{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NPTHLOOUSO4Z4QTRDM3JUBSQNF","short_pith_number":"pith:NPTHLOOU","schema_version":"1.0","canonical_sha256":"6be675b9d493b99e42711b369a0650695ff5968087ee584bdbf61d7af290320f","source":{"kind":"arxiv","id":"2605.23178","version":1},"attestation_state":"computed","paper":{"title":"Composing People Together: Iterative Pose-Image Generation for Multi-Person Interaction Scenes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bharath Hariharan, Hadar Averbuch-Elor, Wenxuan Peng","submitted_at":"2026-05-22T02:56:34Z","abstract_excerpt":"Despite recent progress, text-to-image models still struggle to generate semantically diverse and compositionally accurate multi-person interaction scenes, often collapsing to repetitive layouts, stereotypical poses, and poorly grounded interactions. In this work, we bridge this gap by introducing a dual pose-image representation that brings person-centric structural priors into pretrained diffusion transformers. Our model jointly predicts a 2D pose visualization image and its corresponding RGB image, enabling structure and appearance to co-evolve during learning. At its core, a cross-modal al"},"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":"2605.23178","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-22T02:56:34Z","cross_cats_sorted":[],"title_canon_sha256":"fe4c15fb9324191e36bf21990f15510a2e021ae62c37a273f7f7b70b03f0f544","abstract_canon_sha256":"8a65c68b595db958437c555e72386768251622d0e2866aa5e67f305bda68ae75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:41.821491Z","signature_b64":"Gr5GwY0iy1q4UTYUcLxp7HnmJR8cgb/R/x5EdgWQ6fiRdRhu0umEk7W8Riv+xGXZYXycx6cjMsA9KrkNk2BKAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6be675b9d493b99e42711b369a0650695ff5968087ee584bdbf61d7af290320f","last_reissued_at":"2026-05-25T02:01:41.820625Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:41.820625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Composing People Together: Iterative Pose-Image Generation for Multi-Person Interaction Scenes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bharath Hariharan, Hadar Averbuch-Elor, Wenxuan Peng","submitted_at":"2026-05-22T02:56:34Z","abstract_excerpt":"Despite recent progress, text-to-image models still struggle to generate semantically diverse and compositionally accurate multi-person interaction scenes, often collapsing to repetitive layouts, stereotypical poses, and poorly grounded interactions. In this work, we bridge this gap by introducing a dual pose-image representation that brings person-centric structural priors into pretrained diffusion transformers. Our model jointly predicts a 2D pose visualization image and its corresponding RGB image, enabling structure and appearance to co-evolve during learning. At its core, a cross-modal al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23178","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/2605.23178/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":"2605.23178","created_at":"2026-05-25T02:01:41.820859+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.23178v1","created_at":"2026-05-25T02:01:41.820859+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23178","created_at":"2026-05-25T02:01:41.820859+00:00"},{"alias_kind":"pith_short_12","alias_value":"NPTHLOOUSO4Z","created_at":"2026-05-25T02:01:41.820859+00:00"},{"alias_kind":"pith_short_16","alias_value":"NPTHLOOUSO4Z4QTR","created_at":"2026-05-25T02:01:41.820859+00:00"},{"alias_kind":"pith_short_8","alias_value":"NPTHLOOU","created_at":"2026-05-25T02:01:41.820859+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/NPTHLOOUSO4Z4QTRDM3JUBSQNF","json":"https://pith.science/pith/NPTHLOOUSO4Z4QTRDM3JUBSQNF.json","graph_json":"https://pith.science/api/pith-number/NPTHLOOUSO4Z4QTRDM3JUBSQNF/graph.json","events_json":"https://pith.science/api/pith-number/NPTHLOOUSO4Z4QTRDM3JUBSQNF/events.json","paper":"https://pith.science/paper/NPTHLOOU"},"agent_actions":{"view_html":"https://pith.science/pith/NPTHLOOUSO4Z4QTRDM3JUBSQNF","download_json":"https://pith.science/pith/NPTHLOOUSO4Z4QTRDM3JUBSQNF.json","view_paper":"https://pith.science/paper/NPTHLOOU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.23178&json=true","fetch_graph":"https://pith.science/api/pith-number/NPTHLOOUSO4Z4QTRDM3JUBSQNF/graph.json","fetch_events":"https://pith.science/api/pith-number/NPTHLOOUSO4Z4QTRDM3JUBSQNF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NPTHLOOUSO4Z4QTRDM3JUBSQNF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NPTHLOOUSO4Z4QTRDM3JUBSQNF/action/storage_attestation","attest_author":"https://pith.science/pith/NPTHLOOUSO4Z4QTRDM3JUBSQNF/action/author_attestation","sign_citation":"https://pith.science/pith/NPTHLOOUSO4Z4QTRDM3JUBSQNF/action/citation_signature","submit_replication":"https://pith.science/pith/NPTHLOOUSO4Z4QTRDM3JUBSQNF/action/replication_record"}},"created_at":"2026-05-25T02:01:41.820859+00:00","updated_at":"2026-05-25T02:01:41.820859+00:00"}