{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:P3QC2TTYP2KVHJSQ5PPUIAI4YB","short_pith_number":"pith:P3QC2TTY","schema_version":"1.0","canonical_sha256":"7ee02d4e787e9553a650ebdf44011cc07bb9035e91467cf202c6de42e4b2cddd","source":{"kind":"arxiv","id":"2606.20695","version":1},"attestation_state":"computed","paper":{"title":"How Much Coordination Gain Is Real? A Paired Noise-Floor Protocol for Multi-Agent LLM Benchmarks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Alibek T Kaliyev, Artem Maryanskyy","submitted_at":"2026-06-15T07:25:11Z","abstract_excerpt":"Multi-agent LLM coordination papers report small benchmark deltas as evidence that one architecture beats another. A prior question: how much paired trial-0 disagreement do two protocols produce on the same model and benchmark when their API inputs are configuration-equivalent (matched by code inspection plus a SHA-256 byte audit), short of full identity-replay? On Claude Haiku 4.5 against tau^2-bench retail, the clean configuration-equivalent contrast (no_coord vs. intercept, both inert at trial 0) gives signed paired gaps of +10pp and 0pp across two n=100 seeds; pooled across both, +5pp with"},"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":"2606.20695","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2026-06-15T07:25:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f3f4a7c7ec0abe860b83dacc0af5034066fdfe8cfdf669aecae95ac875232871","abstract_canon_sha256":"567cbd18de4fe3f506c3307f9720f86c7dd174791eb9ad8874d0d39ea5049596"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T00:11:53.892386Z","signature_b64":"s5KKsF/sWX540CNs5yChg2aG1m0d3WKM2kOLKNYvVWV+p2LYVHbZM15Xp5gyK6Uu8aJfD+jznFMnr80dH6TdCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ee02d4e787e9553a650ebdf44011cc07bb9035e91467cf202c6de42e4b2cddd","last_reissued_at":"2026-06-23T00:11:53.891941Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T00:11:53.891941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Much Coordination Gain Is Real? A Paired Noise-Floor Protocol for Multi-Agent LLM Benchmarks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Alibek T Kaliyev, Artem Maryanskyy","submitted_at":"2026-06-15T07:25:11Z","abstract_excerpt":"Multi-agent LLM coordination papers report small benchmark deltas as evidence that one architecture beats another. A prior question: how much paired trial-0 disagreement do two protocols produce on the same model and benchmark when their API inputs are configuration-equivalent (matched by code inspection plus a SHA-256 byte audit), short of full identity-replay? On Claude Haiku 4.5 against tau^2-bench retail, the clean configuration-equivalent contrast (no_coord vs. intercept, both inert at trial 0) gives signed paired gaps of +10pp and 0pp across two n=100 seeds; pooled across both, +5pp with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20695","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/2606.20695/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":"2606.20695","created_at":"2026-06-23T00:11:53.892015+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20695v1","created_at":"2026-06-23T00:11:53.892015+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20695","created_at":"2026-06-23T00:11:53.892015+00:00"},{"alias_kind":"pith_short_12","alias_value":"P3QC2TTYP2KV","created_at":"2026-06-23T00:11:53.892015+00:00"},{"alias_kind":"pith_short_16","alias_value":"P3QC2TTYP2KVHJSQ","created_at":"2026-06-23T00:11:53.892015+00:00"},{"alias_kind":"pith_short_8","alias_value":"P3QC2TTY","created_at":"2026-06-23T00:11:53.892015+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/P3QC2TTYP2KVHJSQ5PPUIAI4YB","json":"https://pith.science/pith/P3QC2TTYP2KVHJSQ5PPUIAI4YB.json","graph_json":"https://pith.science/api/pith-number/P3QC2TTYP2KVHJSQ5PPUIAI4YB/graph.json","events_json":"https://pith.science/api/pith-number/P3QC2TTYP2KVHJSQ5PPUIAI4YB/events.json","paper":"https://pith.science/paper/P3QC2TTY"},"agent_actions":{"view_html":"https://pith.science/pith/P3QC2TTYP2KVHJSQ5PPUIAI4YB","download_json":"https://pith.science/pith/P3QC2TTYP2KVHJSQ5PPUIAI4YB.json","view_paper":"https://pith.science/paper/P3QC2TTY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20695&json=true","fetch_graph":"https://pith.science/api/pith-number/P3QC2TTYP2KVHJSQ5PPUIAI4YB/graph.json","fetch_events":"https://pith.science/api/pith-number/P3QC2TTYP2KVHJSQ5PPUIAI4YB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P3QC2TTYP2KVHJSQ5PPUIAI4YB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P3QC2TTYP2KVHJSQ5PPUIAI4YB/action/storage_attestation","attest_author":"https://pith.science/pith/P3QC2TTYP2KVHJSQ5PPUIAI4YB/action/author_attestation","sign_citation":"https://pith.science/pith/P3QC2TTYP2KVHJSQ5PPUIAI4YB/action/citation_signature","submit_replication":"https://pith.science/pith/P3QC2TTYP2KVHJSQ5PPUIAI4YB/action/replication_record"}},"created_at":"2026-06-23T00:11:53.892015+00:00","updated_at":"2026-06-23T00:11:53.892015+00:00"}