{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:KF25NU3RAZ5QLSPJIWX3BPBTGS","short_pith_number":"pith:KF25NU3R","schema_version":"1.0","canonical_sha256":"5175d6d371067b05c9e945afb0bc3334a27a83534cc5e037fd425d837691ac53","source":{"kind":"arxiv","id":"2012.14660","version":4},"attestation_state":"computed","paper":{"title":"A Theoretical Analysis of the Repetition Problem in Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anthony Man-Cho So, Bei Shi, Wai Lam, Zihao Fu","submitted_at":"2020-12-29T08:51:47Z","abstract_excerpt":"Text generation tasks, including translation, summarization, language models, and etc. see rapid growth during recent years. Despite the remarkable achievements, the repetition problem has been observed in nearly all text generation models undermining the generation performance extensively. To solve the repetition problem, many methods have been proposed, but there is no existing theoretical analysis to show why this problem happens and how it is resolved. In this paper, we propose a new framework for theoretical analysis for the repetition problem. We first define the Average Repetition Proba"},"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":"2012.14660","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-29T08:51:47Z","cross_cats_sorted":[],"title_canon_sha256":"dc0bf4701abdb63c91c1d19fbff6d0feaebd268e04d9ff1731bb3e495a18734b","abstract_canon_sha256":"34ca0e1beca1c4006df6faea66e8ead68458cba92fe4c5cb133aff0b1728f712"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:24:53.199493Z","signature_b64":"/Mat45GiPScQ6PNa1amIpNZkgbPFDnfU2CahGAT4S4Rv+67SrKwzBw7LnU3KZW+EeDc7D6EbHpRpxbPpI40nAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5175d6d371067b05c9e945afb0bc3334a27a83534cc5e037fd425d837691ac53","last_reissued_at":"2026-07-05T02:24:53.199032Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:24:53.199032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Theoretical Analysis of the Repetition Problem in Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anthony Man-Cho So, Bei Shi, Wai Lam, Zihao Fu","submitted_at":"2020-12-29T08:51:47Z","abstract_excerpt":"Text generation tasks, including translation, summarization, language models, and etc. see rapid growth during recent years. Despite the remarkable achievements, the repetition problem has been observed in nearly all text generation models undermining the generation performance extensively. To solve the repetition problem, many methods have been proposed, but there is no existing theoretical analysis to show why this problem happens and how it is resolved. In this paper, we propose a new framework for theoretical analysis for the repetition problem. We first define the Average Repetition Proba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.14660","kind":"arxiv","version":4},"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/2012.14660/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":"2012.14660","created_at":"2026-07-05T02:24:53.199087+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.14660v4","created_at":"2026-07-05T02:24:53.199087+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.14660","created_at":"2026-07-05T02:24:53.199087+00:00"},{"alias_kind":"pith_short_12","alias_value":"KF25NU3RAZ5Q","created_at":"2026-07-05T02:24:53.199087+00:00"},{"alias_kind":"pith_short_16","alias_value":"KF25NU3RAZ5QLSPJ","created_at":"2026-07-05T02:24:53.199087+00:00"},{"alias_kind":"pith_short_8","alias_value":"KF25NU3R","created_at":"2026-07-05T02:24:53.199087+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10466","citing_title":"Self-Attention as a Covariance Readout: A Unified View of In-Context Learning and Repetition","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KF25NU3RAZ5QLSPJIWX3BPBTGS","json":"https://pith.science/pith/KF25NU3RAZ5QLSPJIWX3BPBTGS.json","graph_json":"https://pith.science/api/pith-number/KF25NU3RAZ5QLSPJIWX3BPBTGS/graph.json","events_json":"https://pith.science/api/pith-number/KF25NU3RAZ5QLSPJIWX3BPBTGS/events.json","paper":"https://pith.science/paper/KF25NU3R"},"agent_actions":{"view_html":"https://pith.science/pith/KF25NU3RAZ5QLSPJIWX3BPBTGS","download_json":"https://pith.science/pith/KF25NU3RAZ5QLSPJIWX3BPBTGS.json","view_paper":"https://pith.science/paper/KF25NU3R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.14660&json=true","fetch_graph":"https://pith.science/api/pith-number/KF25NU3RAZ5QLSPJIWX3BPBTGS/graph.json","fetch_events":"https://pith.science/api/pith-number/KF25NU3RAZ5QLSPJIWX3BPBTGS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KF25NU3RAZ5QLSPJIWX3BPBTGS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KF25NU3RAZ5QLSPJIWX3BPBTGS/action/storage_attestation","attest_author":"https://pith.science/pith/KF25NU3RAZ5QLSPJIWX3BPBTGS/action/author_attestation","sign_citation":"https://pith.science/pith/KF25NU3RAZ5QLSPJIWX3BPBTGS/action/citation_signature","submit_replication":"https://pith.science/pith/KF25NU3RAZ5QLSPJIWX3BPBTGS/action/replication_record"}},"created_at":"2026-07-05T02:24:53.199087+00:00","updated_at":"2026-07-05T02:24:53.199087+00:00"}