{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:OI57X7QOFDLDGVH7YLNJAR5Q7P","short_pith_number":"pith:OI57X7QO","canonical_record":{"source":{"id":"2205.11482","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-23T17:34:16Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"853d79d2d37d5df17a0dfbbf6b9444095b450f02aae604200eaaefb2d4fd8b83","abstract_canon_sha256":"9283252481343f86978150fdc2ead2c04d37fbce16e5cd0b969460ddf96c0ff3"},"schema_version":"1.0"},"canonical_sha256":"723bfbfe0e28d63354ffc2da9047b0fbf8de7b6646b821d96b7e0ca9abaaddd1","source":{"kind":"arxiv","id":"2205.11482","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.11482","created_at":"2026-07-05T05:09:59Z"},{"alias_kind":"arxiv_version","alias_value":"2205.11482v3","created_at":"2026-07-05T05:09:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11482","created_at":"2026-07-05T05:09:59Z"},{"alias_kind":"pith_short_12","alias_value":"OI57X7QOFDLD","created_at":"2026-07-05T05:09:59Z"},{"alias_kind":"pith_short_16","alias_value":"OI57X7QOFDLDGVH7","created_at":"2026-07-05T05:09:59Z"},{"alias_kind":"pith_short_8","alias_value":"OI57X7QO","created_at":"2026-07-05T05:09:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:OI57X7QOFDLDGVH7YLNJAR5Q7P","target":"record","payload":{"canonical_record":{"source":{"id":"2205.11482","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-23T17:34:16Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"853d79d2d37d5df17a0dfbbf6b9444095b450f02aae604200eaaefb2d4fd8b83","abstract_canon_sha256":"9283252481343f86978150fdc2ead2c04d37fbce16e5cd0b969460ddf96c0ff3"},"schema_version":"1.0"},"canonical_sha256":"723bfbfe0e28d63354ffc2da9047b0fbf8de7b6646b821d96b7e0ca9abaaddd1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:59.110681Z","signature_b64":"92ARS4PdChsQmNvY+us6mU+qFtq9bzPiqC2EmNuwgbefz7ChlcTEsl6KyJPRyczcvFh0pDQbmmRd1DW4XHzeCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"723bfbfe0e28d63354ffc2da9047b0fbf8de7b6646b821d96b7e0ca9abaaddd1","last_reissued_at":"2026-07-05T05:09:59.110233Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:59.110233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.11482","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:09:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UJc5T3vktEYqp5xPfSW3Z0hMJ/IGPMx2wRm6OD3wF4cftzwAJxntU94GUeD9rGgK7IfzuhgVaf/fJ589sGOpDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T11:26:07.343264Z"},"content_sha256":"93dd161faca6aa3955dc0a8edf5310c17a23c1b964544013b58fe9de778c976c","schema_version":"1.0","event_id":"sha256:93dd161faca6aa3955dc0a8edf5310c17a23c1b964544013b58fe9de778c976c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:OI57X7QOFDLDGVH7YLNJAR5Q7P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Tracing Factual Knowledge in Language Models Back to the Training Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Binbin Xiong, Ekin Aky\\\"urek, Frederick Liu, Ian Tenney, Jacob Andreas, Kelvin Guu, Tolga Bolukbasi","submitted_at":"2022-05-23T17:34:16Z","abstract_excerpt":"Language models (LMs) have been shown to memorize a great deal of factual knowledge contained in their training data. But when an LM generates an assertion, it is often difficult to determine where it learned this information and whether it is true. In this paper, we propose the problem of fact tracing: identifying which training examples taught an LM to generate a particular factual assertion. Prior work on training data attribution (TDA) may offer effective tools for identifying such examples, known as \"proponents\". We present the first quantitative benchmark to evaluate this. We compare two"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11482","kind":"arxiv","version":3},"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/2205.11482/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":"2026-07-05T05:09:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RyhFUxjy2EswMDqvuy6a9QPslzB17zqUh2eFERBGnOqqM15LXt7xcjp1W9moS31J/C08Ggh0wEFYA/ceWwMFDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T11:26:07.343646Z"},"content_sha256":"603fa0e95584556352d2e46db0724ab45cda8879bafe3e75abda775a8896b70d","schema_version":"1.0","event_id":"sha256:603fa0e95584556352d2e46db0724ab45cda8879bafe3e75abda775a8896b70d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OI57X7QOFDLDGVH7YLNJAR5Q7P/bundle.json","state_url":"https://pith.science