{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:A4ZHRZUVMVMPULQ3SZYR363MFO","short_pith_number":"pith:A4ZHRZUV","schema_version":"1.0","canonical_sha256":"073278e6956558fa2e1b96711dfb6c2bbdf77f628e36d2cac2d73faa8bd06474","source":{"kind":"arxiv","id":"2409.19877","version":1},"attestation_state":"computed","paper":{"title":"Contrastive Token Learning with Similarity Decay for Repetition Suppression in Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ben Chen, Huangyu Dai, Kaidi Chen, Wen Jiang, Ying Han, Zihan Liang","submitted_at":"2024-09-30T02:21:39Z","abstract_excerpt":"For crosslingual conversation and trade, Neural Machine Translation (NMT) is pivotal yet faces persistent challenges with monotony and repetition in generated content. Traditional solutions that rely on penalizing text redundancy or token reoccurrence have shown limited efficacy, particularly for lengthy article and e-commerce descriptions with inherent redundancy, even with the advent of Large Language Models (LLMs). This paper investigates the underlying causes of textual repetition through the lens of information entropy, attributing the phenomenon to the elevated uncertainty within the inp"},"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":"2409.19877","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-30T02:21:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e5a2d584fd78a62a574eaff914089fef1b9d880678277c910f4e43d1835a9515","abstract_canon_sha256":"beeb6113fd65a2ceec3e8137fb42fa70c723b9a1cea8d8f1fa244eb8e1e95737"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:24.225142Z","signature_b64":"+s4cnXAHyxpXEMsjipeAf+YSZTU+xkVpvcJQo8ZaBa8gscF4h7/O9HCIVojXFvQEHvprwAiUXk04fJQTQ8TtAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"073278e6956558fa2e1b96711dfb6c2bbdf77f628e36d2cac2d73faa8bd06474","last_reissued_at":"2026-07-05T09:13:24.224635Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:24.224635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Token Learning with Similarity Decay for Repetition Suppression in Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ben Chen, Huangyu Dai, Kaidi Chen, Wen Jiang, Ying Han, Zihan Liang","submitted_at":"2024-09-30T02:21:39Z","abstract_excerpt":"For crosslingual conversation and trade, Neural Machine Translation (NMT) is pivotal yet faces persistent challenges with monotony and repetition in generated content. Traditional solutions that rely on penalizing text redundancy or token reoccurrence have shown limited efficacy, particularly for lengthy article and e-commerce descriptions with inherent redundancy, even with the advent of Large Language Models (LLMs). This paper investigates the underlying causes of textual repetition through the lens of information entropy, attributing the phenomenon to the elevated uncertainty within the inp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19877","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/2409.19877/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":"2409.19877","created_at":"2026-07-05T09:13:24.224695+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.19877v1","created_at":"2026-07-05T09:13:24.224695+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19877","created_at":"2026-07-05T09:13:24.224695+00:00"},{"alias_kind":"pith_short_12","alias_value":"A4ZHRZUVMVMP","created_at":"2026-07-05T09:13:24.224695+00:00"},{"alias_kind":"pith_short_16","alias_value":"A4ZHRZUVMVMPULQ3","created_at":"2026-07-05T09:13:24.224695+00:00"},{"alias_kind":"pith_short_8","alias_value":"A4ZHRZUV","created_at":"2026-07-05T09:13:24.224695+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/A4ZHRZUVMVMPULQ3SZYR363MFO","json":"https://pith.science/pith/A4ZHRZUVMVMPULQ3SZYR363MFO.json","graph_json":"https://pith.science/api/pith-number/A4ZHRZUVMVMPULQ3SZYR363MFO/graph.json","events_json":"https://pith.science/api/pith-number/A4ZHRZUVMVMPULQ3SZYR363MFO/events.json","paper":"https://pith.science/paper/A4ZHRZUV"},"agent_actions":{"view_html":"https://pith.science/pith/A4ZHRZUVMVMPULQ3SZYR363MFO","download_json":"https://pith.science/pith/A4ZHRZUVMVMPULQ3SZYR363MFO.json","view_paper":"https://pith.science/paper/A4ZHRZUV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.19877&json=true","fetch_graph":"https://pith.science/api/pith-number/A4ZHRZUVMVMPULQ3SZYR363MFO/graph.json","fetch_events":"https://pith.science/api/pith-number/A4ZHRZUVMVMPULQ3SZYR363MFO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A4ZHRZUVMVMPULQ3SZYR363MFO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A4ZHRZUVMVMPULQ3SZYR363MFO/action/storage_attestation","attest_author":"https://pith.science/pith/A4ZHRZUVMVMPULQ3SZYR363MFO/action/author_attestation","sign_citation":"https://pith.science/pith/A4ZHRZUVMVMPULQ3SZYR363MFO/action/citation_signature","submit_replication":"https://pith.science/pith/A4ZHRZUVMVMPULQ3SZYR363MFO/action/replication_record"}},"created_at":"2026-07-05T09:13:24.224695+00:00","updated_at":"2026-07-05T09:13:24.224695+00:00"}