{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TD2PDXL326HKCOWFNIUG25NXHK","short_pith_number":"pith:TD2PDXL3","schema_version":"1.0","canonical_sha256":"98f4f1dd7bd78ea13ac56a286d75b73aa6534d69078b97915a40e7cf3c85f6d4","source":{"kind":"arxiv","id":"2605.11154","version":2},"attestation_state":"computed","paper":{"title":"Quantifying the Reconstructability of Astrophysical Methods with Large Language Models and Information Theory: A Case Study in Spectral Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Increasing text clarifies astrophysical method structure but leaves an entropy floor of implementation variance.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"astro-ph.IM","authors_text":"Hsing Wen Lin, Zong-Fu Sie","submitted_at":"2026-05-11T19:00:09Z","abstract_excerpt":"Modern astrophysical studies rely heavily on complex data analysis pipelines; however, published descriptions often lack the detail required for computational reproducibility. In this work, we present an information-theoretic framework to quantify how effectively a method can be reconstructed from its written description. By treating algorithmic reconstruction as a probability distribution generated by Large Language Models (LLMs), we utilize Shannon entropy and Jensen-Shannon divergence to measure how strongly text constrains the hypothesis space of valid implementations. We demonstrate this "},"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":"2605.11154","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"astro-ph.IM","submitted_at":"2026-05-11T19:00:09Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9b48669a9bc0249554fc5aea0c5cd62c907658683247fee0966625212cd7cbe3","abstract_canon_sha256":"c1fa4ea6bcf7e53d840ac824c931659c89cb861376c0ab1af5faa397aa904a4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:04:49.346413Z","signature_b64":"Ca3elvdj3e/ioXrrQQSjNcbaHQ78XcWNfhhpm0sKiJvVeh3kKHSfJCqHs0+OkMGd0FCdWXKbfdYuwVGrsC1VAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98f4f1dd7bd78ea13ac56a286d75b73aa6534d69078b97915a40e7cf3c85f6d4","last_reissued_at":"2026-05-28T02:04:49.345891Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:04:49.345891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantifying the Reconstructability of Astrophysical Methods with Large Language Models and Information Theory: A Case Study in Spectral Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Increasing text clarifies astrophysical method structure but leaves an entropy floor of implementation variance.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"astro-ph.IM","authors_text":"Hsing Wen Lin, Zong-Fu Sie","submitted_at":"2026-05-11T19:00:09Z","abstract_excerpt":"Modern astrophysical studies rely heavily on complex data analysis pipelines; however, published descriptions often lack the detail required for computational reproducibility. In this work, we present an information-theoretic framework to quantify how effectively a method can be reconstructed from its written description. By treating algorithmic reconstruction as a probability distribution generated by Large Language Models (LLMs), we utilize Shannon entropy and Jensen-Shannon divergence to measure how strongly text constrains the hypothesis space of valid implementations. We demonstrate this "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"while increasing text successfully clarifies the overall algorithmic structure, it fails to eliminate variance at the implementation level. This persistent variance establishes an 'entropy floor,' demonstrating that multiple divergent implementations remain consistent with explicit instructions.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That LLM-generated distributions accurately sample the space of valid implementations and that remaining variance after detailed text is caused by missing tacit knowledge in the description rather than limitations of the models or prompting.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LLMs prompted with increasing levels of text on TNO spectral reconstruction from photometry reveal an entropy floor where implementation variance persists, showing text alone cannot capture all tacit expert knowledge needed for exact replication.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Increasing text clarifies astrophysical method structure but leaves an entropy floor of implementation variance.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"69a2c83717a71c6500f082026f6a615e4953b04f7e647cde80439fd428e95fb7"},"source":{"id":"2605.11154","kind":"arxiv","version":2},"verdict":{"id":"57b58581-4157-4895-abc3-c9840be56c5a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T00:45:12.349821Z","strongest_claim":"while increasing text successfully clarifies the overall algorithmic structure, it fails to eliminate variance at the implementation level. This persistent variance establishes an 'entropy floor,' demonstrating that multiple divergent implementations remain consistent with explicit instructions.","one_line_summary":"LLMs prompted with increasing levels of text on TNO spectral reconstruction from photometry reveal an entropy floor where implementation variance persists, showing text alone cannot capture all tacit expert knowledge needed for exact replication.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That LLM-generated distributions accurately sample the space of valid implementations and that remaining variance after detailed text is caused by missing tacit knowledge in the description rather than limitations of the models or prompting.","pith_extraction_headline":"Increasing text clarifies astrophysical method structure but leaves an entropy floor of implementation variance."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.11154/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T05:02:00.597553Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:34:22.369012Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T10:31:16.640154Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T08:44:38.707620Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"9d5b69ecc280d5679c4c4191294ecea11acf6e061663f3ab106762bcc1590ed6"},"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":"2605.11154","created_at":"2026-05-28T02:04:49.345973+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.11154v2","created_at":"2026-05-28T02:04:49.345973+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.11154","created_at":"2026-05-28T02:04:49.345973+00:00"},{"alias_kind":"pith_short_12","alias_value":"TD2PDXL326HK","created_at":"2026-05-28T02:04:49.345973+00:00"},{"alias_kind":"pith_short_16","alias_value":"TD2PDXL326HKCOWF","created_at":"2026-05-28T02:04:49.345973+00:00"},{"alias_kind":"pith_short_8","alias_value":"TD2PDXL3","created_at":"2026-05-28T02:04:49.345973+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/TD2PDXL326HKCOWFNIUG25NXHK","json":"https://pith.science/pith/TD2PDXL326HKCOWFNIUG25NXHK.json","graph_json":"https://pith.science/api/pith-number/TD2PDXL326HKCOWFNIUG25NXHK/graph.json","events_json":"https://pith.science/api/pith-number/TD2PDXL326HKCOWFNIUG25NXHK/events.json","paper":"https://pith.science/paper/TD2PDXL3"},"agent_actions":{"view_html":"https://pith.science/pith/TD2PDXL326HKCOWFNIUG25NXHK","download_json":"https://pith.science/pith/TD2PDXL326HKCOWFNIUG25NXHK.json","view_paper":"https://pith.science/paper/TD2PDXL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.11154&json=true","fetch_graph":"https://pith.science/api/pith-number/TD2PDXL326HKCOWFNIUG25NXHK/graph.json","fetch_events":"https://pith.science/api/pith-number/TD2PDXL326HKCOWFNIUG25NXHK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TD2PDXL326HKCOWFNIUG25NXHK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TD2PDXL326HKCOWFNIUG25NXHK/action/storage_attestation","attest_author":"https://pith.science/pith/TD2PDXL326HKCOWFNIUG25NXHK/action/author_attestation","sign_citation":"https://pith.science/pith/TD2PDXL326HKCOWFNIUG25NXHK/action/citation_signature","submit_replication":"https://pith.science/pith/TD2PDXL326HKCOWFNIUG25NXHK/action/replication_record"}},"created_at":"2026-05-28T02:04:49.345973+00:00","updated_at":"2026-05-28T02:04:49.345973+00:00"}