{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:O4RKBOYVF63QVGAEAAV3YDQBTD","short_pith_number":"pith:O4RKBOYV","canonical_record":{"source":{"id":"2505.14425","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T14:33:29Z","cross_cats_sorted":[],"title_canon_sha256":"418766be6bab8234a73597f942d7fc40a25cdc969a32ca0dcbfea26499d55641","abstract_canon_sha256":"7f5b275841cc6a3c3b3df198c585d7e095f6ebcd72120bcdd518d4d4462233f0"},"schema_version":"1.0"},"canonical_sha256":"7722a0bb152fb70a9804002bbc0e0198d9bf18694373eaedd5a3c3f5604a1e57","source":{"kind":"arxiv","id":"2505.14425","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:O4RKBOYVF63QVGAEAAV3YDQBTD","target":"record","payload":{"canonical_record":{"source":{"id":"2505.14425","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T14:33:29Z","cross_cats_sorted":[],"title_canon_sha256":"418766be6bab8234a73597f942d7fc40a25cdc969a32ca0dcbfea26499d55641","abstract_canon_sha256":"7f5b275841cc6a3c3b3df198c585d7e095f6ebcd72120bcdd518d4d4462233f0"},"schema_version":"1.0"},"canonical_sha256":"7722a0bb152fb70a9804002bbc0e0198d9bf18694373eaedd5a3c3f5604a1e57","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:19.497014Z","signature_b64":"0sT2CeJ95giih7eAjVfEmxqjfFjNenXFXZgGifjuW1zo285sT8ZNwtfLtDGcIEZVij3pw/LdNABA9/pcZ6idBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7722a0bb152fb70a9804002bbc0e0198d9bf18694373eaedd5a3c3f5604a1e57","last_reissued_at":"2026-07-05T11:55:19.496554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:19.496554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.14425","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:55:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hFDfwKitHOGwR77ZzawBzGCNpRH1zYCF0JSEbFXHe9SFffhHqCNqIDwYk+WrPtqspmrcmIDEeJ2Rb9+yhQMqAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:52:32.433831Z"},"content_sha256":"fe7c771dc54cf35b0b1dfadd9e57c393de5505f6ce8d063d1ed6bc3cc72aa5de","schema_version":"1.0","event_id":"sha256:fe7c771dc54cf35b0b1dfadd9e57c393de5505f6ce8d063d1ed6bc3cc72aa5de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:O4RKBOYVF63QVGAEAAV3YDQBTD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Templates to Natural Language: Generalization Challenges in Instruction-Tuned LLMs for Spatial Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chalamalasetti Kranti, David Schlangen, Sherzod Hakimov","submitted_at":"2025-05-20T14:33:29Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14425","kind":"arxiv","version":2},"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/2505.14425/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:55:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qIW9mBB9d0Lgsbrai4Es1ES5ywSPFxA/9u8BdGamd6ErwchgTWKpFH7hXkWEvesNh7PuhVimWBIVYRi83VDPBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:52:32.434676Z"},"content_sha256":"12c79ae5626d00029b7d2edb7c2469611298220cc60284941dfde3d80ff0e282","schema_version":"1.0","event_id":"sha256:12c79ae5626d00029b7d2edb7c2469611298220cc60284941dfde3d80ff0e282"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O4RKBOYVF63QVGAEAAV3YDQBTD/bundle.json","state_url":"https://pith.science/pith/O4RKBOYVF63QVGAEAAV3YDQBTD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O4RKBOYVF63QVGAEAAV3YDQBTD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T05:52:32Z","links":{"resolver":"https://pith.science/pith/O4RKBOYVF63QVGAEAAV3YDQBTD","bundle":"https://pith.science/pith/O4RKBOYVF63QVGAEAAV3YDQBTD/bundle.json","state":"https://pith.science/pith/O4RKBOYVF63QVGAEAAV3YDQBTD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O4RKBOYVF63QVGAEAAV3YDQBTD/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xehkTo/i/nrP6lYa7cDmlo5fIzDG8WJ7gMP3br7HiTrNWaUuxlHb6rFjUfM0Nw7V8yKPQuCxP9cF2xZqXlN1CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T05:52:32.441913Z","bundle_sha256":"637fa37cb371e6140a634a19a9948afad90d08666980b97a7c3908e145bf1277"}}