{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RPEJLCIYTBWZ5K2RSOSX23NP4O","short_pith_number":"pith:RPEJLCIY","canonical_record":{"source":{"id":"2504.03338","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-04T10:42:56Z","cross_cats_sorted":[],"title_canon_sha256":"c55261705a3eca28e909d7b40d8f77b701259860255764f0e3f1c21a7ba68feb","abstract_canon_sha256":"4d2bd0e457756df8f1d898640b7962f347fda25b24b78503f20c8e2afdad2f50"},"schema_version":"1.0"},"canonical_sha256":"8bc8958918986d9eab5193a57d6dafe3b3da0b752bde3f216abd2d7190029c7c","source":{"kind":"arxiv","id":"2504.03338","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.03338","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"arxiv_version","alias_value":"2504.03338v3","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.03338","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"pith_short_12","alias_value":"RPEJLCIYTBWZ","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"pith_short_16","alias_value":"RPEJLCIYTBWZ5K2R","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"pith_short_8","alias_value":"RPEJLCIY","created_at":"2026-07-05T11:20:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RPEJLCIYTBWZ5K2RSOSX23NP4O","target":"record","payload":{"canonical_record":{"source":{"id":"2504.03338","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-04T10:42:56Z","cross_cats_sorted":[],"title_canon_sha256":"c55261705a3eca28e909d7b40d8f77b701259860255764f0e3f1c21a7ba68feb","abstract_canon_sha256":"4d2bd0e457756df8f1d898640b7962f347fda25b24b78503f20c8e2afdad2f50"},"schema_version":"1.0"},"canonical_sha256":"8bc8958918986d9eab5193a57d6dafe3b3da0b752bde3f216abd2d7190029c7c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:11.185082Z","signature_b64":"ihDxpX8EqeUdESjzTUFIb+173rPiloV4m9S6HUvMTOU29A7acBeu05zM+B/TJXu9rnA716P1HhBUOsQqF+TLDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bc8958918986d9eab5193a57d6dafe3b3da0b752bde3f216abd2d7190029c7c","last_reissued_at":"2026-07-05T11:20:11.184659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:11.184659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.03338","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:20:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e1OJm65vFP119HAnt5KcrXBv2n8fgS9MqUA+LtHTXPHCuNJSkZyYiG9aNqW8vYbhpH1dNlaSbPB0dSerKzwkCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T20:49:12.759627Z"},"content_sha256":"5e5e99fd90e4654215237983819b2b2c0842bb73b18d5c68fd84c7444d5596fc","schema_version":"1.0","event_id":"sha256:5e5e99fd90e4654215237983819b2b2c0842bb73b18d5c68fd84c7444d5596fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RPEJLCIYTBWZ5K2RSOSX23NP4O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BabyLM's First Words: Word Segmentation as a Phonological Probing Task","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Paula Buttery, Z\\'ebulon Goriely","submitted_at":"2025-04-04T10:42:56Z","abstract_excerpt":"Language models provide a key framework for studying linguistic theories based on prediction, but phonological analysis using large language models (LLMs) is difficult; there are few phonological benchmarks beyond English and the standard input representation used in LLMs (subwords of graphemes) is not suitable for analyzing the representation of phonemes. In this work, we demonstrate how word segmentation can be used as a phonological probing task, allowing us to study the representations learned by phoneme-based language models trained on child-directed speech across 31 languages. Following "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.03338","kind":"arxiv","version":3},"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/2504.03338/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":"2026-07-05T11:20:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IilmyVAxmgU542EajaihBlt048+WIepGX3kNyZxNFg+JUdoUczRrst5Y7aT6zeFdR8+vwNCYYib7SjGDiEKwCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T20:49:12.760137Z"},"content_sha256":"cc0f97211a18aa96d62e2740c9b33c59f3f58f3fa9389db77a458ef359e8d441","schema_version":"1.0","event_id":"sha256:cc0f97211a18aa96d62e2740c9b33c59f3f58f3fa9389db77a458ef359e8d441"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RPEJLCIYTBWZ5K2RSOSX23NP4O/bundle.json","state_url":"https://pith.science