{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:LUC4CNMAQ664JJ4DHTD2W5LAKN","short_pith_number":"pith:LUC4CNMA","canonical_record":{"source":{"id":"2103.15171","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-03-28T16:43:01Z","cross_cats_sorted":[],"title_canon_sha256":"85396de5c4742964c03d906e3dbed260d1bac5dfefac6386401f7e83a688df57","abstract_canon_sha256":"a69d016ab1989305c2a579ae064b0cc54cf4e2a2d030e2253ef61b75fb8f6b4b"},"schema_version":"1.0"},"canonical_sha256":"5d05c1358087bdc4a7833cc7ab75605340b566cbb6cf2ce47deb85cf0ca02809","source":{"kind":"arxiv","id":"2103.15171","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.15171","created_at":"2026-07-05T02:27:03Z"},{"alias_kind":"arxiv_version","alias_value":"2103.15171v1","created_at":"2026-07-05T02:27:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.15171","created_at":"2026-07-05T02:27:03Z"},{"alias_kind":"pith_short_12","alias_value":"LUC4CNMAQ664","created_at":"2026-07-05T02:27:03Z"},{"alias_kind":"pith_short_16","alias_value":"LUC4CNMAQ664JJ4D","created_at":"2026-07-05T02:27:03Z"},{"alias_kind":"pith_short_8","alias_value":"LUC4CNMA","created_at":"2026-07-05T02:27:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:LUC4CNMAQ664JJ4DHTD2W5LAKN","target":"record","payload":{"canonical_record":{"source":{"id":"2103.15171","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-03-28T16:43:01Z","cross_cats_sorted":[],"title_canon_sha256":"85396de5c4742964c03d906e3dbed260d1bac5dfefac6386401f7e83a688df57","abstract_canon_sha256":"a69d016ab1989305c2a579ae064b0cc54cf4e2a2d030e2253ef61b75fb8f6b4b"},"schema_version":"1.0"},"canonical_sha256":"5d05c1358087bdc4a7833cc7ab75605340b566cbb6cf2ce47deb85cf0ca02809","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:27:03.242956Z","signature_b64":"J1hgWPJgkHAkY1rJ+tbpvehMu4gA7EDYPaV0T4jXvTyShIfmbqgJmDuwNMGkpjg12lWYz0D9Km2VaalRgFldAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d05c1358087bdc4a7833cc7ab75605340b566cbb6cf2ce47deb85cf0ca02809","last_reissued_at":"2026-07-05T02:27:03.242544Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:27:03.242544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.15171","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":"2026-07-05T02:27:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lf++rIwl4umYOdnrIPUuI0iOnFjF8NCrh80pIfpBaNLJfNfKnR71A+J5na6Qsa2cO1iWZseV6VJJrAjFXQT1CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T06:50:57.932449Z"},"content_sha256":"246e431977a0fc41abc74de5a175ee89ae4ae05d337e822c56e513859d9f2b36","schema_version":"1.0","event_id":"sha256:246e431977a0fc41abc74de5a175ee89ae4ae05d337e822c56e513859d9f2b36"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:LUC4CNMAQ664JJ4DHTD2W5LAKN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Bayesian Approach to Identifying Representational Errors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ece Kamar, Julie Shah, Ramya Ramakrishnan, Vaibhav Unhelkar","submitted_at":"2021-03-28T16:43:01Z","abstract_excerpt":"Trained AI systems and expert decision makers can make errors that are often difficult to identify and understand. Determining the root cause for these errors can improve future decisions. This work presents Generative Error Model (GEM), a generative model for inferring representational errors based on observations of an actor's behavior (either simulated agent, robot, or human). The model considers two sources of error: those that occur due to representational limitations -- \"blind spots\" -- and non-representational errors, such as those caused by noise in execution or systematic errors prese"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.15171","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/2103.15171/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":"2026-07-05T02:27:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IgSba4wPLVETdMJm060uEv+oHni4FuywWgCmyGdycc/d/ApCxYT6RPJUYidl/nTyZVuial/8BV4OTfMnMkw+Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T06:50:57.933014Z"},"content_sha256":"1c04073ac9c94f6cdcf7219946fb0e65c544bbec1beb60ab6293bd3b85f121c4","schema_version":"1.0","event_id":"sha256:1c04073ac9c94f6cdcf7219946fb0e65c544bbec1beb60ab6293bd3b85f121c4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LUC4CNMAQ664JJ4DHTD2W5LAKN/bundle.json","state_url":"https://pith.science