{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZAKOCFIEVN2QTVDESDHEENBLVV","short_pith_number":"pith:ZAKOCFIE","canonical_record":{"source":{"id":"2411.09587","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-14T16:57:46Z","cross_cats_sorted":[],"title_canon_sha256":"61aa2182b1824070f9b5de23ee5f0ab210d0f0e19656841d796bf7961a75b461","abstract_canon_sha256":"6ce307e4aea9638a5fe0805e1b43e4044518c714eb5d3a8c7efc14b89227b710"},"schema_version":"1.0"},"canonical_sha256":"c814e11504ab7509d46490ce42342bad509b9cdcd369015ae009f6f9dbe7c2a5","source":{"kind":"arxiv","id":"2411.09587","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.09587","created_at":"2026-07-05T10:34:41Z"},{"alias_kind":"arxiv_version","alias_value":"2411.09587v2","created_at":"2026-07-05T10:34:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09587","created_at":"2026-07-05T10:34:41Z"},{"alias_kind":"pith_short_12","alias_value":"ZAKOCFIEVN2Q","created_at":"2026-07-05T10:34:41Z"},{"alias_kind":"pith_short_16","alias_value":"ZAKOCFIEVN2QTVDE","created_at":"2026-07-05T10:34:41Z"},{"alias_kind":"pith_short_8","alias_value":"ZAKOCFIE","created_at":"2026-07-05T10:34:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZAKOCFIEVN2QTVDESDHEENBLVV","target":"record","payload":{"canonical_record":{"source":{"id":"2411.09587","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-14T16:57:46Z","cross_cats_sorted":[],"title_canon_sha256":"61aa2182b1824070f9b5de23ee5f0ab210d0f0e19656841d796bf7961a75b461","abstract_canon_sha256":"6ce307e4aea9638a5fe0805e1b43e4044518c714eb5d3a8c7efc14b89227b710"},"schema_version":"1.0"},"canonical_sha256":"c814e11504ab7509d46490ce42342bad509b9cdcd369015ae009f6f9dbe7c2a5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:41.174607Z","signature_b64":"TPDNy4k3U8QU13EtolrjbK+OBeI9in8qIr0kZ9N2KPr28z6iTPFwMMhJ073ZYIxLB+d+YdYcaIEI1oHwaTZqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c814e11504ab7509d46490ce42342bad509b9cdcd369015ae009f6f9dbe7c2a5","last_reissued_at":"2026-07-05T10:34:41.173813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:41.173813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.09587","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:34:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"74or2WH89u32AGhjFybE4m2OcEWbyM8X3CNrO7IVKoUschsS2GYE6EKMmR8G0RiyIQAUAxObc9eThw7L/xWXBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T00:21:06.061035Z"},"content_sha256":"1885bc50c31685a30df793fe9ae6fc544f7bd2488c5167ba1b8a870d89c708c6","schema_version":"1.0","event_id":"sha256:1885bc50c31685a30df793fe9ae6fc544f7bd2488c5167ba1b8a870d89c708c6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZAKOCFIEVN2QTVDESDHEENBLVV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BabyLM Challenge: Exploring the Effect of Variation Sets on Language Model Training Efficiency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akari Haga, Akiyo Fukatsu, Arianna Bisazza, Miyu Oba, Yohei Oseki","submitted_at":"2024-11-14T16:57:46Z","abstract_excerpt":"While current large language models have achieved a remarkable success, their data efficiency remains a challenge to overcome. Recently it has been suggested that child-directed speech (CDS) can improve training data efficiency of modern language models based on Transformer neural networks. However, it is not yet understood which specific properties of CDS are effective for training these models. In the context of the BabyLM Challenge, we focus on Variation Sets (VSs), sets of consecutive utterances expressing a similar intent with slightly different words and structures, which are ubiquitous "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09587","kind":"arxiv","version":2},"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/2411.09587/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:34:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GRNZrfvlLt7yXm/12clao+QEmC7Un1N8Oc508OrZdgDYIbeUr+QGVci6uhVHQb9OBTjLXfkeo/UfMw3O3KUcBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T00:21:06.061776Z"},"content_sha256":"9c0134cccc63f7d19db4d7a9d29a06c1b694cc79e76058d6b4d805d35ad8bb09","schema_version":"1.0","event_id":"sha256:9c0134cccc63f7d19db4d7a9d29a06c1b694cc79e76058d6b4d805d35ad8bb09"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZAKOCFIEVN2QTVDESDHEENBLVV/bundle.json","state_url