{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:O4RKBOYVF63QVGAEAAV3YDQBTD","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":"7f5b275841cc6a3c3b3df198c585d7e095f6ebcd72120bcdd518d4d4462233f0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T14:33:29Z","title_canon_sha256":"418766be6bab8234a73597f942d7fc40a25cdc969a32ca0dcbfea26499d55641"},"schema_version":"1.0","source":{"id":"2505.14425","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14425","created_at":"2026-07-05T11:55:19Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14425v2","created_at":"2026-07-05T11:55:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14425","created_at":"2026-07-05T11:55:19Z"},{"alias_kind":"pith_short_12","alias_value":"O4RKBOYVF63Q","created_at":"2026-07-05T11:55:19Z"},{"alias_kind":"pith_short_16","alias_value":"O4RKBOYVF63QVGAE","created_at":"2026-07-05T11:55:19Z"},{"alias_kind":"pith_short_8","alias_value":"O4RKBOYV","created_at":"2026-07-05T11:55:19Z"}],"graph_snapshots":[{"event_id":"sha256:12c79ae5626d00029b7d2edb7c2469611298220cc60284941dfde3d80ff0e282","target":"graph","created_at":"2026-07-05T11:55:19Z","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/2505.14425/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction-tuned large language models (LLMs) have shown strong performance on a variety of tasks; however, generalizing from synthetic to human-authored instructions in grounded environments remains a challenge for them. In this work, we study generalization challenges in spatial grounding tasks where models interpret and translate instructions for building object arrangements on a $2.5$D grid. We fine-tune LLMs using only synthetic instructions and evaluate their performance on a benchmark dataset containing both synthetic and human-written instructions. Our results reveal that while models","authors_text":"Chalamalasetti Kranti, David Schlangen, Sherzod Hakimov","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T14:33:29Z","title":"From Templates to Natural Language: Generalization Challenges in Instruction-Tuned LLMs for Spatial Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14425","kind":"arxiv","version":2},"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:fe7c771dc54cf35b0b1dfadd9e57c393de5505f6ce8d063d1ed6bc3cc72aa5de","target":"record","created_at":"2026-07-05T11:55:19Z","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":"7f5b275841cc6a3c3b3df198c585d7e095f6ebcd72120bcdd518d4d4462233f0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T14:33:29Z","title_canon_sha256":"418766be6bab8234a73597f942d7fc40a25cdc969a32ca0dcbfea26499d55641"},"schema_version":"1.0","source":{"id":"2505.14425","kind":"arxiv","version":2}},"canonical_sha256":"7722a0bb152fb70a9804002bbc0e0198d9bf18694373eaedd5a3c3f5604a1e57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7722a0bb152fb70a9804002bbc0e0198d9bf18694373eaedd5a3c3f5604a1e57","first_computed_at":"2026-07-05T11:55:19.496554Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:55:19.496554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0sT2CeJ95giih7eAjVfEmxqjfFjNenXFXZgGifjuW1zo285sT8ZNwtfLtDGcIEZVij3pw/LdNABA9/pcZ6idBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:55:19.497014Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.14425","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe7c771dc54cf35b0b1dfadd9e57c393de5505f6ce8d063d1ed6bc3cc72aa5de","sha256:12c79ae5626d00029b7d2edb7c2469611298220cc60284941dfde3d80ff0e282"],"state_sha256":"1e460baf2349d83f3f15fb31fc14a04d6858a57fdab67d0026f5a54ea8dc1d40"}