{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VEWIA4IVXVW7LZYWXYC4YHM2O3","short_pith_number":"pith:VEWIA4IV","canonical_record":{"source":{"id":"2607.18454","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-20T19:07:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9c5609bb98ba29cfef05f0620c5acc6e38952b76a87bcea11dc04cdc3e2edd2f","abstract_canon_sha256":"b89f7756f330a3fb0dfdbea57292c3ceb5306cb93b087c36fc31afe2ae1571d9"},"schema_version":"1.0"},"canonical_sha256":"a92c807115bd6df5e716be05cc1d9a76fc3fe174c423add7de44ac661618eb75","source":{"kind":"arxiv","id":"2607.18454","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18454","created_at":"2026-07-22T00:22:49Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18454v1","created_at":"2026-07-22T00:22:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18454","created_at":"2026-07-22T00:22:49Z"},{"alias_kind":"pith_short_12","alias_value":"VEWIA4IVXVW7","created_at":"2026-07-22T00:22:49Z"},{"alias_kind":"pith_short_16","alias_value":"VEWIA4IVXVW7LZYW","created_at":"2026-07-22T00:22:49Z"},{"alias_kind":"pith_short_8","alias_value":"VEWIA4IV","created_at":"2026-07-22T00:22:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VEWIA4IVXVW7LZYWXYC4YHM2O3","target":"record","payload":{"canonical_record":{"source":{"id":"2607.18454","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-20T19:07:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9c5609bb98ba29cfef05f0620c5acc6e38952b76a87bcea11dc04cdc3e2edd2f","abstract_canon_sha256":"b89f7756f330a3fb0dfdbea57292c3ceb5306cb93b087c36fc31afe2ae1571d9"},"schema_version":"1.0"},"canonical_sha256":"a92c807115bd6df5e716be05cc1d9a76fc3fe174c423add7de44ac661618eb75","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T00:22:49.299930Z","signature_b64":"H+HtENkTGZo7ILPFIixVXI65V+MY9AUtl/gaHZcPRLEN5xixzFuZaej5DuXrZIkhMQQDto4Hp+sPyVWlUXfXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a92c807115bd6df5e716be05cc1d9a76fc3fe174c423add7de44ac661618eb75","last_reissued_at":"2026-07-22T00:22:49.299040Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T00:22:49.299040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.18454","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":"2026-07-22T00:22:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ev3X6bBfaGt4tp07HM/n1V0bvIxr+QhYEjOHKnPtOVDeM9Wzi+57t3f5OmMe70rd6bpGyHAw2qFHKiqXogXaAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:15:30.548947Z"},"content_sha256":"eaf6c966b4f9d37d6b0e135d080e9563f09f5a07bf6a5d38445577417e042a11","schema_version":"1.0","event_id":"sha256:eaf6c966b4f9d37d6b0e135d080e9563f09f5a07bf6a5d38445577417e042a11"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VEWIA4IVXVW7LZYWXYC4YHM2O3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Estimating Rare Events in Language Models with Proper Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anqi Liu, Nikita Y. Parulekar","submitted_at":"2026-07-20T19:07:43Z","abstract_excerpt":"Quantifying the risk of rare failures in language models, such as those triggered by adversarial distribution shifts or very large-scale deployments, requires estimating probabilities far too small for random sampling. While recent work has formalized Low Probability Estimation, existing pipelines remain fragile in the rarest regimes: estimators can suffer zero-estimate collapse or systematic bias, and standard evaluation losses can become unstable or poorly matched to asymmetric safety costs. In this work, we introduce Gradient Activation Adaptive Multi-Level Splitting (GA-AMLS), which adapts"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18454","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/2607.18454/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":"2026-07-22T00:22:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q6+e4fcSypyJ0o6joxrTF0b4a+PKsL5iZL9xVOUJ5Bt63Ff6za09UUUmxrCdCMaCmgeQIoNlKR9wVZXdqrhJDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:15:30.549599Z"},"content_sha256":"4ec172cdd1f61974ead4af05adb566ea4d797f14f79a71628741320edc94d106","schema_version":"1.0","event_id":"sha256:4ec172cdd1f61974ead4af05adb566ea4d797f14f79a71628741320edc94d106"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VEWIA4IVXVW7LZYWXYC4YHM2O3/bundle.json","state_url":"https://