{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SHLB3LTLNMNW3EAB4AP7RTEAW7","short_pith_number":"pith:SHLB3LTL","canonical_record":{"source":{"id":"2506.00676","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-31T19:00:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b0cb8bc4fde8de583e2435fde863d7a2e3f76ed73e32b423723784655d182758","abstract_canon_sha256":"3f520ef0325e3ba60921656a7a07080d3f7458b20142315b283cdffd9960798b"},"schema_version":"1.0"},"canonical_sha256":"91d61dae6b6b1b6d9001e01ff8cc80b7f907566721a0946753c771300b96fe17","source":{"kind":"arxiv","id":"2506.00676","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00676","created_at":"2026-07-05T11:13:38Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00676v1","created_at":"2026-07-05T11:13:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00676","created_at":"2026-07-05T11:13:38Z"},{"alias_kind":"pith_short_12","alias_value":"SHLB3LTLNMNW","created_at":"2026-07-05T11:13:38Z"},{"alias_kind":"pith_short_16","alias_value":"SHLB3LTLNMNW3EAB","created_at":"2026-07-05T11:13:38Z"},{"alias_kind":"pith_short_8","alias_value":"SHLB3LTL","created_at":"2026-07-05T11:13:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SHLB3LTLNMNW3EAB4AP7RTEAW7","target":"record","payload":{"canonical_record":{"source":{"id":"2506.00676","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-31T19:00:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b0cb8bc4fde8de583e2435fde863d7a2e3f76ed73e32b423723784655d182758","abstract_canon_sha256":"3f520ef0325e3ba60921656a7a07080d3f7458b20142315b283cdffd9960798b"},"schema_version":"1.0"},"canonical_sha256":"91d61dae6b6b1b6d9001e01ff8cc80b7f907566721a0946753c771300b96fe17","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:38.671723Z","signature_b64":"HyRE28Gr13sgLKlK38UXPKBAeSMdst6Yo6Xg6KHSDBv/hkE4DMOFL/h3UggJHY9cfxUJIrafEEMuZNHt+Bf5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91d61dae6b6b1b6d9001e01ff8cc80b7f907566721a0946753c771300b96fe17","last_reissued_at":"2026-07-05T11:13:38.671220Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:38.671220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.00676","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:13:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WqzyN4AX4inBqO8qgMNe1htrDDL+uKxaLEypWm9oBxVdOQTsAwAg+JuIajwy+ObC70Eb5i7n+ogIwlaoBISPCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:38:35.673116Z"},"content_sha256":"7b6fb4beeb66df9cf2293555668634a29c0db42f90cfc282392b1eade67fdf40","schema_version":"1.0","event_id":"sha256:7b6fb4beeb66df9cf2293555668634a29c0db42f90cfc282392b1eade67fdf40"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SHLB3LTLNMNW3EAB4AP7RTEAW7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SafeTuneBed: A Toolkit for Benchmarking LLM Safety Alignment in Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Saad Hossain, Samanvay Vajpayee, Sirisha Rambhatla","submitted_at":"2025-05-31T19:00:58Z","abstract_excerpt":"As large language models (LLMs) become ubiquitous, parameter-efficient fine-tuning methods and safety-first defenses have proliferated rapidly. However, the number of approaches and their recent increase have resulted in diverse evaluations-varied datasets, metrics, and inconsistent threat settings-making it difficult to fairly compare safety, utility, and robustness across methods. To address this, we introduce SafeTuneBed, a benchmark and toolkit unifying fine-tuning and defense evaluation. SafeTuneBed (i) curates a diverse repository of multiple fine-tuning datasets spanning sentiment analy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00676","kind":"arxiv","version":1},"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/2506.00676/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":"2026-07-05T11:13:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I1IYrZG5HhZ8PIeCeuhPR4I5TsfbOXIkKyrSOwdCUzdmEMi53sQ9bgAfJd6TFoau+um/hngA8yFxbS9Z9qbnAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:38:35.674065Z"},"content_sha256":"13eef711f10c56e6074a610fa03ed57328fbf01fd83d43c3f50c880f275d215c","schema_version":"1.0","event_id":"sha256:13eef711f10c56e6074a610fa03ed57328fbf01fd83d43c3f50c880f275d215c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SHLB3LTLNMNW3EAB4AP7RTEAW7/bundle.json","state_url