/pith/LUC4CNMAQ664JJ4DHTD2W5LAKN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LUC4CNMAQ664JJ4DHTD2W5LAKN/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":"2026-08-14T06:50:57Z","links":{"resolver":"https://pith.science/pith/LUC4CNMAQ664JJ4DHTD2W5LAKN","bundle":"https://pith.science/pith/LUC4CNMAQ664JJ4DHTD2W5LAKN/bundle.json","state":"https://pith.science/pith/LUC4CNMAQ664JJ4DHTD2W5LAKN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LUC4CNMAQ664JJ4DHTD2W5LAKN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:LUC4CNMAQ664JJ4DHTD2W5LAKN","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":"a69d016ab1989305c2a579ae064b0cc54cf4e2a2d030e2253ef61b75fb8f6b4b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-03-28T16:43:01Z","title_canon_sha256":"85396de5c4742964c03d906e3dbed260d1bac5dfefac6386401f7e83a688df57"},"schema_version":"1.0","source":{"id":"2103.15171","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.15171","created_at":"2026-07-05T02:27:03Z"},{"alias_kind":"arxiv_version","alias_value":"2103.15171v1","created_at":"2026-07-05T02:27:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.15171","created_at":"2026-07-05T02:27:03Z"},{"alias_kind":"pith_short_12","alias_value":"LUC4CNMAQ664","created_at":"2026-07-05T02:27:03Z"},{"alias_kind":"pith_short_16","alias_value":"LUC4CNMAQ664JJ4D","created_at":"2026-07-05T02:27:03Z"},{"alias_kind":"pith_short_8","alias_value":"LUC4CNMA","created_at":"2026-07-05T02:27:03Z"}],"graph_snapshots":[{"event_id":"sha256:1c04073ac9c94f6cdcf7219946fb0e65c544bbec1beb60ab6293bd3b85f121c4","target":"graph","created_at":"2026-07-05T02:27:03Z","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/2103.15171/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Trained AI systems and expert decision makers can make errors that are often difficult to identify and understand. Determining the root cause for these errors can improve future decisions. This work presents Generative Error Model (GEM), a generative model for inferring representational errors based on observations of an actor's behavior (either simulated agent, robot, or human). The model considers two sources of error: those that occur due to representational limitations -- \"blind spots\" -- and non-representational errors, such as those caused by noise in execution or systematic errors prese","authors_text":"Ece Kamar, Julie Shah, Ramya Ramakrishnan, Vaibhav Unhelkar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-03-28T16:43:01Z","title":"A Bayesian Approach to Identifying Representational Errors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.15171","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":"sha256:246e431977a0fc41abc74de5a175ee89ae4ae05d337e822c56e513859d9f2b36","target":"record","created_at":"2026-07-05T02:27:03Z","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":"a69d016ab1989305c2a579ae064b0cc54cf4e2a2d030e2253ef61b75fb8f6b4b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-03-28T16:43:01Z","title_canon_sha256":"85396de5c4742964c03d906e3dbed260d1bac5dfefac6386401f7e83a688df57"},"schema_version":"1.0","source":{"id":"2103.15171","kind":"arxiv","version":1}},"canonical_sha256":"5d05c1358087bdc4a7833cc7ab75605340b566cbb6cf2ce47deb85cf0ca02809","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d05c1358087bdc4a7833cc7ab75605340b566cbb6cf2ce47deb85cf0ca02809","first_computed_at":"2026-07-05T02:27:03.242544Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:27:03.242544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J1hgWPJgkHAkY1rJ+tbpvehMu4gA7EDYPaV0T4jXvTyShIfmbqgJmDuwNMGkpjg12lWYz0D9Km2VaalRgFldAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:27:03.242956Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.15171","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:246e431977a0fc41abc74de5a175ee89ae4ae05d337e822c56e513859d9f2b36","sha256:1c04073ac9c94f6cdcf7219946fb0e65c544bbec1beb60ab6293bd3b85f121c4"],"state_sha256":"4a41fe720b8df105b139906a845c415f21735737bbb7504e0ca3e521d721b2f4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8tsY/PCMUFmQTCWs5TPY9VGLFMBkFKdYLoY5j2oC42nCJN50Ti3ShzU/WWuOyoDl+FyjrIUsqhcCN0OiTzuSDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T06:50:57.936804Z","bundle_sha256":"6a632f45c6b141d174467c0a5340ee844640d483377349d612099956285043f4"}}