{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:CXZEVYUT2HTKSFSB6BHV6KA7CL","short_pith_number":"pith:CXZEVYUT","canonical_record":{"source":{"id":"1508.05154","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-21T00:25:51Z","cross_cats_sorted":[],"title_canon_sha256":"701c1b80c9e61eff2b60055f3b1d32ed4141cb67184be312e228a212e612962f","abstract_canon_sha256":"c21d32c2aa276dc12f7b21366b49e5008ed7cfd4370da20ac3e88312e4a779ea"},"schema_version":"1.0"},"canonical_sha256":"15f24ae293d1e6a91641f04f5f281f12c602a926073768f676807c05f91b08f8","source":{"kind":"arxiv","id":"1508.05154","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1508.05154","created_at":"2026-05-18T01:34:07Z"},{"alias_kind":"arxiv_version","alias_value":"1508.05154v2","created_at":"2026-05-18T01:34:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.05154","created_at":"2026-05-18T01:34:07Z"},{"alias_kind":"pith_short_12","alias_value":"CXZEVYUT2HTK","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_16","alias_value":"CXZEVYUT2HTKSFSB","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_8","alias_value":"CXZEVYUT","created_at":"2026-05-18T12:29:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:CXZEVYUT2HTKSFSB6BHV6KA7CL","target":"record","payload":{"canonical_record":{"source":{"id":"1508.05154","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-21T00:25:51Z","cross_cats_sorted":[],"title_canon_sha256":"701c1b80c9e61eff2b60055f3b1d32ed4141cb67184be312e228a212e612962f","abstract_canon_sha256":"c21d32c2aa276dc12f7b21366b49e5008ed7cfd4370da20ac3e88312e4a779ea"},"schema_version":"1.0"},"canonical_sha256":"15f24ae293d1e6a91641f04f5f281f12c602a926073768f676807c05f91b08f8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:34:07.139522Z","signature_b64":"7VKYW+F6wuFAKMG/EO8YE8DcSeABb8p+K2CuWnoitLc5GtYti7HuNDXwW2LT3BxMy6Lqycf35PtgkfAwkMIKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15f24ae293d1e6a91641f04f5f281f12c602a926073768f676807c05f91b08f8","last_reissued_at":"2026-05-18T01:34:07.139066Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:34:07.139066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1508.05154","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:34:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3MrUTVTyc+NxoB3ZVPOwXMialTGjtHmR9WhVbA0quBFGGFDW1lFtCqhWKlsQwsjYqtJlqopxIIvfRSTeLifHCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T04:00:00.624675Z"},"content_sha256":"d8eaaec5fe1b70ee38603e869e64d8989e67b8b749d0c1668e7b6d83f7fe618b","schema_version":"1.0","event_id":"sha256:d8eaaec5fe1b70ee38603e869e64d8989e67b8b749d0c1668e7b6d83f7fe618b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:CXZEVYUT2HTKSFSB6BHV6KA7CL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Posterior calibration and exploratory analysis for natural language processing models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Brendan O'Connor, Khanh Nguyen","submitted_at":"2015-08-21T00:25:51Z","abstract_excerpt":"Many models in natural language processing define probabilistic distributions over linguistic structures. We argue that (1) the quality of a model' s posterior distribution can and should be directly evaluated, as to whether probabilities correspond to empirical frequencies, and (2) NLP uncertainty can be projected not only to pipeline components, but also to exploratory data analysis, telling a user when to trust and not trust the NLP analysis. We present a method to analyze calibration, and apply it to compare the miscalibration of several commonly used models. We also contribute a coreferen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.05154","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T01:34:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WUbXTj3aBBgp9onu4K+jLrSq48FhaGN6H+6TUNyoSxVqAC2Ogyn4x4g6zSmCATK0HGZMJDgMFwpASYPRRDfsBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T04:00:00.625039Z"},"content_sha256":"a8087552525a79769b6beeb931d475d74570204b82e2934c27d8a1e9c26bb2da","schema_version":"1.0","event_id":"sha256:a8087552525a79769b6beeb931d475d74570204b82e2934c27d8a1e9c26bb2da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CXZEVYUT2HTKSFSB6BHV6KA7CL/bundle.json","state_url":"https://pith.science/pith/CXZEVYUT2HTKSFSB