{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YV7ETYNBGSTHVB2U2WGDSHHZE3","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":"edc757ef3a667986330addec34c303a35d80aa7bac5a3e60cfa7327995f4a10f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T05:03:23Z","title_canon_sha256":"216944797c95e3ef7aef3494f45a7649dab8fe30960912180cb171f8114c0002"},"schema_version":"1.0","source":{"id":"2406.12274","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12274","created_at":"2026-07-05T09:49:06Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12274v2","created_at":"2026-07-05T09:49:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12274","created_at":"2026-07-05T09:49:06Z"},{"alias_kind":"pith_short_12","alias_value":"YV7ETYNBGSTH","created_at":"2026-07-05T09:49:06Z"},{"alias_kind":"pith_short_16","alias_value":"YV7ETYNBGSTHVB2U","created_at":"2026-07-05T09:49:06Z"},{"alias_kind":"pith_short_8","alias_value":"YV7ETYNB","created_at":"2026-07-05T09:49:06Z"}],"graph_snapshots":[{"event_id":"sha256:12bb10b190316431f7a6ed6f90dc1b0d17247d690e250f025cfd2a6a55f54552","target":"graph","created_at":"2026-07-05T09:49:06Z","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/2406.12274/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safety-aligned language models often exhibit fragile and imbalanced safety mechanisms, increasing the likelihood of generating unsafe content. In addition, incorporating new knowledge through editing techniques to language models can further compromise safety. To address these issues, we propose SafeInfer, a context-adaptive, decoding-time safety alignment strategy for generating safe responses to user queries. SafeInfer comprises two phases: the safety amplification phase, which employs safe demonstration examples to adjust the model's hidden states and increase the likelihood of safer output","authors_text":"Animesh Mukherjee, Rima Hazra, Sayan Layek, Shanu Kumar, Soham Tripathy, Somnath Banerjee","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T05:03:23Z","title":"SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12274","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:d859c168c59c32fc4f4fade8d0363722a8dd72e6d492a7087fc76af2d60d6e2e","target":"record","created_at":"2026-07-05T09:49:06Z","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":"edc757ef3a667986330addec34c303a35d80aa7bac5a3e60cfa7327995f4a10f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T05:03:23Z","title_canon_sha256":"216944797c95e3ef7aef3494f45a7649dab8fe30960912180cb171f8114c0002"},"schema_version":"1.0","source":{"id":"2406.12274","kind":"arxiv","version":2}},"canonical_sha256":"c57e49e1a134a67a8754d58c391cf926c80153b7caaf51bbd16f3858a0454f67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c57e49e1a134a67a8754d58c391cf926c80153b7caaf51bbd16f3858a0454f67","first_computed_at":"2026-07-05T09:49:06.823324Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:06.823324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Un0Nq4NSWA3+Zsad/Y7iNY+f8pvBQUwTCO6BDlAayGbsDAP/n6eAvMnL78yjQVJXMhZFyDzKoFPNIjzJLU/iBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:06.823808Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.12274","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d859c168c59c32fc4f4fade8d0363722a8dd72e6d492a7087fc76af2d60d6e2e","sha256:12bb10b190316431f7a6ed6f90dc1b0d17247d690e250f025cfd2a6a55f54552"],"state_sha256":"78f44c997de0fd2f506144594afbc83f0f4e4b03deb900ea168fb8272fe91bd6"}