{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:V7ABTWOJ72QDFFO5HZRCFFIKBU","short_pith_number":"pith:V7ABTWOJ","schema_version":"1.0","canonical_sha256":"afc019d9c9fea03295dd3e6222950a0d01655f18d830827c3c30fb18fd4e554e","source":{"kind":"arxiv","id":"2310.01188","version":2},"attestation_state":"computed","paper":{"title":"Quantifying the Plausibility of Context Reliance in Neural Machine Translation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.CL","authors_text":"Arianna Bisazza, Gabriele Sarti, Grzegorz Chrupa{\\l}a, Malvina Nissim","submitted_at":"2023-10-02T13:26:43Z","abstract_excerpt":"Establishing whether language models can use contextual information in a human-plausible way is important to ensure their trustworthiness in real-world settings. However, the questions of when and which parts of the context affect model generations are typically tackled separately, with current plausibility evaluations being practically limited to a handful of artificial benchmarks. To address this, we introduce Plausibility Evaluation of Context Reliance (PECoRe), an end-to-end interpretability framework designed to quantify context usage in language models' generations. Our approach leverage"},"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":"2310.01188","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-02T13:26:43Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"title_canon_sha256":"d4aaeba49c579c75db591995cc1a4af94f51e56978031c12e25d2b80c524a53f","abstract_canon_sha256":"9a52e749685e026bed692787f3c16749cfd1bb748cefa73efe248d715a01bb6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:24.902024Z","signature_b64":"nJ/2+xn75erW1nLtduLXsOwtMXknP2aYNACWAAhBfaL/UgFFXgnf5wiIc6GJxkMqCN4d+qCZEyvNLhIvdVbxBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afc019d9c9fea03295dd3e6222950a0d01655f18d830827c3c30fb18fd4e554e","last_reissued_at":"2026-07-05T07:55:24.901509Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:24.901509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantifying the Plausibility of Context Reliance in Neural Machine Translation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.CL","authors_text":"Arianna Bisazza, Gabriele Sarti, Grzegorz Chrupa{\\l}a, Malvina Nissim","submitted_at":"2023-10-02T13:26:43Z","abstract_excerpt":"Establishing whether language models can use contextual information in a human-plausible way is important to ensure their trustworthiness in real-world settings. However, the questions of when and which parts of the context affect model generations are typically tackled separately, with current plausibility evaluations being practically limited to a handful of artificial benchmarks. To address this, we introduce Plausibility Evaluation of Context Reliance (PECoRe), an end-to-end interpretability framework designed to quantify context usage in language models' generations. Our approach leverage"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01188","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/2310.01188/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":"2310.01188","created_at":"2026-07-05T07:55:24.901567+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.01188v2","created_at":"2026-07-05T07:55:24.901567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01188","created_at":"2026-07-05T07:55:24.901567+00:00"},{"alias_kind":"pith_short_12","alias_value":"V7ABTWOJ72QD","created_at":"2026-07-05T07:55:24.901567+00:00"},{"alias_kind":"pith_short_16","alias_value":"V7ABTWOJ72QDFFO5","created_at":"2026-07-05T07:55:24.901567+00:00"},{"alias_kind":"pith_short_8","alias_value":"V7ABTWOJ","created_at":"2026-07-05T07:55:24.901567+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29489","citing_title":"Which Tokens Need Context? A Reference-Based Analysis of Translation Responsibility Using Fertility and Entropy","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V7ABTWOJ72QDFFO5HZRCFFIKBU","json":"https://pith.science/pith/V7ABTWOJ72QDFFO5HZRCFFIKBU.json","graph_json":"https://pith.science/api/pith-number/V7ABTWOJ72QDFFO5HZRCFFIKBU/graph.json","events_json":"https://pith.science/api/pith-number/V7ABTWOJ72QDFFO5HZRCFFIKBU/events.json","paper":"https://pith.science/paper/V7ABTWOJ"},"agent_actions":{"view_html":"https://pith.science/pith/V7ABTWOJ72QDFFO5HZRCFFIKBU","download_json":"https://pith.science/pith/V7ABTWOJ72QDFFO5HZRCFFIKBU.json","view_paper":"https://pith.science/paper/V7ABTWOJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.01188&json=true","fetch_graph":"https://pith.science/api/pith-number/V7ABTWOJ72QDFFO5HZRCFFIKBU/graph.json","fetch_events":"https://pith.science/api/pith-number/V7ABTWOJ72QDFFO5HZRCFFIKBU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V7ABTWOJ72QDFFO5HZRCFFIKBU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V7ABTWOJ72QDFFO5HZRCFFIKBU/action/storage_attestation","attest_author":"https://pith.science/pith/V7ABTWOJ72QDFFO5HZRCFFIKBU/action/author_attestation","sign_citation":"https://pith.science/pith/V7ABTWOJ72QDFFO5HZRCFFIKBU/action/citation_signature","submit_replication":"https://pith.science/pith/V7ABTWOJ72QDFFO5HZRCFFIKBU/action/replication_record"}},"created_at":"2026-07-05T07:55:24.901567+00:00","updated_at":"2026-07-05T07:55:24.901567+00:00"}