pith.science/pith/VEWIA4IVXVW7LZYWXYC4YHM2O3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VEWIA4IVXVW7LZYWXYC4YHM2O3/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":"2026-08-08T13:15:30Z","links":{"resolver":"https://pith.science/pith/VEWIA4IVXVW7LZYWXYC4YHM2O3","bundle":"https://pith.science/pith/VEWIA4IVXVW7LZYWXYC4YHM2O3/bundle.json","state":"https://pith.science/pith/VEWIA4IVXVW7LZYWXYC4YHM2O3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VEWIA4IVXVW7LZYWXYC4YHM2O3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VEWIA4IVXVW7LZYWXYC4YHM2O3","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":"b89f7756f330a3fb0dfdbea57292c3ceb5306cb93b087c36fc31afe2ae1571d9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-20T19:07:43Z","title_canon_sha256":"9c5609bb98ba29cfef05f0620c5acc6e38952b76a87bcea11dc04cdc3e2edd2f"},"schema_version":"1.0","source":{"id":"2607.18454","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18454","created_at":"2026-07-22T00:22:49Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18454v1","created_at":"2026-07-22T00:22:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18454","created_at":"2026-07-22T00:22:49Z"},{"alias_kind":"pith_short_12","alias_value":"VEWIA4IVXVW7","created_at":"2026-07-22T00:22:49Z"},{"alias_kind":"pith_short_16","alias_value":"VEWIA4IVXVW7LZYW","created_at":"2026-07-22T00:22:49Z"},{"alias_kind":"pith_short_8","alias_value":"VEWIA4IV","created_at":"2026-07-22T00:22:49Z"}],"graph_snapshots":[{"event_id":"sha256:4ec172cdd1f61974ead4af05adb566ea4d797f14f79a71628741320edc94d106","target":"graph","created_at":"2026-07-22T00:22:49Z","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/2607.18454/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Quantifying the risk of rare failures in language models, such as those triggered by adversarial distribution shifts or very large-scale deployments, requires estimating probabilities far too small for random sampling. While recent work has formalized Low Probability Estimation, existing pipelines remain fragile in the rarest regimes: estimators can suffer zero-estimate collapse or systematic bias, and standard evaluation losses can become unstable or poorly matched to asymmetric safety costs. In this work, we introduce Gradient Activation Adaptive Multi-Level Splitting (GA-AMLS), which adapts","authors_text":"Anqi Liu, Nikita Y. Parulekar","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-20T19:07:43Z","title":"Estimating Rare Events in Language Models with Proper Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18454","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:eaf6c966b4f9d37d6b0e135d080e9563f09f5a07bf6a5d38445577417e042a11","target":"record","created_at":"2026-07-22T00:22:49Z","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":"b89f7756f330a3fb0dfdbea57292c3ceb5306cb93b087c36fc31afe2ae1571d9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-20T19:07:43Z","title_canon_sha256":"9c5609bb98ba29cfef05f0620c5acc6e38952b76a87bcea11dc04cdc3e2edd2f"},"schema_version":"1.0","source":{"id":"2607.18454","kind":"arxiv","version":1}},"canonical_sha256":"a92c807115bd6df5e716be05cc1d9a76fc3fe174c423add7de44ac661618eb75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a92c807115bd6df5e716be05cc1d9a76fc3fe174c423add7de44ac661618eb75","first_computed_at":"2026-07-22T00:22:49.299040Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T00:22:49.299040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H+HtENkTGZo7ILPFIixVXI65V+MY9AUtl/gaHZcPRLEN5xixzFuZaej5DuXrZIkhMQQDto4Hp+sPyVWlUXfXAw==","signature_status":"signed_v1","signed_at":"2026-07-22T00:22:49.299930Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.18454","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eaf6c966b4f9d37d6b0e135d080e9563f09f5a07bf6a5d38445577417e042a11","sha256:4ec172cdd1f61974ead4af05adb566ea4d797f14f79a71628741320edc94d106"],"state_sha256":"3ed9debbfb3fb855cfe57b9b7f014743469bce720916cab7ddeff2420b851bd8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"klSWiiHy5m3jbsshwqVczxAUL+VCOg2X7QpKtKcbnAJKAT77vAC6lHXW2L8eLtQqCrP2hKw0TTk2TC4mLTOTAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:15:30.554035Z","bundle_sha256":"8a2506942d8b7237b106abe2482bb5656c1fa8118be0177f42d5a9fec09d1c64"}}