6BHV6KA7CL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CXZEVYUT2HTKSFSB6BHV6KA7CL/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":"2026-05-28T04:00:00Z","links":{"resolver":"https://pith.science/pith/CXZEVYUT2HTKSFSB6BHV6KA7CL","bundle":"https://pith.science/pith/CXZEVYUT2HTKSFSB6BHV6KA7CL/bundle.json","state":"https://pith.science/pith/CXZEVYUT2HTKSFSB6BHV6KA7CL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CXZEVYUT2HTKSFSB6BHV6KA7CL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:CXZEVYUT2HTKSFSB6BHV6KA7CL","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":"c21d32c2aa276dc12f7b21366b49e5008ed7cfd4370da20ac3e88312e4a779ea","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-21T00:25:51Z","title_canon_sha256":"701c1b80c9e61eff2b60055f3b1d32ed4141cb67184be312e228a212e612962f"},"schema_version":"1.0","source":{"id":"1508.05154","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1508.05154","created_at":"2026-05-18T01:34:07Z"},{"alias_kind":"arxiv_version","alias_value":"1508.05154v2","created_at":"2026-05-18T01:34:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.05154","created_at":"2026-05-18T01:34:07Z"},{"alias_kind":"pith_short_12","alias_value":"CXZEVYUT2HTK","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_16","alias_value":"CXZEVYUT2HTKSFSB","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_8","alias_value":"CXZEVYUT","created_at":"2026-05-18T12:29:17Z"}],"graph_snapshots":[{"event_id":"sha256:a8087552525a79769b6beeb931d475d74570204b82e2934c27d8a1e9c26bb2da","target":"graph","created_at":"2026-05-18T01:34:07Z","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"},"paper":{"abstract_excerpt":"Many models in natural language processing define probabilistic distributions over linguistic structures. We argue that (1) the quality of a model' s posterior distribution can and should be directly evaluated, as to whether probabilities correspond to empirical frequencies, and (2) NLP uncertainty can be projected not only to pipeline components, but also to exploratory data analysis, telling a user when to trust and not trust the NLP analysis. We present a method to analyze calibration, and apply it to compare the miscalibration of several commonly used models. We also contribute a coreferen","authors_text":"Brendan O'Connor, Khanh Nguyen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-21T00:25:51Z","title":"Posterior calibration and exploratory analysis for natural language processing models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.05154","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:d8eaaec5fe1b70ee38603e869e64d8989e67b8b749d0c1668e7b6d83f7fe618b","target":"record","created_at":"2026-05-18T01:34:07Z","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":"c21d32c2aa276dc12f7b21366b49e5008ed7cfd4370da20ac3e88312e4a779ea","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-21T00:25:51Z","title_canon_sha256":"701c1b80c9e61eff2b60055f3b1d32ed4141cb67184be312e228a212e612962f"},"schema_version":"1.0","source":{"id":"1508.05154","kind":"arxiv","version":2}},"canonical_sha256":"15f24ae293d1e6a91641f04f5f281f12c602a926073768f676807c05f91b08f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15f24ae293d1e6a91641f04f5f281f12c602a926073768f676807c05f91b08f8","first_computed_at":"2026-05-18T01:34:07.139066Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:34:07.139066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7VKYW+F6wuFAKMG/EO8YE8DcSeABb8p+K2CuWnoitLc5GtYti7HuNDXwW2LT3BxMy6Lqycf35PtgkfAwkMIKBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:34:07.139522Z","signed_message":"canonical_sha256_bytes"},"source_id":"1508.05154","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d8eaaec5fe1b70ee38603e869e64d8989e67b8b749d0c1668e7b6d83f7fe618b","sha256:a8087552525a79769b6beeb931d475d74570204b82e2934c27d8a1e9c26bb2da"],"state_sha256":"8852144982d1cf2d51fb87bee6fdaa147ea2b794c4f659a3bb0fcf03bec759f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pC+3L1vWKsQkb6+m55KU/7GYUeX0MxsU6bsXWGCE3fd2ZkUZ88jkWd1B8v69ko2nicBsB8F/j/pv8DVwTIyFAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T04:00:00.627216Z","bundle_sha256":"0cf244e210d4a6d231a551845507ffd797a9c1bb575e1e2f1f48f9d9cbb6d584"}}