":"2026-07-05T10:36:18.771545Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:18.771545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.16406","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":"2026-07-05T10:36:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MZTQLtFlvjfbwppT6nTcDDNoZclYjOqLcfZzb2uaacVP9JV1bPDgFwdT0CNix92q5YP8FivxaHQYUYllzDOpAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T18:01:10.976998Z"},"content_sha256":"48cfecc2f9013005a479027a807dcb6e221b82de2adaf9bbab7436085cba06f0","schema_version":"1.0","event_id":"sha256:48cfecc2f9013005a479027a807dcb6e221b82de2adaf9bbab7436085cba06f0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3OPTKOC2IMGX3UNRM2VSTF4Z4P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VerbDiff: Text-Only Diffusion Models with Enhanced Interaction Awareness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MM"],"primary_cat":"cs.GR","authors_text":"Dong-Jin Kim, Hyunwoo Oh, Kwanyoung Lee, SeungJu Cha, Ye-Chan Kim","submitted_at":"2025-03-20T17:56:20Z","abstract_excerpt":"Recent large-scale text-to-image diffusion models generate photorealistic images but often struggle to accurately depict interactions between humans and objects due to their limited ability to differentiate various interaction words. In this work, we propose VerbDiff to address the challenge of capturing nuanced interactions within text-to-image diffusion models. VerbDiff is a novel text-to-image generation model that weakens the bias between interaction words and objects, enhancing the understanding of interactions. Specifically, we disentangle various interaction words from frequency-based a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16406","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/2503.16406/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":"2026-07-05T10:36:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0ZgGZCMB9B/BvpWsZCrIi3BNtKpqx6zP8l0iW8uREp/13M/T8pT0drzUa4/oNaQeVTJvQ/gxAg7V8KkGFC94Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T18:01:10.978003Z"},"content_sha256":"c4bd74a8598ebc38c2aed8b327cf4f9d35ed3a422dff5f9a6a88740521aaf631","schema_version":"1.0","event_id":"sha256:c4bd74a8598ebc38c2aed8b327cf4f9d35ed3a422dff5f9a6a88740521aaf631"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3OPTKOC2IMGX3UNRM2VSTF4Z4P/bundle.json","state_url":"https://pith.science/pith/3OPTKOC2IMGX3UNRM2VSTF4Z4P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3OPTKOC2IMGX3UNRM2VSTF4Z4P/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":"2026-08-16T18:01:10Z","links":{"resolver":"https://pith.science/pith/3OPTKOC2IMGX3UNRM2VSTF4Z4P","bundle":"https://pith.science/pith/3OPTKOC2IMGX3UNRM2VSTF4Z4P/bundle.json","state":"https://pith.science/pith/3OPTKOC2IMGX3UNRM2VSTF4Z4P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3OPTKOC2IMGX3UNRM2VSTF4Z4P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3OPTKOC2IMGX3UNRM2VSTF4Z4P","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":"6c4a617ee58039f8dab3c23ebb8801eb568ab7c573a26f2cf1a74ce617f90584","cross_cats_sorted":["cs.CV","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2025-03-20T17:56:20Z","title_canon_sha256":"cd489a0d8fbf7f359ee971fa1d658113da2f051e1cb186a972050587877d642e"},"schema_version":"1.0","source":{"id":"2503.16406","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.16406","created_at":"2026-07-05T10:36:18Z"},{"alias_kind":"arxiv_version","alias_value":"2503.16406v1","created_at":"2026-07-05T10:36:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16406","created_at":"2026-07-05T10:36:18Z"},{"alias_kind":"pith_short_12","alias_value":"3OPTKOC2IMGX","created_at":"2026-07-05T10:36:18Z"},{"alias_kind":"pith_short_16","alias_value":"3OPTKOC2IMGX3UNR","created_at":"2026-07-05T10:36:18Z"},{"alias_kind":"pith_short_8","alias_value":"3OPTKOC2","created_at":"2026-07-05T10:36:18Z"}],"graph_snapshots":[{"event_id":"sha256:c4bd74a8598ebc38c2aed8b327cf4f9d35ed3a422dff5f9a6a88740521aaf631","target":"graph","created_at":"2026-07-05T10:36:18Z","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/2503.16406/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent large-scale text-to-image diffusion models generate photorealistic images but often struggle to accurately depict interactions between humans and objects due to their limited ability to differentiate various interaction words. In this work, we propose VerbDiff to address the challenge of capturing nuanced interactions within text-to-image diffusion models. VerbDiff is a novel text-to-image generation model that weakens the bias between interaction words and objects, enhancing the understanding of interactions. Specifically, we disentangle various interaction words from frequency-based a","authors_text":"Dong-Jin Kim, Hyunwoo Oh, Kwanyoung Lee, SeungJu Cha, Ye-Chan Kim","cross_cats":["cs.CV","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2025-03-20T17:56:20Z","title":"VerbDiff: Text-Only Diffusion Models with Enhanced Interaction Awareness"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16406","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":"sha256:48cfecc2f9013005a479027a807dcb6e221b82de2adaf9bbab7436085cba06f0","target":"record","created_at":"2026-07-05T10:36:18Z","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":"6c4a617ee58039f8dab3c23ebb8801eb568ab7c573a26f2cf1a74ce617f90584","cross_cats_sorted":["cs.CV","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2025-03-20T17:56:20Z","title_canon_sha256":"cd489a0d8fbf7f359ee971fa1d658113da2f051e1cb186a972050587877d642e"},"schema_version":"1.0","source":{"id":"2503.16406","kind":"arxiv","version":1}},"canonical_sha256":"db9f35385a430d7dd1b166ab299799e3ead1bfd5e204291be9007d00643429e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db9f35385a430d7dd1b166ab299799e3ead1bfd5e204291be9007d00643429e9","first_computed_at":"2026-07-05T10:36:18.771545Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:36:18.771545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"88LPRjBMnEBkDCrOktoqgQAO6XS/rekhJ6QofcK3Z9d40u4NRfsbjQWgodNyyCut1hKX6zlSOwwZwtdDm8KQAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:36:18.772358Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.16406","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48cfecc2f9013005a479027a807dcb6e221b82de2adaf9bbab7436085cba06f0","sha256:c4bd74a8598ebc38c2aed8b327cf4f9d35ed3a422dff5f9a6a88740521aaf631"],"state_sha256":"7931854572fdae47770d94d09a52390618f48c8dce6fe9be84e68f5067d35cb4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NJXmFMD43NfrUPkGxS1/QMOv7U9qTxbgoZTCN6COgpwei5WXfaXL+PBj4eeMcKsIRGBhXK/1UJAa7kqWaMZxCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T18:01:10.985457Z","bundle_sha256":"7d48626acf96a934d9ccb60cf1c3f4db3544ec7d15c9a2fa3fec0fe93c884d93"}}