/pith/RPEJLCIYTBWZ5K2RSOSX23NP4O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RPEJLCIYTBWZ5K2RSOSX23NP4O/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":"2026-08-22T20:49:12Z","links":{"resolver":"https://pith.science/pith/RPEJLCIYTBWZ5K2RSOSX23NP4O","bundle":"https://pith.science/pith/RPEJLCIYTBWZ5K2RSOSX23NP4O/bundle.json","state":"https://pith.science/pith/RPEJLCIYTBWZ5K2RSOSX23NP4O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RPEJLCIYTBWZ5K2RSOSX23NP4O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RPEJLCIYTBWZ5K2RSOSX23NP4O","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":"4d2bd0e457756df8f1d898640b7962f347fda25b24b78503f20c8e2afdad2f50","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-04T10:42:56Z","title_canon_sha256":"c55261705a3eca28e909d7b40d8f77b701259860255764f0e3f1c21a7ba68feb"},"schema_version":"1.0","source":{"id":"2504.03338","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.03338","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"arxiv_version","alias_value":"2504.03338v3","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.03338","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"pith_short_12","alias_value":"RPEJLCIYTBWZ","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"pith_short_16","alias_value":"RPEJLCIYTBWZ5K2R","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"pith_short_8","alias_value":"RPEJLCIY","created_at":"2026-07-05T11:20:11Z"}],"graph_snapshots":[{"event_id":"sha256:cc0f97211a18aa96d62e2740c9b33c59f3f58f3fa9389db77a458ef359e8d441","target":"graph","created_at":"2026-07-05T11:20:11Z","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/2504.03338/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models provide a key framework for studying linguistic theories based on prediction, but phonological analysis using large language models (LLMs) is difficult; there are few phonological benchmarks beyond English and the standard input representation used in LLMs (subwords of graphemes) is not suitable for analyzing the representation of phonemes. In this work, we demonstrate how word segmentation can be used as a phonological probing task, allowing us to study the representations learned by phoneme-based language models trained on child-directed speech across 31 languages. Following ","authors_text":"Paula Buttery, Z\\'ebulon Goriely","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-04T10:42:56Z","title":"BabyLM's First Words: Word Segmentation as a Phonological Probing Task"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.03338","kind":"arxiv","version":3},"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":"sha256:5e5e99fd90e4654215237983819b2b2c0842bb73b18d5c68fd84c7444d5596fc","target":"record","created_at":"2026-07-05T11:20:11Z","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":"4d2bd0e457756df8f1d898640b7962f347fda25b24b78503f20c8e2afdad2f50","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-04T10:42:56Z","title_canon_sha256":"c55261705a3eca28e909d7b40d8f77b701259860255764f0e3f1c21a7ba68feb"},"schema_version":"1.0","source":{"id":"2504.03338","kind":"arxiv","version":3}},"canonical_sha256":"8bc8958918986d9eab5193a57d6dafe3b3da0b752bde3f216abd2d7190029c7c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8bc8958918986d9eab5193a57d6dafe3b3da0b752bde3f216abd2d7190029c7c","first_computed_at":"2026-07-05T11:20:11.184659Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:11.184659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ihDxpX8EqeUdESjzTUFIb+173rPiloV4m9S6HUvMTOU29A7acBeu05zM+B/TJXu9rnA716P1HhBUOsQqF+TLDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:11.185082Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.03338","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e5e99fd90e4654215237983819b2b2c0842bb73b18d5c68fd84c7444d5596fc","sha256:cc0f97211a18aa96d62e2740c9b33c59f3f58f3fa9389db77a458ef359e8d441"],"state_sha256":"3781628276016ff1b833460462f994a325821df290b1f333eb5e3543b0fb9bab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3yspZBpBnCJMV972j6rkf+z6esKtWpCbC/yHP7A83v66eeGOowuDxdJZLdpgdMERtqdwt3MGPLgoHetnFx9VDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T20:49:12.764631Z","bundle_sha256":"f3cc1a650414369e4131ac8ed28036647c3e1b119f7a36bdbadc802ba066c5b5"}}