{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NPTHLOOUSO4Z4QTRDM3JUBSQNF","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":"8a65c68b595db958437c555e72386768251622d0e2866aa5e67f305bda68ae75","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-22T02:56:34Z","title_canon_sha256":"fe4c15fb9324191e36bf21990f15510a2e021ae62c37a273f7f7b70b03f0f544"},"schema_version":"1.0","source":{"id":"2605.23178","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23178","created_at":"2026-05-25T02:01:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23178v1","created_at":"2026-05-25T02:01:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23178","created_at":"2026-05-25T02:01:41Z"},{"alias_kind":"pith_short_12","alias_value":"NPTHLOOUSO4Z","created_at":"2026-05-25T02:01:41Z"},{"alias_kind":"pith_short_16","alias_value":"NPTHLOOUSO4Z4QTR","created_at":"2026-05-25T02:01:41Z"},{"alias_kind":"pith_short_8","alias_value":"NPTHLOOU","created_at":"2026-05-25T02:01:41Z"}],"graph_snapshots":[{"event_id":"sha256:bf266ff09b06f77d9789909ee24ca6b47499c2049035bde79410b2d098d5fcbb","target":"graph","created_at":"2026-05-25T02:01:41Z","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/2605.23178/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bharath Hariharan, Hadar Averbuch-Elor, Wenxuan Peng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-22T02:56:34Z","title":"Composing People Together: Iterative Pose-Image Generation for Multi-Person Interaction Scenes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23178","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":"sha256:111bf2a43520787b32431928546c0185720728d6b03e4b69dfc4327e36dba348","target":"record","created_at":"2026-05-25T02:01:41Z","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":"8a65c68b595db958437c555e72386768251622d0e2866aa5e67f305bda68ae75","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-22T02:56:34Z","title_canon_sha256":"fe4c15fb9324191e36bf21990f15510a2e021ae62c37a273f7f7b70b03f0f544"},"schema_version":"1.0","source":{"id":"2605.23178","kind":"arxiv","version":1}},"canonical_sha256":"6be675b9d493b99e42711b369a0650695ff5968087ee584bdbf61d7af290320f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6be675b9d493b99e42711b369a0650695ff5968087ee584bdbf61d7af290320f","first_computed_at":"2026-05-25T02:01:41.820625Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:41.820625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gr5GwY0iy1q4UTYUcLxp7HnmJR8cgb/R/x5EdgWQ6fiRdRhu0umEk7W8Riv+xGXZYXycx6cjMsA9KrkNk2BKAw==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:41.821491Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.23178","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:111bf2a43520787b32431928546c0185720728d6b03e4b69dfc4327e36dba348","sha256:bf266ff09b06f77d9789909ee24ca6b47499c2049035bde79410b2d098d5fcbb"],"state_sha256":"03fe0e163cf82b10dd23ffbfd6dc43914951a7eec671581ab1e7483020d3cb6e"}