{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Z4POVTN35ABSMBNE7WCR3ERWFE","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":"21b9574b0f3d27e6aec76ee429c53fe4e37777c1311bd0584fe9fa26b954e6f4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-01T07:08:45Z","title_canon_sha256":"de9c331a5b7205b79749dff65258d9df1c683df5ed2b8dd8c11956e61b369fca"},"schema_version":"1.0","source":{"id":"2509.01185","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.01185","created_at":"2026-07-05T12:05:04Z"},{"alias_kind":"arxiv_version","alias_value":"2509.01185v2","created_at":"2026-07-05T12:05:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01185","created_at":"2026-07-05T12:05:04Z"},{"alias_kind":"pith_short_12","alias_value":"Z4POVTN35ABS","created_at":"2026-07-05T12:05:04Z"},{"alias_kind":"pith_short_16","alias_value":"Z4POVTN35ABSMBNE","created_at":"2026-07-05T12:05:04Z"},{"alias_kind":"pith_short_8","alias_value":"Z4POVTN3","created_at":"2026-07-05T12:05:04Z"}],"graph_snapshots":[{"event_id":"sha256:c06003c2b9e2fe5a27d170ca3168fb85684b4e4e8d75fea69b7206e055effa80","target":"graph","created_at":"2026-07-05T12:05:04Z","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/2509.01185/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ability of large language models (LLMs) to process and reason over long textual inputs is critical for a wide range of real-world applications. However, progress in this area is significantly constrained by the absence of high-quality, diverse, and verifiable long-context datasets suitable for both training and evaluation. This work introduces a modular, extensible framework for synthetic long-context data generation via prompt-based interaction with LLMs. The framework supports multiple training and alignment objectives, including Supervised Fine-Tuning (SFT), Direct Preference Optimizati","authors_text":"Abhigya Verma, Seganrasan Subramanian","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-01T07:08:45Z","title":"Modular Techniques for Synthetic Long-Context Data Generation in Language Model Training and Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01185","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:c29821b73fc78aea75a50a5d5c688f06458405272ffe81b1ded7ee5c9f197850","target":"record","created_at":"2026-07-05T12:05:04Z","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":"21b9574b0f3d27e6aec76ee429c53fe4e37777c1311bd0584fe9fa26b954e6f4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-01T07:08:45Z","title_canon_sha256":"de9c331a5b7205b79749dff65258d9df1c683df5ed2b8dd8c11956e61b369fca"},"schema_version":"1.0","source":{"id":"2509.01185","kind":"arxiv","version":2}},"canonical_sha256":"cf1eeacdbbe8032605a4fd851d92362923a04073bb61b6afe4476bbda8b41beb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf1eeacdbbe8032605a4fd851d92362923a04073bb61b6afe4476bbda8b41beb","first_computed_at":"2026-07-05T12:05:04.201860Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:05:04.201860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h0YCxmZWqsokuj0DF86SVO35shT+38HVow5Iey3ZyC1JZ8QtuCChOhi3e+f2Z0b58VissmB9lFZVrRAaZ9i8AA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:05:04.202524Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.01185","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c29821b73fc78aea75a50a5d5c688f06458405272ffe81b1ded7ee5c9f197850","sha256:c06003c2b9e2fe5a27d170ca3168fb85684b4e4e8d75fea69b7206e055effa80"],"state_sha256":"3eb9452d2059c0f0220ff306e564ac84ebfea31daf93a23999cc8729c4035aeb"}