{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WC3CJTLIPWHUPIZ2QT6UT5WL7O","short_pith_number":"pith:WC3CJTLI","schema_version":"1.0","canonical_sha256":"b0b624cd687d8f47a33a84fd49f6cbfb8b94a1ddb390efb45cf0a584263739cb","source":{"kind":"arxiv","id":"2506.11075","version":1},"attestation_state":"computed","paper":{"title":"Fifteen Years of Child-Centered Long-Form Recordings: Promises, Resources, and Remaining Challenges to Validity","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Alejandrina Cristia, Emmanuel Dupoux, Loann Peurey, Lucas Gautheron, Manel Khentout, Marvin Lavechin, Tarek Kunze","submitted_at":"2025-06-04T01:45:42Z","abstract_excerpt":"Audio-recordings collected with a child-worn device are a fundamental tool in child language research. Long-form recordings collected over whole days promise to capture children's input and production with minimal observer bias, and therefore high validity. The sheer volume of resulting data necessitates automated analysis to extract relevant metrics for researchers and clinicians. This paper summarizes collective knowledge on this technique, providing entry points to existing resources. We also highlight various sources of error that threaten the accuracy of automated annotations and the inte"},"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":"2506.11075","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-04T01:45:42Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"0c054de97953703564f376877c84cd0ee9cc6c2459f50f43c3d307e1e9847dbe","abstract_canon_sha256":"a627803287851e509e068fded91ea10f3ebdbec0447eb41ad25dc5c01228a731"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:47.247517Z","signature_b64":"FEtcDEn9zMYfjnhMHYjRLOZX4BPJJk8OkxEC2oiN7R6v2u2QjvPWsWNFPtTShT5+GhEuom9iwLm6r1BofH42Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0b624cd687d8f47a33a84fd49f6cbfb8b94a1ddb390efb45cf0a584263739cb","last_reissued_at":"2026-07-05T12:02:47.246968Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:47.246968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fifteen Years of Child-Centered Long-Form Recordings: Promises, Resources, and Remaining Challenges to Validity","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Alejandrina Cristia, Emmanuel Dupoux, Loann Peurey, Lucas Gautheron, Manel Khentout, Marvin Lavechin, Tarek Kunze","submitted_at":"2025-06-04T01:45:42Z","abstract_excerpt":"Audio-recordings collected with a child-worn device are a fundamental tool in child language research. Long-form recordings collected over whole days promise to capture children's input and production with minimal observer bias, and therefore high validity. The sheer volume of resulting data necessitates automated analysis to extract relevant metrics for researchers and clinicians. This paper summarizes collective knowledge on this technique, providing entry points to existing resources. We also highlight various sources of error that threaten the accuracy of automated annotations and the inte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11075","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/2506.11075/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":"2506.11075","created_at":"2026-07-05T12:02:47.247044+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.11075v1","created_at":"2026-07-05T12:02:47.247044+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11075","created_at":"2026-07-05T12:02:47.247044+00:00"},{"alias_kind":"pith_short_12","alias_value":"WC3CJTLIPWHU","created_at":"2026-07-05T12:02:47.247044+00:00"},{"alias_kind":"pith_short_16","alias_value":"WC3CJTLIPWHUPIZ2","created_at":"2026-07-05T12:02:47.247044+00:00"},{"alias_kind":"pith_short_8","alias_value":"WC3CJTLI","created_at":"2026-07-05T12:02:47.247044+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.11075","citing_title":"Fifteen Years of Child-Centered Long-Form Recordings: Promises, Resources, and Remaining Challenges to Validity","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WC3CJTLIPWHUPIZ2QT6UT5WL7O","json":"https://pith.science/pith/WC3CJTLIPWHUPIZ2QT6UT5WL7O.json","graph_json":"https://pith.science/api/pith-number/WC3CJTLIPWHUPIZ2QT6UT5WL7O/graph.json","events_json":"https://pith.science/api/pith-number/WC3CJTLIPWHUPIZ2QT6UT5WL7O/events.json","paper":"https://pith.science/paper/WC3CJTLI"},"agent_actions":{"view_html":"https://pith.science/pith/WC3CJTLIPWHUPIZ2QT6UT5WL7O","download_json":"https://pith.science/pith/WC3CJTLIPWHUPIZ2QT6UT5WL7O.json","view_paper":"https://pith.science/paper/WC3CJTLI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.11075&json=true","fetch_graph":"https://pith.science/api/pith-number/WC3CJTLIPWHUPIZ2QT6UT5WL7O/graph.json","fetch_events":"https://pith.science/api/pith-number/WC3CJTLIPWHUPIZ2QT6UT5WL7O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WC3CJTLIPWHUPIZ2QT6UT5WL7O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WC3CJTLIPWHUPIZ2QT6UT5WL7O/action/storage_attestation","attest_author":"https://pith.science/pith/WC3CJTLIPWHUPIZ2QT6UT5WL7O/action/author_attestation","sign_citation":"https://pith.science/pith/WC3CJTLIPWHUPIZ2QT6UT5WL7O/action/citation_signature","submit_replication":"https://pith.science/pith/WC3CJTLIPWHUPIZ2QT6UT5WL7O/action/replication_record"}},"created_at":"2026-07-05T12:02:47.247044+00:00","updated_at":"2026-07-05T12:02:47.247044+00:00"}