{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FLRJUBD5ZPBZYBDODAKUXLKJ2B","short_pith_number":"pith:FLRJUBD5","schema_version":"1.0","canonical_sha256":"2ae29a047dcbc39c046e18154bad49d051ec70b3dfe1d4d4fdc7520710072f08","source":{"kind":"arxiv","id":"2607.18245","version":1},"attestation_state":"computed","paper":{"title":"SAAG: Structured Agent Assessment and Grounding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Amit Sheth, Anvi Kohli, Ritvik Garimella, Vedant Khandelwal","submitted_at":"2026-04-30T19:33:58Z","abstract_excerpt":"Exact-match evaluation of agent-calling obscures qualitatively different failure modes: a model may select the right function yet hallucinate argument values, or satisfy a schema while choosing a agent for the wrong reason. Existing benchmarks collapse these distinctions into a single binary score, leaving practitioners unable to diagnose where agent calls fail. We propose SAAG a cascaded diagnostic framework that decomposes agent-calling evaluation into three sequential stages: registry conformance, structural completeness, and argument grounding, each producing interpretable stage-specific d"},"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":"2607.18245","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-30T19:33:58Z","cross_cats_sorted":[],"title_canon_sha256":"bb8753a0280773e64866bcbeb6fb89609d183c958fb9de9b7ce31e1dd7680f39","abstract_canon_sha256":"03d522acd2d51fa57f7ae7933c0625eb1c0b03f62f83bb9043ca280ca0e14b53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T00:22:38.317766Z","signature_b64":"/O7oUi5auQNFuadgeZpUDcdd8OGJ4p7DcZII4pSGHsL18VxrZ21YIpcaIhjdQ71qHExh++UXuIh7NMRazQ37Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ae29a047dcbc39c046e18154bad49d051ec70b3dfe1d4d4fdc7520710072f08","last_reissued_at":"2026-07-22T00:22:38.316921Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T00:22:38.316921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAAG: Structured Agent Assessment and Grounding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Amit Sheth, Anvi Kohli, Ritvik Garimella, Vedant Khandelwal","submitted_at":"2026-04-30T19:33:58Z","abstract_excerpt":"Exact-match evaluation of agent-calling obscures qualitatively different failure modes: a model may select the right function yet hallucinate argument values, or satisfy a schema while choosing a agent for the wrong reason. Existing benchmarks collapse these distinctions into a single binary score, leaving practitioners unable to diagnose where agent calls fail. We propose SAAG a cascaded diagnostic framework that decomposes agent-calling evaluation into three sequential stages: registry conformance, structural completeness, and argument grounding, each producing interpretable stage-specific d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18245","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/2607.18245/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":"2607.18245","created_at":"2026-07-22T00:22:38.317343+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.18245v1","created_at":"2026-07-22T00:22:38.317343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18245","created_at":"2026-07-22T00:22:38.317343+00:00"},{"alias_kind":"pith_short_12","alias_value":"FLRJUBD5ZPBZ","created_at":"2026-07-22T00:22:38.317343+00:00"},{"alias_kind":"pith_short_16","alias_value":"FLRJUBD5ZPBZYBDO","created_at":"2026-07-22T00:22:38.317343+00:00"},{"alias_kind":"pith_short_8","alias_value":"FLRJUBD5","created_at":"2026-07-22T00:22:38.317343+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/FLRJUBD5ZPBZYBDODAKUXLKJ2B","json":"https://pith.science/pith/FLRJUBD5ZPBZYBDODAKUXLKJ2B.json","graph_json":"https://pith.science/api/pith-number/FLRJUBD5ZPBZYBDODAKUXLKJ2B/graph.json","events_json":"https://pith.science/api/pith-number/FLRJUBD5ZPBZYBDODAKUXLKJ2B/events.json","paper":"https://pith.science/paper/FLRJUBD5"},"agent_actions":{"view_html":"https://pith.science/pith/FLRJUBD5ZPBZYBDODAKUXLKJ2B","download_json":"https://pith.science/pith/FLRJUBD5ZPBZYBDODAKUXLKJ2B.json","view_paper":"https://pith.science/paper/FLRJUBD5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.18245&json=true","fetch_graph":"https://pith.science/api/pith-number/FLRJUBD5ZPBZYBDODAKUXLKJ2B/graph.json","fetch_events":"https://pith.science/api/pith-number/FLRJUBD5ZPBZYBDODAKUXLKJ2B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FLRJUBD5ZPBZYBDODAKUXLKJ2B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FLRJUBD5ZPBZYBDODAKUXLKJ2B/action/storage_attestation","attest_author":"https://pith.science/pith/FLRJUBD5ZPBZYBDODAKUXLKJ2B/action/author_attestation","sign_citation":"https://pith.science/pith/FLRJUBD5ZPBZYBDODAKUXLKJ2B/action/citation_signature","submit_replication":"https://pith.science/pith/FLRJUBD5ZPBZYBDODAKUXLKJ2B/action/replication_record"}},"created_at":"2026-07-22T00:22:38.317343+00:00","updated_at":"2026-07-22T00:22:38.317343+00:00"}