{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:44AVRDDWDUFQPJS35YWFFIWS27","short_pith_number":"pith:44AVRDDW","canonical_record":{"source":{"id":"2606.09822","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T17:58:36Z","cross_cats_sorted":["cs.FL"],"title_canon_sha256":"86be71472acfda16808c58250b3e58249bb43001a0ceaef8f7cb8994eb916efa","abstract_canon_sha256":"86f4237d5faa716f3d75b994fd599ddbae26712a85946b9d3c5b05e8d1113418"},"schema_version":"1.0"},"canonical_sha256":"e701588c761d0b07a65bee2c52a2d2d7d61bdbcd8cda9e2bf8769fe6590ca423","source":{"kind":"arxiv","id":"2606.09822","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09822","created_at":"2026-06-09T02:09:12Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09822v1","created_at":"2026-06-09T02:09:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09822","created_at":"2026-06-09T02:09:12Z"},{"alias_kind":"pith_short_12","alias_value":"44AVRDDWDUFQ","created_at":"2026-06-09T02:09:12Z"},{"alias_kind":"pith_short_16","alias_value":"44AVRDDWDUFQPJS3","created_at":"2026-06-09T02:09:12Z"},{"alias_kind":"pith_short_8","alias_value":"44AVRDDW","created_at":"2026-06-09T02:09:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:44AVRDDWDUFQPJS35YWFFIWS27","target":"record","payload":{"canonical_record":{"source":{"id":"2606.09822","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T17:58:36Z","cross_cats_sorted":["cs.FL"],"title_canon_sha256":"86be71472acfda16808c58250b3e58249bb43001a0ceaef8f7cb8994eb916efa","abstract_canon_sha256":"86f4237d5faa716f3d75b994fd599ddbae26712a85946b9d3c5b05e8d1113418"},"schema_version":"1.0"},"canonical_sha256":"e701588c761d0b07a65bee2c52a2d2d7d61bdbcd8cda9e2bf8769fe6590ca423","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:09:12.491358Z","signature_b64":"k4mcUwU+CREpzc/mmr6ZyZ+c7Ha61I2k8j4ZfZ+v93/wqgKEvEVgRZQlWBpLa/pBanD4M68CY/M9n8XwiBSyBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e701588c761d0b07a65bee2c52a2d2d7d61bdbcd8cda9e2bf8769fe6590ca423","last_reissued_at":"2026-06-09T02:09:12.490514Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:09:12.490514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.09822","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T02:09:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NwWcHkuiKLNtVBgWRqZU1G7uyGo0dxREdMraxLko28+g0ZQgJvO4tNUXWOF2Pm6hbQ//pB2LEOUyZ7Y6a5u5DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T08:45:36.154931Z"},"content_sha256":"5eddb867604b58bcd179815aa82405a8297058d566741a808fa301c4957ae980","schema_version":"1.0","event_id":"sha256:5eddb867604b58bcd179815aa82405a8297058d566741a808fa301c4957ae980"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:44AVRDDWDUFQPJS35YWFFIWS27","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Causally Evaluating the Learnability of Formal Language Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.FL"],"primary_cat":"cs.CL","authors_text":"Anej Svete, Brian DuSell, Josef Valvoda, Reda Boumasmoud, Ryan Cotterell, V\\'esteinn Sn{\\ae}bjarnarson","submitted_at":"2026-06-08T17:58:36Z","abstract_excerpt":"Language models, as multi-task learners, acquire a wide range of abilities during training. A fundamental question is how much task-specific data is needed to learn a given task. Answering this for natural language is difficult: tasks are hard to delineate and can confound one another. To rigorously investigate the relationship between data frequency and learnability, we turn to a controlled setting using formal languages induced from probabilistic finite automata. These serve as a methodological testbed to demonstrate that standard correlational evaluation practices are inherently flawed. To "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09822","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/2606.09822/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":"2026-06-09T02:09:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V8On+4gDQHsQfjzGDltQ+oaTP/SajZqhRmoi2Epj0FADZdelTRiyxPEpks8Zdoq9niE43RZfTPyeMZsTKuLnDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T08:45:36.155309Z"},"content_sha256":"4a05b60c08646aae54c6ae5dcbdf6d336ce68f086c6bf2d23efc690c49e8a815","schema_version":"1.0","event_id":"sha256:4a05b60c08646aae54c6ae5dcbdf6d336ce68f086c6bf2d23efc690c49e8a815"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/44AVRDDWDUFQPJS35YWFFIWS27/bundle.json","state_url":"https://pith.science/pith/44AVRDDWDUFQPJS35YWFFIWS27/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/44AVRDDWDUFQPJS35YWFFIWS27/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":"2026-06-28T08:45:36Z","links":{"resolver":"https://pith.science/pith/44AVRDDWDUFQPJS35YWFFIWS27","bundle":"https://pith.science/pith/44AVRDDWDUFQPJS35YWFFIWS27/bundle.json","state":"https://pith.science/pith/44AVRDDWDUFQPJS35YWFFIWS27/state.json","well_known_bundle":"https://pith.science/.well-known/pith/44AVRDDWDUFQPJS35YWFFIWS27/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:44AVRDDWDUFQPJS35YWFFIWS27","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":"86f4237d5faa716f3d75b994fd599ddbae26712a85946b9d3c5b05e8d1113418","cross_cats_sorted":["cs.FL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T17:58:36Z","title_canon_sha256":"86be71472acfda16808c58250b3e58249bb43001a0ceaef8f7cb8994eb916efa"},"schema_version":"1.0","source":{"id":"2606.09822","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09822","created_at":"2026-06-09T02:09:12Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09822v1","created_at":"2026-06-09T02:09:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09822","created_at":"2026-06-09T02:09:12Z"},{"alias_kind":"pith_short_12","alias_value":"44AVRDDWDUFQ","created_at":"2026-06-09T02:09:12Z"},{"alias_kind":"pith_short_16","alias_value":"44AVRDDWDUFQPJS3","created_at":"2026-06-09T02:09:12Z"},{"alias_kind":"pith_short_8","alias_value":"44AVRDDW","created_at":"2026-06-09T02:09:12Z"}],"graph_snapshots":[{"event_id":"sha256:4a05b60c08646aae54c6ae5dcbdf6d336ce68f086c6bf2d23efc690c49e8a815","target":"graph","created_at":"2026-06-09T02:09:12Z","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/2606.09822/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models, as multi-task learners, acquire a wide range of abilities during training. A fundamental question is how much task-specific data is needed to learn a given task. Answering this for natural language is difficult: tasks are hard to delineate and can confound one another. To rigorously investigate the relationship between data frequency and learnability, we turn to a controlled setting using formal languages induced from probabilistic finite automata. These serve as a methodological testbed to demonstrate that standard correlational evaluation practices are inherently flawed. To ","authors_text":"Anej Svete, Brian DuSell, Josef Valvoda, Reda Boumasmoud, Ryan Cotterell, V\\'esteinn Sn{\\ae}bjarnarson","cross_cats":["cs.FL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T17:58:36Z","title":"Causally Evaluating the Learnability of Formal Language Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09822","kind":"arxiv","version":1},"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":"sha256:5eddb867604b58bcd179815aa82405a8297058d566741a808fa301c4957ae980","target":"record","created_at":"2026-06-09T02:09:12Z","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":"86f4237d5faa716f3d75b994fd599ddbae26712a85946b9d3c5b05e8d1113418","cross_cats_sorted":["cs.FL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T17:58:36Z","title_canon_sha256":"86be71472acfda16808c58250b3e58249bb43001a0ceaef8f7cb8994eb916efa"},"schema_version":"1.0","source":{"id":"2606.09822","kind":"arxiv","version":1}},"canonical_sha256":"e701588c761d0b07a65bee2c52a2d2d7d61bdbcd8cda9e2bf8769fe6590ca423","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e701588c761d0b07a65bee2c52a2d2d7d61bdbcd8cda9e2bf8769fe6590ca423","first_computed_at":"2026-06-09T02:09:12.490514Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:09:12.490514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k4mcUwU+CREpzc/mmr6ZyZ+c7Ha61I2k8j4ZfZ+v93/wqgKEvEVgRZQlWBpLa/pBanD4M68CY/M9n8XwiBSyBA==","signature_status":"signed_v1","signed_at":"2026-06-09T02:09:12.491358Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.09822","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5eddb867604b58bcd179815aa82405a8297058d566741a808fa301c4957ae980","sha256:4a05b60c08646aae54c6ae5dcbdf6d336ce68f086c6bf2d23efc690c49e8a815"],"state_sha256":"337f7ea6b9b822c82c74b1c633d940f87bf4c84149b22e3c604d482de4512997"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eH8yGtitGp3IQUPPzdR8TWKqfUDmexu2L+SkMIuvNlkaVz99DVj5PLaZOX1t7uYplg5pl7nvRdpPcACeLxZsDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T08:45:36.157277Z","bundle_sha256":"00a64b5ebaf19eaeed558a2ac03294a40d2de217b4f01e9b694b82e0312891fb"}}