{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7VXXFDZRNYJFIGUB4WQLQFQWRL","short_pith_number":"pith:7VXXFDZR","schema_version":"1.0","canonical_sha256":"fd6f728f316e12541a81e5a0b816168aefbbf8cc50fdfda18fa01968f1b5df89","source":{"kind":"arxiv","id":"2506.05387","version":2},"attestation_state":"computed","paper":{"title":"Advancing Decoding Strategies: Enhancements in Locally Typical Sampling for LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jaydip Sen, Saptarshi Sengupta, Subhasis Dasgupta","submitted_at":"2025-06-03T14:25:23Z","abstract_excerpt":"This chapter explores advancements in decoding strategies for large language models (LLMs), focusing on enhancing the Locally Typical Sampling (LTS) algorithm. Traditional decoding methods, such as top-k and nucleus sampling, often struggle to balance fluency, diversity, and coherence in text generation. To address these challenges, Adaptive Semantic-Aware Typicality Sampling (ASTS) is proposed as an improved version of LTS, incorporating dynamic entropy thresholding, multi-objective scoring, and reward-penalty adjustments. ASTS ensures contextually coherent and diverse text generation while m"},"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":"2506.05387","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T14:25:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2dabdbbc37313e81b31c954eba477fa5b9c9cb0ef5c3b88eb431fb6ecc39f444","abstract_canon_sha256":"5122f611c6f47f441c2414f7aba29e2b926d4f8e829f3797191ebaa171a3caa5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:04:32.835477Z","signature_b64":"iH7hvRFCQXI4T9mKBfGN6jBbOQCCGUBAaSytohNR3BsWO1aZv/PhoSJy83RF+4leh7EXcKSpQ29y90QsnXXDBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd6f728f316e12541a81e5a0b816168aefbbf8cc50fdfda18fa01968f1b5df89","last_reissued_at":"2026-06-02T03:04:32.834948Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:04:32.834948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advancing Decoding Strategies: Enhancements in Locally Typical Sampling for LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jaydip Sen, Saptarshi Sengupta, Subhasis Dasgupta","submitted_at":"2025-06-03T14:25:23Z","abstract_excerpt":"This chapter explores advancements in decoding strategies for large language models (LLMs), focusing on enhancing the Locally Typical Sampling (LTS) algorithm. Traditional decoding methods, such as top-k and nucleus sampling, often struggle to balance fluency, diversity, and coherence in text generation. To address these challenges, Adaptive Semantic-Aware Typicality Sampling (ASTS) is proposed as an improved version of LTS, incorporating dynamic entropy thresholding, multi-objective scoring, and reward-penalty adjustments. ASTS ensures contextually coherent and diverse text generation while m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05387","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/2506.05387/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":"2506.05387","created_at":"2026-06-02T03:04:32.835012+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05387v2","created_at":"2026-06-02T03:04:32.835012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05387","created_at":"2026-06-02T03:04:32.835012+00:00"},{"alias_kind":"pith_short_12","alias_value":"7VXXFDZRNYJF","created_at":"2026-06-02T03:04:32.835012+00:00"},{"alias_kind":"pith_short_16","alias_value":"7VXXFDZRNYJFIGUB","created_at":"2026-06-02T03:04:32.835012+00:00"},{"alias_kind":"pith_short_8","alias_value":"7VXXFDZR","created_at":"2026-06-02T03:04:32.835012+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/7VXXFDZRNYJFIGUB4WQLQFQWRL","json":"https://pith.science/pith/7VXXFDZRNYJFIGUB4WQLQFQWRL.json","graph_json":"https://pith.science/api/pith-number/7VXXFDZRNYJFIGUB4WQLQFQWRL/graph.json","events_json":"https://pith.science/api/pith-number/7VXXFDZRNYJFIGUB4WQLQFQWRL/events.json","paper":"https://pith.science/paper/7VXXFDZR"},"agent_actions":{"view_html":"https://pith.science/pith/7VXXFDZRNYJFIGUB4WQLQFQWRL","download_json":"https://pith.science/pith/7VXXFDZRNYJFIGUB4WQLQFQWRL.json","view_paper":"https://pith.science/paper/7VXXFDZR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05387&json=true","fetch_graph":"https://pith.science/api/pith-number/7VXXFDZRNYJFIGUB4WQLQFQWRL/graph.json","fetch_events":"https://pith.science/api/pith-number/7VXXFDZRNYJFIGUB4WQLQFQWRL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7VXXFDZRNYJFIGUB4WQLQFQWRL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7VXXFDZRNYJFIGUB4WQLQFQWRL/action/storage_attestation","attest_author":"https://pith.science/pith/7VXXFDZRNYJFIGUB4WQLQFQWRL/action/author_attestation","sign_citation":"https://pith.science/pith/7VXXFDZRNYJFIGUB4WQLQFQWRL/action/citation_signature","submit_replication":"https://pith.science/pith/7VXXFDZRNYJFIGUB4WQLQFQWRL/action/replication_record"}},"created_at":"2026-06-02T03:04:32.835012+00:00","updated_at":"2026-06-02T03:04:32.835012+00:00"}