{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:D6UF3BN6GP3ZOBNKYZEMNUOLFJ","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":"e4439f3438c55c726d9f141db1bf5b000d763d4a7b9b5da5704136927c83651c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-18T09:08:53Z","title_canon_sha256":"20ee7bd98ecfa6840f8d63543704eac117c2403b6a17122b1d5622f69b9aac72"},"schema_version":"1.0","source":{"id":"2509.14760","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.14760","created_at":"2026-06-04T01:08:32Z"},{"alias_kind":"arxiv_version","alias_value":"2509.14760v3","created_at":"2026-06-04T01:08:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.14760","created_at":"2026-06-04T01:08:32Z"},{"alias_kind":"pith_short_12","alias_value":"D6UF3BN6GP3Z","created_at":"2026-06-04T01:08:32Z"},{"alias_kind":"pith_short_16","alias_value":"D6UF3BN6GP3ZOBNK","created_at":"2026-06-04T01:08:32Z"},{"alias_kind":"pith_short_8","alias_value":"D6UF3BN6","created_at":"2026-06-04T01:08:32Z"}],"graph_snapshots":[{"event_id":"sha256:eb13171224d718da24435db72740d35ef82ce7a9d62572a6305a7c85b670036d","target":"graph","created_at":"2026-06-04T01:08:32Z","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/2509.14760/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly applied in diverse real-world scenarios, each governed by bespoke behavioral and safety specifications (spec) custom-tailored by users or organizations. These spec, categorized into safety-spec and behavioral-spec, vary across scenarios and evolve with changing preferences and requirements. We formalize this challenge as specification alignment, focusing on LLMs' ability to follow dynamic, scenario-specific spec from both behavioral and safety perspectives. To address this challenge, we propose Align3, a lightweight method that employs Test-Time De","authors_text":"Bo Li, Dongrui Liu, Haoran Zhang, Xuyang Hu, Yafu Li, Yu Cheng, Zhilin Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-18T09:08:53Z","title":"Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Deliberation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.14760","kind":"arxiv","version":3},"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":"sha256:6b0a8ab6bd3c187c490a6c6148e319d4f516bc9edb239ce34ed268f1dd677398","target":"record","created_at":"2026-06-04T01:08:32Z","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":"e4439f3438c55c726d9f141db1bf5b000d763d4a7b9b5da5704136927c83651c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-18T09:08:53Z","title_canon_sha256":"20ee7bd98ecfa6840f8d63543704eac117c2403b6a17122b1d5622f69b9aac72"},"schema_version":"1.0","source":{"id":"2509.14760","kind":"arxiv","version":3}},"canonical_sha256":"1fa85d85be33f79705aac648c6d1cb2a5e2c61987ad8ce54ec8fab90555bd4b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1fa85d85be33f79705aac648c6d1cb2a5e2c61987ad8ce54ec8fab90555bd4b9","first_computed_at":"2026-06-04T01:08:32.073488Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:08:32.073488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z7msNkRLyyjlfVt8XA5EmfQjFZJuPpl3OwB+g+o4CY1RVMkhCjgjHnIn17bnLstbZTBXMGAH9hHlay8/Eu7wCw==","signature_status":"signed_v1","signed_at":"2026-06-04T01:08:32.074188Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.14760","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b0a8ab6bd3c187c490a6c6148e319d4f516bc9edb239ce34ed268f1dd677398","sha256:eb13171224d718da24435db72740d35ef82ce7a9d62572a6305a7c85b670036d"],"state_sha256":"1aaa003ba8f309343395c18fabc423000a902fa93e0120f35c6a76617cd20da6"}