{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IF7N7FI4MGS2EY6CQ3OVFRKCYY","short_pith_number":"pith:IF7N7FI4","schema_version":"1.0","canonical_sha256":"417edf951c61a5a263c286dd52c542c60fb97de96f6817685e7d39496587ce27","source":{"kind":"arxiv","id":"2310.11648","version":2},"attestation_state":"computed","paper":{"title":"Zero-shot Faithfulness Evaluation for Text Summarization with Foundation Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kenny Q. Zhu, Qi Jia, Siyu Ren, Yizhu Liu","submitted_at":"2023-10-18T01:20:16Z","abstract_excerpt":"Despite tremendous improvements in natural language generation, summarization models still suffer from the unfaithfulness issue. Previous work evaluates faithfulness either using models trained on the other tasks or in-domain synthetic data, or prompting a large model such as ChatGPT. This paper proposes to do zero-shot faithfulness evaluation simply with a moderately-sized foundation language model. We introduce a new metric FFLM, which is a combination of probability changes based on the intuition that prefixing a piece of text that is consistent with the output will increase the probability"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.11648","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-18T01:20:16Z","cross_cats_sorted":[],"title_canon_sha256":"81cbcd97fe2713db1dc89e0028dc970e3b099a1c74f2e540ce62613fb539ef32","abstract_canon_sha256":"580bb4ee91a0fe89dbffba4a723cf1e1fb55ce9d6d5283f8c1d36c9c0c32f439"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:01.215196Z","signature_b64":"j1hQJosVgOmsgOsMCejpQhk3d4mVlCesJyaLziYUnn+kiBezpKr254FQnMLdLR/Li4tvi4xiMaADqYZs4Y4HAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"417edf951c61a5a263c286dd52c542c60fb97de96f6817685e7d39496587ce27","last_reissued_at":"2026-07-05T07:24:01.214776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:01.214776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-shot Faithfulness Evaluation for Text Summarization with Foundation Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kenny Q. Zhu, Qi Jia, Siyu Ren, Yizhu Liu","submitted_at":"2023-10-18T01:20:16Z","abstract_excerpt":"Despite tremendous improvements in natural language generation, summarization models still suffer from the unfaithfulness issue. Previous work evaluates faithfulness either using models trained on the other tasks or in-domain synthetic data, or prompting a large model such as ChatGPT. This paper proposes to do zero-shot faithfulness evaluation simply with a moderately-sized foundation language model. We introduce a new metric FFLM, which is a combination of probability changes based on the intuition that prefixing a piece of text that is consistent with the output will increase the probability"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11648","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.11648/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.11648","created_at":"2026-07-05T07:24:01.214827+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.11648v2","created_at":"2026-07-05T07:24:01.214827+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11648","created_at":"2026-07-05T07:24:01.214827+00:00"},{"alias_kind":"pith_short_12","alias_value":"IF7N7FI4MGS2","created_at":"2026-07-05T07:24:01.214827+00:00"},{"alias_kind":"pith_short_16","alias_value":"IF7N7FI4MGS2EY6C","created_at":"2026-07-05T07:24:01.214827+00:00"},{"alias_kind":"pith_short_8","alias_value":"IF7N7FI4","created_at":"2026-07-05T07:24:01.214827+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IF7N7FI4MGS2EY6CQ3OVFRKCYY","json":"https://pith.science/pith/IF7N7FI4MGS2EY6CQ3OVFRKCYY.json","graph_json":"https://pith.science/api/pith-number/IF7N7FI4MGS2EY6CQ3OVFRKCYY/graph.json","events_json":"https://pith.science/api/pith-number/IF7N7FI4MGS2EY6CQ3OVFRKCYY/events.json","paper":"https://pith.science/paper/IF7N7FI4"},"agent_actions":{"view_html":"https://pith.science/pith/IF7N7FI4MGS2EY6CQ3OVFRKCYY","download_json":"https://pith.science/pith/IF7N7FI4MGS2EY6CQ3OVFRKCYY.json","view_paper":"https://pith.science/paper/IF7N7FI4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.11648&json=true","fetch_graph":"https://pith.science/api/pith-number/IF7N7FI4MGS2EY6CQ3OVFRKCYY/graph.json","fetch_events":"https://pith.science/api/pith-number/IF7N7FI4MGS2EY6CQ3OVFRKCYY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IF7N7FI4MGS2EY6CQ3OVFRKCYY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IF7N7FI4MGS2EY6CQ3OVFRKCYY/action/storage_attestation","attest_author":"https://pith.science/pith/IF7N7FI4MGS2EY6CQ3OVFRKCYY/action/author_attestation","sign_citation":"https://pith.science/pith/IF7N7FI4MGS2EY6CQ3OVFRKCYY/action/citation_signature","submit_replication":"https://pith.science/pith/IF7N7FI4MGS2EY6CQ3OVFRKCYY/action/replication_record"}},"created_at":"2026-07-05T07:24:01.214827+00:00","updated_at":"2026-07-05T07:24:01.214827+00:00"}