{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:T6OKITZHPS6ZECAKFY44AGWBGV","short_pith_number":"pith:T6OKITZH","canonical_record":{"source":{"id":"2405.15750","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-24T17:47:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"62f62e69fcce877ffea531159a15761e45cce71703165e6b4e15b2b6be11a611","abstract_canon_sha256":"43f070ba353bfb59f8369f28ab3e8283d6edf035fa08cb8b0568ea17ea058bcc"},"schema_version":"1.0"},"canonical_sha256":"9f9ca44f277cbd92080a2e39c01ac13561bb79b02c06b143b767140a2aea90b7","source":{"kind":"arxiv","id":"2405.15750","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.15750","created_at":"2026-07-05T08:52:54Z"},{"alias_kind":"arxiv_version","alias_value":"2405.15750v2","created_at":"2026-07-05T08:52:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15750","created_at":"2026-07-05T08:52:54Z"},{"alias_kind":"pith_short_12","alias_value":"T6OKITZHPS6Z","created_at":"2026-07-05T08:52:54Z"},{"alias_kind":"pith_short_16","alias_value":"T6OKITZHPS6ZECAK","created_at":"2026-07-05T08:52:54Z"},{"alias_kind":"pith_short_8","alias_value":"T6OKITZH","created_at":"2026-07-05T08:52:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:T6OKITZHPS6ZECAKFY44AGWBGV","target":"record","payload":{"canonical_record":{"source":{"id":"2405.15750","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-24T17:47:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"62f62e69fcce877ffea531159a15761e45cce71703165e6b4e15b2b6be11a611","abstract_canon_sha256":"43f070ba353bfb59f8369f28ab3e8283d6edf035fa08cb8b0568ea17ea058bcc"},"schema_version":"1.0"},"canonical_sha256":"9f9ca44f277cbd92080a2e39c01ac13561bb79b02c06b143b767140a2aea90b7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:54.237543Z","signature_b64":"wpwp0pi0f1QYXutIGsIZGTpM+pEWAuQFF/D37/DZ+TpYcSLtu26Wm6OBqTKNTOfrkj+zM54YWndgx94aTJOnCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f9ca44f277cbd92080a2e39c01ac13561bb79b02c06b143b767140a2aea90b7","last_reissued_at":"2026-07-05T08:52:54.237109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:54.237109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.15750","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":"2026-07-05T08:52:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3T78UMF02TPATsEotJjrQHVJAQ0RZQImKpE2ovaJYkjFrrC0z6utGKdo0ZoHyJVErM0kRQIWb0/kpFhRrYIuBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:32:15.789280Z"},"content_sha256":"135d3e25a9c6c2201890186967545ac475d6ec03bfce8946653bb9d3da17dd39","schema_version":"1.0","event_id":"sha256:135d3e25a9c6c2201890186967545ac475d6ec03bfce8946653bb9d3da17dd39"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:T6OKITZHPS6ZECAKFY44AGWBGV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Filtered Corpus Training (FiCT) Shows that Language Models can Generalize from Indirect Evidence","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abhinav Patil, Andy Lapastora, Clevis Willrich, Jaap Jumelet, Lexie Wang, Peter Shen, Shane Steinert-Threlkeld, Yu Ying Chiu","submitted_at":"2024-05-24T17:47:20Z","abstract_excerpt":"This paper introduces Filtered Corpus Training, a method that trains language models (LMs) on corpora with certain linguistic constructions filtered out from the training data, and uses it to measure the ability of LMs to perform linguistic generalization on the basis of indirect evidence. We apply the method to both LSTM and Transformer LMs (of roughly comparable size), developing filtered corpora that target a wide range of linguistic phenomena. Our results show that while transformers are better qua LMs (as measured by perplexity), both models perform equally and surprisingly well on lingui"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15750","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/2405.15750/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":"2026-07-05T08:52:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BtHzlS2CVQTVrlCgL2UExKAcw6FZYBpZ2GJL6XLE1WaUTorAM2cozDv4T9D/1vosaDXkbHtNj56PmEqTxj3bBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:32:15.789665Z"},"content_sha256":"b044da43f67094b50abfb324d1d9ea1e0da9df6a155271e3da407491434eb55d","schema_version":"1.0","event_id":"sha256:b044da43f67094b50abfb324d1d9ea1e0da9df6a155271e3da407491434eb55d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T6OKITZHPS6ZECAKFY44AGWBGV/bundle.json","state_url":"https