":"https://pith.science/pith/ZAKOCFIEVN2QTVDESDHEENBLVV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZAKOCFIEVN2QTVDESDHEENBLVV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-15T00:21:06Z","links":{"resolver":"https://pith.science/pith/ZAKOCFIEVN2QTVDESDHEENBLVV","bundle":"https://pith.science/pith/ZAKOCFIEVN2QTVDESDHEENBLVV/bundle.json","state":"https://pith.science/pith/ZAKOCFIEVN2QTVDESDHEENBLVV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZAKOCFIEVN2QTVDESDHEENBLVV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZAKOCFIEVN2QTVDESDHEENBLVV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6ce307e4aea9638a5fe0805e1b43e4044518c714eb5d3a8c7efc14b89227b710","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-14T16:57:46Z","title_canon_sha256":"61aa2182b1824070f9b5de23ee5f0ab210d0f0e19656841d796bf7961a75b461"},"schema_version":"1.0","source":{"id":"2411.09587","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.09587","created_at":"2026-07-05T10:34:41Z"},{"alias_kind":"arxiv_version","alias_value":"2411.09587v2","created_at":"2026-07-05T10:34:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09587","created_at":"2026-07-05T10:34:41Z"},{"alias_kind":"pith_short_12","alias_value":"ZAKOCFIEVN2Q","created_at":"2026-07-05T10:34:41Z"},{"alias_kind":"pith_short_16","alias_value":"ZAKOCFIEVN2QTVDE","created_at":"2026-07-05T10:34:41Z"},{"alias_kind":"pith_short_8","alias_value":"ZAKOCFIE","created_at":"2026-07-05T10:34:41Z"}],"graph_snapshots":[{"event_id":"sha256:9c0134cccc63f7d19db4d7a9d29a06c1b694cc79e76058d6b4d805d35ad8bb09","target":"graph","created_at":"2026-07-05T10:34:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.09587/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While current large language models have achieved a remarkable success, their data efficiency remains a challenge to overcome. Recently it has been suggested that child-directed speech (CDS) can improve training data efficiency of modern language models based on Transformer neural networks. However, it is not yet understood which specific properties of CDS are effective for training these models. In the context of the BabyLM Challenge, we focus on Variation Sets (VSs), sets of consecutive utterances expressing a similar intent with slightly different words and structures, which are ubiquitous ","authors_text":"Akari Haga, Akiyo Fukatsu, Arianna Bisazza, Miyu Oba, Yohei Oseki","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-14T16:57:46Z","title":"BabyLM Challenge: Exploring the Effect of Variation Sets on Language Model Training Efficiency"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09587","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1885bc50c31685a30df793fe9ae6fc544f7bd2488c5167ba1b8a870d89c708c6","target":"record","created_at":"2026-07-05T10:34:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6ce307e4aea9638a5fe0805e1b43e4044518c714eb5d3a8c7efc14b89227b710","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-14T16:57:46Z","title_canon_sha256":"61aa2182b1824070f9b5de23ee5f0ab210d0f0e19656841d796bf7961a75b461"},"schema_version":"1.0","source":{"id":"2411.09587","kind":"arxiv","version":2}},"canonical_sha256":"c814e11504ab7509d46490ce42342bad509b9cdcd369015ae009f6f9dbe7c2a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c814e11504ab7509d46490ce42342bad509b9cdcd369015ae009f6f9dbe7c2a5","first_computed_at":"2026-07-05T10:34:41.173813Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:34:41.173813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TPDNy4k3U8QU13EtolrjbK+OBeI9in8qIr0kZ9N2KPr28z6iTPFwMMhJ073ZYIxLB+d+YdYcaIEI1oHwaTZqCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:34:41.174607Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.09587","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1885bc50c31685a30df793fe9ae6fc544f7bd2488c5167ba1b8a870d89c708c6","sha256:9c0134cccc63f7d19db4d7a9d29a06c1b694cc79e76058d6b4d805d35ad8bb09"],"state_sha256":"5b434c9e7006586e06dd8c13f7f7db38a05e5c20d12e9986d7b87086935fc5ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w4zHsx5ANTHmRy04HzWU5cw3tQC/Zbt8wihVrFpVyC/60JVgSBsTQC42NJYJvlmLRcfkia/zmwWBUyYycQuFAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T00:21:06.065345Z","bundle_sha256":"4154190733f860f935c8ced34db28aadc9eb8fe86e7955190c37cca8bbc79d48"}}