{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:53BCA2RTGQ6NLFKX4ME2IBJ4KY","short_pith_number":"pith:53BCA2RT","canonical_record":{"source":{"id":"2605.20915","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T08:59:23Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"139ff59f8ffa93322999fe7489b43ec9052d21e696d66fa28f7d73a74f6fb59c","abstract_canon_sha256":"29bd7cce8a304cf78f81934b24f81070ff3500e01c2f24078f347d410ddb2ffc"},"schema_version":"1.0"},"canonical_sha256":"eec2206a33343cd59557e309a4053c562f6a54bd526d8c7f7ae95fda0f17cff4","source":{"kind":"arxiv","id":"2605.20915","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20915","created_at":"2026-05-21T01:05:27Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20915v1","created_at":"2026-05-21T01:05:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20915","created_at":"2026-05-21T01:05:27Z"},{"alias_kind":"pith_short_12","alias_value":"53BCA2RTGQ6N","created_at":"2026-05-21T01:05:27Z"},{"alias_kind":"pith_short_16","alias_value":"53BCA2RTGQ6NLFKX","created_at":"2026-05-21T01:05:27Z"},{"alias_kind":"pith_short_8","alias_value":"53BCA2RT","created_at":"2026-05-21T01:05:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:53BCA2RTGQ6NLFKX4ME2IBJ4KY","target":"record","payload":{"canonical_record":{"source":{"id":"2605.20915","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T08:59:23Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"139ff59f8ffa93322999fe7489b43ec9052d21e696d66fa28f7d73a74f6fb59c","abstract_canon_sha256":"29bd7cce8a304cf78f81934b24f81070ff3500e01c2f24078f347d410ddb2ffc"},"schema_version":"1.0"},"canonical_sha256":"eec2206a33343cd59557e309a4053c562f6a54bd526d8c7f7ae95fda0f17cff4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:27.788411Z","signature_b64":"7pqUWPgWuopE1zSwHbG4vVlJipVIsfhzZufAvqirx25N2uv8Q8ZrCQjzXMQ3GY2up7cAtIUzSKBQ2cZ5q6gwBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eec2206a33343cd59557e309a4053c562f6a54bd526d8c7f7ae95fda0f17cff4","last_reissued_at":"2026-05-21T01:05:27.787786Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:27.787786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.20915","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":"2026-05-21T01:05:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WO2SX/51CyFy6REb8u+70pdAzzarflPtUnVBeY0BohzI/P+SvOb4ND8Gf4F26sFU2H6180DUiUW4XRFl6rLiDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T01:58:04.594542Z"},"content_sha256":"ad24a237ded493a9f18e977938353f0d120ee6d5a287ca6048bb5214460bcbb9","schema_version":"1.0","event_id":"sha256:ad24a237ded493a9f18e977938353f0d120ee6d5a287ca6048bb5214460bcbb9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:53BCA2RTGQ6NLFKX4ME2IBJ4KY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Calibration vs Decision Making: Revisiting the Reliability Paradox in Unlearned Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ashutosh Modi, Divyaksh Shukla","submitted_at":"2026-05-20T08:59:23Z","abstract_excerpt":"Machine unlearning aims to remove the influence of specific training data from a model while preserving reliable behavior on the remaining data, making reliable prediction and uncertainty estimation essential for evaluation. Calibration is commonly used as a proxy for reliability in language models, but low calibration error does not necessarily imply reliable decision rules, as models may rely on spurious correlations while remaining well calibrated. We investigate this gap in generative language models using the multiple-choice question-answering evaluation protocol on the TOFU benchmark, me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20915","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/2605.20915/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":"2026-05-21T01:05:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jpVfSsP3f1MrThNbfXFOjUZ9f4gPt20oN03Kprb/uddlmDdAtcjnbhHRLEul57pSvWyhnhBpx2tbnYWOp+LmDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T01:58:04.594947Z"},"content_sha256":"7e4401c109a8c0523188580f0d8033dac67f8826592ae6c4407a5eba95b01255","schema_version":"1.0","event_id":"sha256:7e4401c109a8c0523188580f0d8033dac67f8826592ae6c4407a5eba95b01255"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/53BCA2RTGQ6NLFKX4ME2IBJ4KY/bundle.json","state_url":"https://pith.science/pith/53BCA2RTGQ6NLFKX4ME2IBJ4KY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/53BCA2RTGQ6NLFKX4ME2IBJ4KY/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":"2026-05-23T01:58:04Z","links":{"resolver":"https://pith.science/pith/53BCA2RTGQ6NLFKX4ME2IBJ4KY","bundle":"https://pith.science/pith/53BCA2RTGQ6NLFKX4ME2IBJ4KY/bundle.json","state":"https://pith.science/pith/53BCA2RTGQ6NLFKX4ME2IBJ4KY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/53BCA2RTGQ6NLFKX4ME2IBJ4KY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:53BCA2RTGQ6NLFKX4ME2IBJ4KY","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":"29bd7cce8a304cf78f81934b24f81070ff3500e01c2f24078f347d410ddb2ffc","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T08:59:23Z","title_canon_sha256":"139ff59f8ffa93322999fe7489b43ec9052d21e696d66fa28f7d73a74f6fb59c"},"schema_version":"1.0","source":{"id":"2605.20915","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20915","created_at":"2026-05-21T01:05:27Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20915v1","created_at":"2026-05-21T01:05:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20915","created_at":"2026-05-21T01:05:27Z"},{"alias_kind":"pith_short_12","alias_value":"53BCA2RTGQ6N","created_at":"2026-05-21T01:05:27Z"},{"alias_kind":"pith_short_16","alias_value":"53BCA2RTGQ6NLFKX","created_at":"2026-05-21T01:05:27Z"},{"alias_kind":"pith_short_8","alias_value":"53BCA2RT","created_at":"2026-05-21T01:05:27Z"}],"graph_snapshots":[{"event_id":"sha256:7e4401c109a8c0523188580f0d8033dac67f8826592ae6c4407a5eba95b01255","target":"graph","created_at":"2026-05-21T01:05:27Z","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/2605.20915/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine unlearning aims to remove the influence of specific training data from a model while preserving reliable behavior on the remaining data, making reliable prediction and uncertainty estimation essential for evaluation. Calibration is commonly used as a proxy for reliability in language models, but low calibration error does not necessarily imply reliable decision rules, as models may rely on spurious correlations while remaining well calibrated. We investigate this gap in generative language models using the multiple-choice question-answering evaluation protocol on the TOFU benchmark, me","authors_text":"Ashutosh Modi, Divyaksh Shukla","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T08:59:23Z","title":"Calibration vs Decision Making: Revisiting the Reliability Paradox in Unlearned Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20915","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:ad24a237ded493a9f18e977938353f0d120ee6d5a287ca6048bb5214460bcbb9","target":"record","created_at":"2026-05-21T01:05:27Z","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":"29bd7cce8a304cf78f81934b24f81070ff3500e01c2f24078f347d410ddb2ffc","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T08:59:23Z","title_canon_sha256":"139ff59f8ffa93322999fe7489b43ec9052d21e696d66fa28f7d73a74f6fb59c"},"schema_version":"1.0","source":{"id":"2605.20915","kind":"arxiv","version":1}},"canonical_sha256":"eec2206a33343cd59557e309a4053c562f6a54bd526d8c7f7ae95fda0f17cff4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eec2206a33343cd59557e309a4053c562f6a54bd526d8c7f7ae95fda0f17cff4","first_computed_at":"2026-05-21T01:05:27.787786Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:05:27.787786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7pqUWPgWuopE1zSwHbG4vVlJipVIsfhzZufAvqirx25N2uv8Q8ZrCQjzXMQ3GY2up7cAtIUzSKBQ2cZ5q6gwBw==","signature_status":"signed_v1","signed_at":"2026-05-21T01:05:27.788411Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20915","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad24a237ded493a9f18e977938353f0d120ee6d5a287ca6048bb5214460bcbb9","sha256:7e4401c109a8c0523188580f0d8033dac67f8826592ae6c4407a5eba95b01255"],"state_sha256":"c85f87f3ec699386361c436b4c402f5c8afc1e3377c7227dc8125e844e3d0445"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t9D3Za/+opwymN3SUwgXRO4MzYSmx9emJH87Oa2vesZx6z54FKoXkCUL9U4uNp7R08XYca035e0bHbYXS/G+DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T01:58:04.597190Z","bundle_sha256":"76f7be6095ffccea2cd53051037d07f47ca696b167fb390a80de9a0d2a87fde4"}}