://pith.science/pith/T6OKITZHPS6ZECAKFY44AGWBGV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T6OKITZHPS6ZECAKFY44AGWBGV/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":"2026-07-07T10:32:15Z","links":{"resolver":"https://pith.science/pith/T6OKITZHPS6ZECAKFY44AGWBGV","bundle":"https://pith.science/pith/T6OKITZHPS6ZECAKFY44AGWBGV/bundle.json","state":"https://pith.science/pith/T6OKITZHPS6ZECAKFY44AGWBGV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T6OKITZHPS6ZECAKFY44AGWBGV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:T6OKITZHPS6ZECAKFY44AGWBGV","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":"43f070ba353bfb59f8369f28ab3e8283d6edf035fa08cb8b0568ea17ea058bcc","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-24T17:47:20Z","title_canon_sha256":"62f62e69fcce877ffea531159a15761e45cce71703165e6b4e15b2b6be11a611"},"schema_version":"1.0","source":{"id":"2405.15750","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.15750","created_at":"2026-07-05T08:52:54Z"},{"alias_kind":"arxiv_version","alias_value":"2405.15750v2","created_at":"2026-07-05T08:52:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15750","created_at":"2026-07-05T08:52:54Z"},{"alias_kind":"pith_short_12","alias_value":"T6OKITZHPS6Z","created_at":"2026-07-05T08:52:54Z"},{"alias_kind":"pith_short_16","alias_value":"T6OKITZHPS6ZECAK","created_at":"2026-07-05T08:52:54Z"},{"alias_kind":"pith_short_8","alias_value":"T6OKITZH","created_at":"2026-07-05T08:52:54Z"}],"graph_snapshots":[{"event_id":"sha256:b044da43f67094b50abfb324d1d9ea1e0da9df6a155271e3da407491434eb55d","target":"graph","created_at":"2026-07-05T08:52:54Z","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/2405.15750/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces Filtered Corpus Training, a method that trains language models (LMs) on corpora with certain linguistic constructions filtered out from the training data, and uses it to measure the ability of LMs to perform linguistic generalization on the basis of indirect evidence. We apply the method to both LSTM and Transformer LMs (of roughly comparable size), developing filtered corpora that target a wide range of linguistic phenomena. Our results show that while transformers are better qua LMs (as measured by perplexity), both models perform equally and surprisingly well on lingui","authors_text":"Abhinav Patil, Andy Lapastora, Clevis Willrich, Jaap Jumelet, Lexie Wang, Peter Shen, Shane Steinert-Threlkeld, Yu Ying Chiu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-24T17:47:20Z","title":"Filtered Corpus Training (FiCT) Shows that Language Models can Generalize from Indirect Evidence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15750","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":"sha256:135d3e25a9c6c2201890186967545ac475d6ec03bfce8946653bb9d3da17dd39","target":"record","created_at":"2026-07-05T08:52:54Z","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":"43f070ba353bfb59f8369f28ab3e8283d6edf035fa08cb8b0568ea17ea058bcc","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-24T17:47:20Z","title_canon_sha256":"62f62e69fcce877ffea531159a15761e45cce71703165e6b4e15b2b6be11a611"},"schema_version":"1.0","source":{"id":"2405.15750","kind":"arxiv","version":2}},"canonical_sha256":"9f9ca44f277cbd92080a2e39c01ac13561bb79b02c06b143b767140a2aea90b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f9ca44f277cbd92080a2e39c01ac13561bb79b02c06b143b767140a2aea90b7","first_computed_at":"2026-07-05T08:52:54.237109Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:52:54.237109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wpwp0pi0f1QYXutIGsIZGTpM+pEWAuQFF/D37/DZ+TpYcSLtu26Wm6OBqTKNTOfrkj+zM54YWndgx94aTJOnCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:52:54.237543Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.15750","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:135d3e25a9c6c2201890186967545ac475d6ec03bfce8946653bb9d3da17dd39","sha256:b044da43f67094b50abfb324d1d9ea1e0da9df6a155271e3da407491434eb55d"],"state_sha256":"e385491208e305eb2917e367686c30e35eee6f6e4626d6be82542383cb0f86e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z29cCT83F3jHti5oBzlafP02iPrBtKIqgAH0AeovZTgXC2u6aUg3HhL6AWNz9EilmDDmGlT200/Epuhy/zCHBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:32:15.791818Z","bundle_sha256":"ba1df5de8430619a91b6aad7822c41c0794295119b7b7ab10558267a4716bdcd"}}