{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:P3ALIRHXTLXRN5TWFDK2ZGCLGN","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":"1f914a5454e1347ea4f509247bbb2f11a0725adbfa872988c96e585f61654ee4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-23T07:21:17Z","title_canon_sha256":"a89aa2be9455275dc03a90c64f645c0b32ee96bf049f7539c9d29c1d45b73bc7"},"schema_version":"1.0","source":{"id":"2412.17348","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.17348","created_at":"2026-07-05T09:53:21Z"},{"alias_kind":"arxiv_version","alias_value":"2412.17348v1","created_at":"2026-07-05T09:53:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17348","created_at":"2026-07-05T09:53:21Z"},{"alias_kind":"pith_short_12","alias_value":"P3ALIRHXTLXR","created_at":"2026-07-05T09:53:21Z"},{"alias_kind":"pith_short_16","alias_value":"P3ALIRHXTLXRN5TW","created_at":"2026-07-05T09:53:21Z"},{"alias_kind":"pith_short_8","alias_value":"P3ALIRHX","created_at":"2026-07-05T09:53:21Z"}],"graph_snapshots":[{"event_id":"sha256:a6575e47d5428845413fd41f10545a3c81282921e7bdca94366b8ec61d69ce7b","target":"graph","created_at":"2026-07-05T09:53:21Z","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/2412.17348/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the popularity and widespread use of semi-structured data formats such as JSON, end-to-end supervised learning applied directly to such data remains underexplored. We present ORIGAMI (Object RepresentatIon via Generative Autoregressive ModellIng), a transformer-based architecture that directly processes nested key/value pairs while preserving their hierarchical semantics. Our key technical contributions include: (1) a structure-preserving tokenizer, (2) a novel key/value position encoding scheme, and (3) a grammar-constrained training and inference framework that ensures valid outputs ","authors_text":"Alana Huang, Robin Vujanic, Thomas R\\\"uckstie\\ss","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17348","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":"sha256:4b78162c5c2e3cebeae94cea721b9f3eb454a3eeeef3f45f252672482936e332","target":"record","created_at":"2026-07-05T09:53:21Z","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":"1f914a5454e1347ea4f509247bbb2f11a0725adbfa872988c96e585f61654ee4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-23T07:21:17Z","title_canon_sha256":"a89aa2be9455275dc03a90c64f645c0b32ee96bf049f7539c9d29c1d45b73bc7"},"schema_version":"1.0","source":{"id":"2412.17348","kind":"arxiv","version":1}},"canonical_sha256":"7ec0b444f79aef16f67628d5ac984b336f2b8a72c839a3f306de1a0400454c6a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ec0b444f79aef16f67628d5ac984b336f2b8a72c839a3f306de1a0400454c6a","first_computed_at":"2026-07-05T09:53:21.256517Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:21.256517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e3w05tnPYw8iE0wo7HoCEBvJGlsOM9pXBaG3cOka9ZHmwQlwgOzQCBygAMBGNwfVq5hxEocOJrnwxl0NYgW6CA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:21.256963Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.17348","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b78162c5c2e3cebeae94cea721b9f3eb454a3eeeef3f45f252672482936e332","sha256:a6575e47d5428845413fd41f10545a3c81282921e7bdca94366b8ec61d69ce7b"],"state_sha256":"1777cb09559061fe4284812854685c35e66072b0b34bb6ce43969ffa037fabd3"}