{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MZGYOO24JZD7ID7PAFIZZFMVLZ","short_pith_number":"pith:MZGYOO24","schema_version":"1.0","canonical_sha256":"664d873b5c4e47f40fef01519c95955e71298e9266a493a644fc97fe56ce281e","source":{"kind":"arxiv","id":"2504.20946","version":2},"attestation_state":"computed","paper":{"title":"Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ali Emami, Tyler McDonald","submitted_at":"2025-04-29T17:14:54Z","abstract_excerpt":"Knowledge distillation allows smaller neural networks to emulate the performance of larger, teacher models with reduced computational demands. Traditional methods for Large Language Models (LLMs) often necessitate extensive fine-tuning, which limits their accessibility. To address this, we introduce Trace-of-Thought Prompting, a novel framework designed to distill critical reasoning capabilities from high-resource teacher models (over 8 billion parameters) to low-resource student models (up to 8 billion parameters). This approach leverages problem decomposition to enhance interpretability and "},"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":"2504.20946","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-29T17:14:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2ea2f8dd202b4f10eb7805310b5cceae3960809ae240885c058a4df81c170e5e","abstract_canon_sha256":"0ab4d94046efa86b01a544d444f68a14c821c1a0f2d8028cf40a1d2400c7f34b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:39.904214Z","signature_b64":"B5tdeiCH+kWLGkreDlElPQT/Ff6A3BxmB2X94REOQ1/CeB7NmAaPxbmULEPQfcCF3vmtLshqNeXTyOt4sXKEBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"664d873b5c4e47f40fef01519c95955e71298e9266a493a644fc97fe56ce281e","last_reissued_at":"2026-07-05T10:56:39.903838Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:39.903838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ali Emami, Tyler McDonald","submitted_at":"2025-04-29T17:14:54Z","abstract_excerpt":"Knowledge distillation allows smaller neural networks to emulate the performance of larger, teacher models with reduced computational demands. Traditional methods for Large Language Models (LLMs) often necessitate extensive fine-tuning, which limits their accessibility. To address this, we introduce Trace-of-Thought Prompting, a novel framework designed to distill critical reasoning capabilities from high-resource teacher models (over 8 billion parameters) to low-resource student models (up to 8 billion parameters). This approach leverages problem decomposition to enhance interpretability and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20946","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/2504.20946/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":"2504.20946","created_at":"2026-07-05T10:56:39.903889+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.20946v2","created_at":"2026-07-05T10:56:39.903889+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20946","created_at":"2026-07-05T10:56:39.903889+00:00"},{"alias_kind":"pith_short_12","alias_value":"MZGYOO24JZD7","created_at":"2026-07-05T10:56:39.903889+00:00"},{"alias_kind":"pith_short_16","alias_value":"MZGYOO24JZD7ID7P","created_at":"2026-07-05T10:56:39.903889+00:00"},{"alias_kind":"pith_short_8","alias_value":"MZGYOO24","created_at":"2026-07-05T10:56:39.903889+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/MZGYOO24JZD7ID7PAFIZZFMVLZ","json":"https://pith.science/pith/MZGYOO24JZD7ID7PAFIZZFMVLZ.json","graph_json":"https://pith.science/api/pith-number/MZGYOO24JZD7ID7PAFIZZFMVLZ/graph.json","events_json":"https://pith.science/api/pith-number/MZGYOO24JZD7ID7PAFIZZFMVLZ/events.json","paper":"https://pith.science/paper/MZGYOO24"},"agent_actions":{"view_html":"https://pith.science/pith/MZGYOO24JZD7ID7PAFIZZFMVLZ","download_json":"https://pith.science/pith/MZGYOO24JZD7ID7PAFIZZFMVLZ.json","view_paper":"https://pith.science/paper/MZGYOO24","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.20946&json=true","fetch_graph":"https://pith.science/api/pith-number/MZGYOO24JZD7ID7PAFIZZFMVLZ/graph.json","fetch_events":"https://pith.science/api/pith-number/MZGYOO24JZD7ID7PAFIZZFMVLZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MZGYOO24JZD7ID7PAFIZZFMVLZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MZGYOO24JZD7ID7PAFIZZFMVLZ/action/storage_attestation","attest_author":"https://pith.science/pith/MZGYOO24JZD7ID7PAFIZZFMVLZ/action/author_attestation","sign_citation":"https://pith.science/pith/MZGYOO24JZD7ID7PAFIZZFMVLZ/action/citation_signature","submit_replication":"https://pith.science/pith/MZGYOO24JZD7ID7PAFIZZFMVLZ/action/replication_record"}},"created_at":"2026-07-05T10:56:39.903889+00:00","updated_at":"2026-07-05T10:56:39.903889+00:00"}