{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XBQQK7XJ7UBAI3P36LGAGH2FQR","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":"0293a51437a170990ad98bdf777ac73bd7127f54b633d5940bced1e364b0bd45","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-09-05T11:42:03Z","title_canon_sha256":"41d4a5af33bb69fd78b6bd85f0fb18ee44c584430e9485a5979b56fd6aca53a7"},"schema_version":"1.0","source":{"id":"2509.05031","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.05031","created_at":"2026-07-05T12:05:34Z"},{"alias_kind":"arxiv_version","alias_value":"2509.05031v1","created_at":"2026-07-05T12:05:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05031","created_at":"2026-07-05T12:05:34Z"},{"alias_kind":"pith_short_12","alias_value":"XBQQK7XJ7UBA","created_at":"2026-07-05T12:05:34Z"},{"alias_kind":"pith_short_16","alias_value":"XBQQK7XJ7UBAI3P3","created_at":"2026-07-05T12:05:34Z"},{"alias_kind":"pith_short_8","alias_value":"XBQQK7XJ","created_at":"2026-07-05T12:05:34Z"}],"graph_snapshots":[{"event_id":"sha256:cf75b9c9e1d45a4a7d5d0412ae7c0a93337e3815d4019676e8842f621c164f97","target":"graph","created_at":"2026-07-05T12:05:34Z","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/2509.05031/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deictic gestures, like pointing, are a fundamental form of non-verbal communication, enabling humans to direct attention to specific objects or locations. This capability is essential in Human-Robot Interaction (HRI), where robots should be able to predict human intent and anticipate appropriate responses. In this work, we propose the Multi-Modality Inter-TransFormer (MM-ITF), a modular architecture to predict objects in a controlled tabletop scenario with the NICOL robot, where humans indicate targets through natural pointing gestures. Leveraging inter-modality attention, MM-ITF maps 2D point","authors_text":"Hassan Ali, Luca M\\\"uller, Luk\\'a\\v{s} Gajdo\\v{s}ech, Philipp Allgeuer, Stefan Wermter","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-09-05T11:42:03Z","title":"Pointing-Guided Target Estimation via Transformer-Based Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05031","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:cc1e6e2d338d300e25c7dbe83517f8f8c00cda4a994f0c52499a3c62fceaddc7","target":"record","created_at":"2026-07-05T12:05:34Z","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":"0293a51437a170990ad98bdf777ac73bd7127f54b633d5940bced1e364b0bd45","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-09-05T11:42:03Z","title_canon_sha256":"41d4a5af33bb69fd78b6bd85f0fb18ee44c584430e9485a5979b56fd6aca53a7"},"schema_version":"1.0","source":{"id":"2509.05031","kind":"arxiv","version":1}},"canonical_sha256":"b861057ee9fd02046dfbf2cc031f458458a675035cf2b8512fce4f2ba82b0a7c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b861057ee9fd02046dfbf2cc031f458458a675035cf2b8512fce4f2ba82b0a7c","first_computed_at":"2026-07-05T12:05:34.783808Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:05:34.783808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4TaGRmnb/1PnD921oKPJgWG84eu1+uszwxuV324pOBdHaoXl8gFe698ATn+jdPXVu3T25r6iaGqkQVTnUqKPCg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:05:34.784281Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.05031","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc1e6e2d338d300e25c7dbe83517f8f8c00cda4a994f0c52499a3c62fceaddc7","sha256:cf75b9c9e1d45a4a7d5d0412ae7c0a93337e3815d4019676e8842f621c164f97"],"state_sha256":"f2923ea63fb90113ccb046eadba8f9dabbbaeab82d89613ed05baee7f50477fc"}