/pith/OI57X7QOFDLDGVH7YLNJAR5Q7P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OI57X7QOFDLDGVH7YLNJAR5Q7P/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":"2026-08-18T11:26:07Z","links":{"resolver":"https://pith.science/pith/OI57X7QOFDLDGVH7YLNJAR5Q7P","bundle":"https://pith.science/pith/OI57X7QOFDLDGVH7YLNJAR5Q7P/bundle.json","state":"https://pith.science/pith/OI57X7QOFDLDGVH7YLNJAR5Q7P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OI57X7QOFDLDGVH7YLNJAR5Q7P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:OI57X7QOFDLDGVH7YLNJAR5Q7P","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":"9283252481343f86978150fdc2ead2c04d37fbce16e5cd0b969460ddf96c0ff3","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-23T17:34:16Z","title_canon_sha256":"853d79d2d37d5df17a0dfbbf6b9444095b450f02aae604200eaaefb2d4fd8b83"},"schema_version":"1.0","source":{"id":"2205.11482","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.11482","created_at":"2026-07-05T05:09:59Z"},{"alias_kind":"arxiv_version","alias_value":"2205.11482v3","created_at":"2026-07-05T05:09:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11482","created_at":"2026-07-05T05:09:59Z"},{"alias_kind":"pith_short_12","alias_value":"OI57X7QOFDLD","created_at":"2026-07-05T05:09:59Z"},{"alias_kind":"pith_short_16","alias_value":"OI57X7QOFDLDGVH7","created_at":"2026-07-05T05:09:59Z"},{"alias_kind":"pith_short_8","alias_value":"OI57X7QO","created_at":"2026-07-05T05:09:59Z"}],"graph_snapshots":[{"event_id":"sha256:603fa0e95584556352d2e46db0724ab45cda8879bafe3e75abda775a8896b70d","target":"graph","created_at":"2026-07-05T05:09:59Z","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/2205.11482/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models (LMs) have been shown to memorize a great deal of factual knowledge contained in their training data. But when an LM generates an assertion, it is often difficult to determine where it learned this information and whether it is true. In this paper, we propose the problem of fact tracing: identifying which training examples taught an LM to generate a particular factual assertion. Prior work on training data attribution (TDA) may offer effective tools for identifying such examples, known as \"proponents\". We present the first quantitative benchmark to evaluate this. We compare two","authors_text":"Binbin Xiong, Ekin Aky\\\"urek, Frederick Liu, Ian Tenney, Jacob Andreas, Kelvin Guu, Tolga Bolukbasi","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-23T17:34:16Z","title":"Towards Tracing Factual Knowledge in Language Models Back to the Training Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11482","kind":"arxiv","version":3},"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":"sha256:93dd161faca6aa3955dc0a8edf5310c17a23c1b964544013b58fe9de778c976c","target":"record","created_at":"2026-07-05T05:09:59Z","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":"9283252481343f86978150fdc2ead2c04d37fbce16e5cd0b969460ddf96c0ff3","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-23T17:34:16Z","title_canon_sha256":"853d79d2d37d5df17a0dfbbf6b9444095b450f02aae604200eaaefb2d4fd8b83"},"schema_version":"1.0","source":{"id":"2205.11482","kind":"arxiv","version":3}},"canonical_sha256":"723bfbfe0e28d63354ffc2da9047b0fbf8de7b6646b821d96b7e0ca9abaaddd1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"723bfbfe0e28d63354ffc2da9047b0fbf8de7b6646b821d96b7e0ca9abaaddd1","first_computed_at":"2026-07-05T05:09:59.110233Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:09:59.110233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"92ARS4PdChsQmNvY+us6mU+qFtq9bzPiqC2EmNuwgbefz7ChlcTEsl6KyJPRyczcvFh0pDQbmmRd1DW4XHzeCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:09:59.110681Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.11482","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:93dd161faca6aa3955dc0a8edf5310c17a23c1b964544013b58fe9de778c976c","sha256:603fa0e95584556352d2e46db0724ab45cda8879bafe3e75abda775a8896b70d"],"state_sha256":"525286b42218b8ed4387b5ce7caa2523148418c939ebabf76c769403c27815f8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OAptiw2XRd5ASImHq1r33dTpiFnbFvI+/Vab0lOVoyWkodbdpXSuyTtbRya54cgu30pRcs+rpJOT3KD0P2dUBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T11:26:07.346059Z","bundle_sha256":"6f46eeff48470696810532207bf9e1d095581bb706942dc01a88ea0548415c7f"}}