{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PZNKVSAN46TMRWCWE52TOGISP7","short_pith_number":"pith:PZNKVSAN","schema_version":"1.0","canonical_sha256":"7e5aaac80de7a6c8d85627753719127ffbf23c97b0c19c550cb8b0e8abcde4f4","source":{"kind":"arxiv","id":"2502.18342","version":1},"attestation_state":"computed","paper":{"title":"BRIDO: Bringing Democratic Order to Abstractive Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Harshith Goka, Hyeonmok Ko, Junhyun Lee","submitted_at":"2025-02-25T16:33:50Z","abstract_excerpt":"Hallucination refers to the inaccurate, irrelevant, and inconsistent text generated from large language models (LLMs). While the LLMs have shown great promise in a variety of tasks, the issue of hallucination still remains a major challenge for many practical uses. In this paper, we tackle the issue of hallucination in abstract text summarization by mitigating exposure bias. Existing models targeted for exposure bias mitigation, namely BRIO, aim for better summarization quality in the ROUGE score. We propose a model that uses a similar exposure bias mitigation strategy but with a goal that is "},"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":"2502.18342","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-25T16:33:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6266e244fea11bd9cb6fa915a63329a8331abb295afa0a5eb32ae173cdf4fc32","abstract_canon_sha256":"da284af5af98dcb7e64f05078f46f2de4d5db112066b68c0b84c1b6d47a75e4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:52.555767Z","signature_b64":"OoEYedEXJ0BhtBP3HLsRf2uC3yYx1F9EClbR77BPAAeN615h25UNipJ+hq3Zi/doX0ZUKUGsaNkBC2ua2C/pDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e5aaac80de7a6c8d85627753719127ffbf23c97b0c19c550cb8b0e8abcde4f4","last_reissued_at":"2026-07-05T10:19:52.555280Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:52.555280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BRIDO: Bringing Democratic Order to Abstractive Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Harshith Goka, Hyeonmok Ko, Junhyun Lee","submitted_at":"2025-02-25T16:33:50Z","abstract_excerpt":"Hallucination refers to the inaccurate, irrelevant, and inconsistent text generated from large language models (LLMs). While the LLMs have shown great promise in a variety of tasks, the issue of hallucination still remains a major challenge for many practical uses. In this paper, we tackle the issue of hallucination in abstract text summarization by mitigating exposure bias. Existing models targeted for exposure bias mitigation, namely BRIO, aim for better summarization quality in the ROUGE score. We propose a model that uses a similar exposure bias mitigation strategy but with a goal that is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18342","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/2502.18342/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":"2502.18342","created_at":"2026-07-05T10:19:52.555339+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.18342v1","created_at":"2026-07-05T10:19:52.555339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18342","created_at":"2026-07-05T10:19:52.555339+00:00"},{"alias_kind":"pith_short_12","alias_value":"PZNKVSAN46TM","created_at":"2026-07-05T10:19:52.555339+00:00"},{"alias_kind":"pith_short_16","alias_value":"PZNKVSAN46TMRWCW","created_at":"2026-07-05T10:19:52.555339+00:00"},{"alias_kind":"pith_short_8","alias_value":"PZNKVSAN","created_at":"2026-07-05T10:19:52.555339+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/PZNKVSAN46TMRWCWE52TOGISP7","json":"https://pith.science/pith/PZNKVSAN46TMRWCWE52TOGISP7.json","graph_json":"https://pith.science/api/pith-number/PZNKVSAN46TMRWCWE52TOGISP7/graph.json","events_json":"https://pith.science/api/pith-number/PZNKVSAN46TMRWCWE52TOGISP7/events.json","paper":"https://pith.science/paper/PZNKVSAN"},"agent_actions":{"view_html":"https://pith.science/pith/PZNKVSAN46TMRWCWE52TOGISP7","download_json":"https://pith.science/pith/PZNKVSAN46TMRWCWE52TOGISP7.json","view_paper":"https://pith.science/paper/PZNKVSAN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.18342&json=true","fetch_graph":"https://pith.science/api/pith-number/PZNKVSAN46TMRWCWE52TOGISP7/graph.json","fetch_events":"https://pith.science/api/pith-number/PZNKVSAN46TMRWCWE52TOGISP7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PZNKVSAN46TMRWCWE52TOGISP7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PZNKVSAN46TMRWCWE52TOGISP7/action/storage_attestation","attest_author":"https://pith.science/pith/PZNKVSAN46TMRWCWE52TOGISP7/action/author_attestation","sign_citation":"https://pith.science/pith/PZNKVSAN46TMRWCWE52TOGISP7/action/citation_signature","submit_replication":"https://pith.science/pith/PZNKVSAN46TMRWCWE52TOGISP7/action/replication_record"}},"created_at":"2026-07-05T10:19:52.555339+00:00","updated_at":"2026-07-05T10:19:52.555339+00:00"}