{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SLUFEXM33XHPGRJ3ONK7P6USVX","short_pith_number":"pith:SLUFEXM3","schema_version":"1.0","canonical_sha256":"92e8525d9bddcef3453b7355f7fa92ade9a3ea72ea7ab26e4d338b1327672be8","source":{"kind":"arxiv","id":"2505.02236","version":1},"attestation_state":"computed","paper":{"title":"Improving Physical Object State Representation in Text-to-Image Generative Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chaitanya Chakka, Deepti Ghadiyaram, Tianle Chen","submitted_at":"2025-05-04T20:24:57Z","abstract_excerpt":"Current text-to-image generative models struggle to accurately represent object states (e.g., \"a table without a bottle,\" \"an empty tumbler\"). In this work, we first design a fully-automatic pipeline to generate high-quality synthetic data that accurately captures objects in varied states. Next, we fine-tune several open-source text-to-image models on this synthetic data. We evaluate the performance of the fine-tuned models by quantifying the alignment of the generated images to their prompts using GPT4o-mini, and achieve an average absolute improvement of 8+% across four models on the public "},"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":"2505.02236","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-04T20:24:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a96b3f729c93fc154bc33097b13dce18e55213d6a259e0ff323e9f8e0dd33825","abstract_canon_sha256":"076c06c4ae18f18835a49dd3e2e23ac83c75f891c9d95d4c8be7eff02149b977"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:34.218115Z","signature_b64":"3daB0SKXG9aQhHx125Z4PPJdiQ5XjYw3ElnYp7zvz6A8DxtjTeJNrQMKYDJ4wideiDCWjlzoyU4efffPxISwCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92e8525d9bddcef3453b7355f7fa92ade9a3ea72ea7ab26e4d338b1327672be8","last_reissued_at":"2026-07-05T10:58:34.217661Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:34.217661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Physical Object State Representation in Text-to-Image Generative Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chaitanya Chakka, Deepti Ghadiyaram, Tianle Chen","submitted_at":"2025-05-04T20:24:57Z","abstract_excerpt":"Current text-to-image generative models struggle to accurately represent object states (e.g., \"a table without a bottle,\" \"an empty tumbler\"). In this work, we first design a fully-automatic pipeline to generate high-quality synthetic data that accurately captures objects in varied states. Next, we fine-tune several open-source text-to-image models on this synthetic data. We evaluate the performance of the fine-tuned models by quantifying the alignment of the generated images to their prompts using GPT4o-mini, and achieve an average absolute improvement of 8+% across four models on the public "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02236","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/2505.02236/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":"2505.02236","created_at":"2026-07-05T10:58:34.217731+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.02236v1","created_at":"2026-07-05T10:58:34.217731+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02236","created_at":"2026-07-05T10:58:34.217731+00:00"},{"alias_kind":"pith_short_12","alias_value":"SLUFEXM33XHP","created_at":"2026-07-05T10:58:34.217731+00:00"},{"alias_kind":"pith_short_16","alias_value":"SLUFEXM33XHPGRJ3","created_at":"2026-07-05T10:58:34.217731+00:00"},{"alias_kind":"pith_short_8","alias_value":"SLUFEXM3","created_at":"2026-07-05T10:58:34.217731+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/SLUFEXM33XHPGRJ3ONK7P6USVX","json":"https://pith.science/pith/SLUFEXM33XHPGRJ3ONK7P6USVX.json","graph_json":"https://pith.science/api/pith-number/SLUFEXM33XHPGRJ3ONK7P6USVX/graph.json","events_json":"https://pith.science/api/pith-number/SLUFEXM33XHPGRJ3ONK7P6USVX/events.json","paper":"https://pith.science/paper/SLUFEXM3"},"agent_actions":{"view_html":"https://pith.science/pith/SLUFEXM33XHPGRJ3ONK7P6USVX","download_json":"https://pith.science/pith/SLUFEXM33XHPGRJ3ONK7P6USVX.json","view_paper":"https://pith.science/paper/SLUFEXM3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.02236&json=true","fetch_graph":"https://pith.science/api/pith-number/SLUFEXM33XHPGRJ3ONK7P6USVX/graph.json","fetch_events":"https://pith.science/api/pith-number/SLUFEXM33XHPGRJ3ONK7P6USVX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SLUFEXM33XHPGRJ3ONK7P6USVX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SLUFEXM33XHPGRJ3ONK7P6USVX/action/storage_attestation","attest_author":"https://pith.science/pith/SLUFEXM33XHPGRJ3ONK7P6USVX/action/author_attestation","sign_citation":"https://pith.science/pith/SLUFEXM33XHPGRJ3ONK7P6USVX/action/citation_signature","submit_replication":"https://pith.science/pith/SLUFEXM33XHPGRJ3ONK7P6USVX/action/replication_record"}},"created_at":"2026-07-05T10:58:34.217731+00:00","updated_at":"2026-07-05T10:58:34.217731+00:00"}