":"https://pith.science/pith/SHLB3LTLNMNW3EAB4AP7RTEAW7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SHLB3LTLNMNW3EAB4AP7RTEAW7/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":"2026-08-08T09:38:35Z","links":{"resolver":"https://pith.science/pith/SHLB3LTLNMNW3EAB4AP7RTEAW7","bundle":"https://pith.science/pith/SHLB3LTLNMNW3EAB4AP7RTEAW7/bundle.json","state":"https://pith.science/pith/SHLB3LTLNMNW3EAB4AP7RTEAW7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SHLB3LTLNMNW3EAB4AP7RTEAW7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SHLB3LTLNMNW3EAB4AP7RTEAW7","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":"3f520ef0325e3ba60921656a7a07080d3f7458b20142315b283cdffd9960798b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-31T19:00:58Z","title_canon_sha256":"b0cb8bc4fde8de583e2435fde863d7a2e3f76ed73e32b423723784655d182758"},"schema_version":"1.0","source":{"id":"2506.00676","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00676","created_at":"2026-07-05T11:13:38Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00676v1","created_at":"2026-07-05T11:13:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00676","created_at":"2026-07-05T11:13:38Z"},{"alias_kind":"pith_short_12","alias_value":"SHLB3LTLNMNW","created_at":"2026-07-05T11:13:38Z"},{"alias_kind":"pith_short_16","alias_value":"SHLB3LTLNMNW3EAB","created_at":"2026-07-05T11:13:38Z"},{"alias_kind":"pith_short_8","alias_value":"SHLB3LTL","created_at":"2026-07-05T11:13:38Z"}],"graph_snapshots":[{"event_id":"sha256:13eef711f10c56e6074a610fa03ed57328fbf01fd83d43c3f50c880f275d215c","target":"graph","created_at":"2026-07-05T11:13:38Z","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/2506.00676/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models (LLMs) become ubiquitous, parameter-efficient fine-tuning methods and safety-first defenses have proliferated rapidly. However, the number of approaches and their recent increase have resulted in diverse evaluations-varied datasets, metrics, and inconsistent threat settings-making it difficult to fairly compare safety, utility, and robustness across methods. To address this, we introduce SafeTuneBed, a benchmark and toolkit unifying fine-tuning and defense evaluation. SafeTuneBed (i) curates a diverse repository of multiple fine-tuning datasets spanning sentiment analy","authors_text":"Saad Hossain, Samanvay Vajpayee, Sirisha Rambhatla","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-31T19:00:58Z","title":"SafeTuneBed: A Toolkit for Benchmarking LLM Safety Alignment in Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00676","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":"sha256:7b6fb4beeb66df9cf2293555668634a29c0db42f90cfc282392b1eade67fdf40","target":"record","created_at":"2026-07-05T11:13:38Z","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":"3f520ef0325e3ba60921656a7a07080d3f7458b20142315b283cdffd9960798b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-31T19:00:58Z","title_canon_sha256":"b0cb8bc4fde8de583e2435fde863d7a2e3f76ed73e32b423723784655d182758"},"schema_version":"1.0","source":{"id":"2506.00676","kind":"arxiv","version":1}},"canonical_sha256":"91d61dae6b6b1b6d9001e01ff8cc80b7f907566721a0946753c771300b96fe17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91d61dae6b6b1b6d9001e01ff8cc80b7f907566721a0946753c771300b96fe17","first_computed_at":"2026-07-05T11:13:38.671220Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:38.671220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HyRE28Gr13sgLKlK38UXPKBAeSMdst6Yo6Xg6KHSDBv/hkE4DMOFL/h3UggJHY9cfxUJIrafEEMuZNHt+Bf5Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:38.671723Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00676","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7b6fb4beeb66df9cf2293555668634a29c0db42f90cfc282392b1eade67fdf40","sha256:13eef711f10c56e6074a610fa03ed57328fbf01fd83d43c3f50c880f275d215c"],"state_sha256":"cf370d4085af2a0dd73ace5ff1341dd91de7ab8af8c32139367eb143f49a4bb4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t7FaQ1rOUJ8YQDBUY561+4RJsg+STWQCK+Gi6NxHcH+6wjYRFPkRKd2ZpS7SqbtKqCKaLe+5GloJrsPYr5xCAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:38:35.680272Z","bundle_sha256":"31fc3cf0b765578c052fa5827acdf1bc5ca2c180e8c02db9bcb40a35dc76523f"}}