{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZNYM7FRJWCYNWKEMNCDZBZPAAT","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":"73bd601b37bf7891a79f52de1da082944770fbd28ce99e6d39a1b06f5ff4d90c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-08T18:24:12Z","title_canon_sha256":"23311a744ab24ea597857bdeb70d1c0825448ac8c57f5be07ac3bab25c6a288b"},"schema_version":"1.0","source":{"id":"2405.18438","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18438","created_at":"2026-07-05T08:24:25Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18438v1","created_at":"2026-07-05T08:24:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18438","created_at":"2026-07-05T08:24:25Z"},{"alias_kind":"pith_short_12","alias_value":"ZNYM7FRJWCYN","created_at":"2026-07-05T08:24:25Z"},{"alias_kind":"pith_short_16","alias_value":"ZNYM7FRJWCYNWKEM","created_at":"2026-07-05T08:24:25Z"},{"alias_kind":"pith_short_8","alias_value":"ZNYM7FRJ","created_at":"2026-07-05T08:24:25Z"}],"graph_snapshots":[{"event_id":"sha256:1f633738cd19a938acdcef39d038e74504bcbaee027319577db7e51ee50a61e0","target":"graph","created_at":"2026-07-05T08:24:25Z","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/2405.18438/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The connection between our 3D surroundings and the descriptive language that characterizes them would be well-suited for localizing and generating human motion in context but for one problem. The complexity introduced by multiple modalities makes capturing this connection challenging with a fixed set of descriptors. Specifically, closed vocabulary scene encoders, which require learning text-scene associations from scratch, have been favored in the literature, often resulting in inaccurate motion grounding. In this paper, we propose a method that integrates an open vocabulary scene encoder into","authors_text":"Fernando De la Torre, Koichiro Niinuma, L\\'aszl\\'o A. Jeni, Ryosuke Kawamura, Zolt\\'an \\'A. Milacski","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-08T18:24:12Z","title":"GHOST: Grounded Human Motion Generation with Open Vocabulary Scene-and-Text Contexts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18438","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:c38ce820016a310966d2674cf764d2112606affd038642f431ba6915caf46fe4","target":"record","created_at":"2026-07-05T08:24:25Z","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":"73bd601b37bf7891a79f52de1da082944770fbd28ce99e6d39a1b06f5ff4d90c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-08T18:24:12Z","title_canon_sha256":"23311a744ab24ea597857bdeb70d1c0825448ac8c57f5be07ac3bab25c6a288b"},"schema_version":"1.0","source":{"id":"2405.18438","kind":"arxiv","version":1}},"canonical_sha256":"cb70cf9629b0b0db288c688790e5e004f498c8580f2d6b6df0f7113ee8cbcb1a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb70cf9629b0b0db288c688790e5e004f498c8580f2d6b6df0f7113ee8cbcb1a","first_computed_at":"2026-07-05T08:24:25.712114Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:25.712114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zur44YpIm/bB2Jtp2QWdCW4mgBxgAsskVChqOx9Qj6lXyqGX2r3zRMGgSVrD0JuKP96wv8mlQ4gXZNa0bRqHBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:25.712618Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.18438","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c38ce820016a310966d2674cf764d2112606affd038642f431ba6915caf46fe4","sha256:1f633738cd19a938acdcef39d038e74504bcbaee027319577db7e51ee50a61e0"],"state_sha256":"643b017b2313946c7e04ef0854bb414b04ae95900bfef4b989788a63b7d2ce36"}