{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YGKTUBGVFRIPCQJN3VSFNOWVOM","short_pith_number":"pith:YGKTUBGV","schema_version":"1.0","canonical_sha256":"c1953a04d52c50f1412ddd6456bad57310ca8a329f72570432a4f0268e2a610d","source":{"kind":"arxiv","id":"2605.28787","version":1},"attestation_state":"computed","paper":{"title":"Do Agents Need Semantic Metadata? A Comparative Study in Agentic Data Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Alon Halevy, Natasha Noy, Shiyu Chen, Tarfah Alrashed","submitted_at":"2026-05-27T17:46:43Z","abstract_excerpt":"In the era of autonomous agents, machine-actionable data is critical for data-driven workflows. For more than a decade, semantic metadata like schema.org has anchored the FAIR principles (Findable, Accessible, Interoperable, and Reusable) for machine-actionable data and enabled discovery tools like Google Dataset Search. However, the rise of Large Language Models (LLMs) capable of navigating the unstructured web raises a fundamental question: Is semantic metadata still necessary for agentic data discovery, or can agents reliably retrieve actionable data directly from the web? We present a comp"},"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":"2605.28787","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-27T17:46:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2b22067172a8990ad9b80c23cb65cb943691c342022611c0e2113fb8a7ce42d4","abstract_canon_sha256":"7118e2bf60c7439139f54ed44fe5a881f124a0fd6c422fabb40491332400e926"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:05:03.609502Z","signature_b64":"EtcjGwsWCf1OhMJRUQkuZAWcCr7WQB2QterbVshE/xFeLmK35VV6cwnW/NAJqY9gvkO9SkCOwFWzggm503JPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1953a04d52c50f1412ddd6456bad57310ca8a329f72570432a4f0268e2a610d","last_reissued_at":"2026-05-28T02:05:03.608963Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:05:03.608963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do Agents Need Semantic Metadata? A Comparative Study in Agentic Data Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Alon Halevy, Natasha Noy, Shiyu Chen, Tarfah Alrashed","submitted_at":"2026-05-27T17:46:43Z","abstract_excerpt":"In the era of autonomous agents, machine-actionable data is critical for data-driven workflows. For more than a decade, semantic metadata like schema.org has anchored the FAIR principles (Findable, Accessible, Interoperable, and Reusable) for machine-actionable data and enabled discovery tools like Google Dataset Search. However, the rise of Large Language Models (LLMs) capable of navigating the unstructured web raises a fundamental question: Is semantic metadata still necessary for agentic data discovery, or can agents reliably retrieve actionable data directly from the web? We present a comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28787","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/2605.28787/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":"2605.28787","created_at":"2026-05-28T02:05:03.609021+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28787v1","created_at":"2026-05-28T02:05:03.609021+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28787","created_at":"2026-05-28T02:05:03.609021+00:00"},{"alias_kind":"pith_short_12","alias_value":"YGKTUBGVFRIP","created_at":"2026-05-28T02:05:03.609021+00:00"},{"alias_kind":"pith_short_16","alias_value":"YGKTUBGVFRIPCQJN","created_at":"2026-05-28T02:05:03.609021+00:00"},{"alias_kind":"pith_short_8","alias_value":"YGKTUBGV","created_at":"2026-05-28T02:05:03.609021+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/YGKTUBGVFRIPCQJN3VSFNOWVOM","json":"https://pith.science/pith/YGKTUBGVFRIPCQJN3VSFNOWVOM.json","graph_json":"https://pith.science/api/pith-number/YGKTUBGVFRIPCQJN3VSFNOWVOM/graph.json","events_json":"https://pith.science/api/pith-number/YGKTUBGVFRIPCQJN3VSFNOWVOM/events.json","paper":"https://pith.science/paper/YGKTUBGV"},"agent_actions":{"view_html":"https://pith.science/pith/YGKTUBGVFRIPCQJN3VSFNOWVOM","download_json":"https://pith.science/pith/YGKTUBGVFRIPCQJN3VSFNOWVOM.json","view_paper":"https://pith.science/paper/YGKTUBGV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28787&json=true","fetch_graph":"https://pith.science/api/pith-number/YGKTUBGVFRIPCQJN3VSFNOWVOM/graph.json","fetch_events":"https://pith.science/api/pith-number/YGKTUBGVFRIPCQJN3VSFNOWVOM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YGKTUBGVFRIPCQJN3VSFNOWVOM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YGKTUBGVFRIPCQJN3VSFNOWVOM/action/storage_attestation","attest_author":"https://pith.science/pith/YGKTUBGVFRIPCQJN3VSFNOWVOM/action/author_attestation","sign_citation":"https://pith.science/pith/YGKTUBGVFRIPCQJN3VSFNOWVOM/action/citation_signature","submit_replication":"https://pith.science/pith/YGKTUBGVFRIPCQJN3VSFNOWVOM/action/replication_record"}},"created_at":"2026-05-28T02:05:03.609021+00:00","updated_at":"2026-05-28T02:05:03.609021+00:00"}