{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OG5P4MK3K2HWYRD7NOJKL4ZRGO","short_pith_number":"pith:OG5P4MK3","schema_version":"1.0","canonical_sha256":"71bafe315b568f6c447f6b92a5f3313398cce1f8d1c5aa6414d52e7a7edf1f35","source":{"kind":"arxiv","id":"2506.05017","version":1},"attestation_state":"computed","paper":{"title":"Controlling Summarization Length Through EOS Token Weighting","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Emmanouil Stergiadis, Eran Fainman, Ilya Gusev, Zeno Belligoli","submitted_at":"2025-06-05T13:25:28Z","abstract_excerpt":"Controlling the length of generated text can be crucial in various text-generation tasks, including summarization. Existing methods often require complex model alterations, limiting compatibility with pre-trained models. We address these limitations by developing a simple approach for controlling the length of automatic text summaries by increasing the importance of correctly predicting the EOS token in the cross-entropy loss computation. The proposed methodology is agnostic to architecture and decoding algorithms and orthogonal to other inference-time techniques to control the generation leng"},"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":"2506.05017","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T13:25:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9bba810e11a4c742d7e43eb3babdb4915a47add0320e71372f24758c0ba0e1e3","abstract_canon_sha256":"3c08aeb2888aaafcdaefa49e5d165012cb84ba2ec2385f6508897b18f44de8b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:41.026898Z","signature_b64":"wekQcarXkmijklWu1o++eTaiNPGJqFgz8Q+hL7PENRk1l1krD5qllE9AN9JuTOYAvwFzxx3ay5MJG7jS88kyAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71bafe315b568f6c447f6b92a5f3313398cce1f8d1c5aa6414d52e7a7edf1f35","last_reissued_at":"2026-07-05T11:16:41.026361Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:41.026361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Controlling Summarization Length Through EOS Token Weighting","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Emmanouil Stergiadis, Eran Fainman, Ilya Gusev, Zeno Belligoli","submitted_at":"2025-06-05T13:25:28Z","abstract_excerpt":"Controlling the length of generated text can be crucial in various text-generation tasks, including summarization. Existing methods often require complex model alterations, limiting compatibility with pre-trained models. We address these limitations by developing a simple approach for controlling the length of automatic text summaries by increasing the importance of correctly predicting the EOS token in the cross-entropy loss computation. The proposed methodology is agnostic to architecture and decoding algorithms and orthogonal to other inference-time techniques to control the generation leng"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05017","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/2506.05017/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":"2506.05017","created_at":"2026-07-05T11:16:41.026429+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05017v1","created_at":"2026-07-05T11:16:41.026429+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05017","created_at":"2026-07-05T11:16:41.026429+00:00"},{"alias_kind":"pith_short_12","alias_value":"OG5P4MK3K2HW","created_at":"2026-07-05T11:16:41.026429+00:00"},{"alias_kind":"pith_short_16","alias_value":"OG5P4MK3K2HWYRD7","created_at":"2026-07-05T11:16:41.026429+00:00"},{"alias_kind":"pith_short_8","alias_value":"OG5P4MK3","created_at":"2026-07-05T11:16:41.026429+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.22267","citing_title":"TiCo: Time-Controllable Spoken Dialogue Model","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OG5P4MK3K2HWYRD7NOJKL4ZRGO","json":"https://pith.science/pith/OG5P4MK3K2HWYRD7NOJKL4ZRGO.json","graph_json":"https://pith.science/api/pith-number/OG5P4MK3K2HWYRD7NOJKL4ZRGO/graph.json","events_json":"https://pith.science/api/pith-number/OG5P4MK3K2HWYRD7NOJKL4ZRGO/events.json","paper":"https://pith.science/paper/OG5P4MK3"},"agent_actions":{"view_html":"https://pith.science/pith/OG5P4MK3K2HWYRD7NOJKL4ZRGO","download_json":"https://pith.science/pith/OG5P4MK3K2HWYRD7NOJKL4ZRGO.json","view_paper":"https://pith.science/paper/OG5P4MK3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05017&json=true","fetch_graph":"https://pith.science/api/pith-number/OG5P4MK3K2HWYRD7NOJKL4ZRGO/graph.json","fetch_events":"https://pith.science/api/pith-number/OG5P4MK3K2HWYRD7NOJKL4ZRGO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OG5P4MK3K2HWYRD7NOJKL4ZRGO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OG5P4MK3K2HWYRD7NOJKL4ZRGO/action/storage_attestation","attest_author":"https://pith.science/pith/OG5P4MK3K2HWYRD7NOJKL4ZRGO/action/author_attestation","sign_citation":"https://pith.science/pith/OG5P4MK3K2HWYRD7NOJKL4ZRGO/action/citation_signature","submit_replication":"https://pith.science/pith/OG5P4MK3K2HWYRD7NOJKL4ZRGO/action/replication_record"}},"created_at":"2026-07-05T11:16:41.026429+00:00","updated_at":"2026-07-05T11:16:41.026429+00:00"}