{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:U7D35KPF7PVBBP36IHAFLSG6GY","short_pith_number":"pith:U7D35KPF","canonical_record":{"source":{"id":"2409.12440","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-19T03:48:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a5217b279d937075656f697eb06b9f39de27314931f227e9d229b7fd77be66f7","abstract_canon_sha256":"10f0af1f485696478c3ec2167b50859e84b0cb5890bc805bb98171ee21f01f19"},"schema_version":"1.0"},"canonical_sha256":"a7c7bea9e5fbea10bf7e41c055c8de36338c75c83467eeac45b936a0b34b6a9c","source":{"kind":"arxiv","id":"2409.12440","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.12440","created_at":"2026-07-05T09:08:54Z"},{"alias_kind":"arxiv_version","alias_value":"2409.12440v1","created_at":"2026-07-05T09:08:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12440","created_at":"2026-07-05T09:08:54Z"},{"alias_kind":"pith_short_12","alias_value":"U7D35KPF7PVB","created_at":"2026-07-05T09:08:54Z"},{"alias_kind":"pith_short_16","alias_value":"U7D35KPF7PVBBP36","created_at":"2026-07-05T09:08:54Z"},{"alias_kind":"pith_short_8","alias_value":"U7D35KPF","created_at":"2026-07-05T09:08:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:U7D35KPF7PVBBP36IHAFLSG6GY","target":"record","payload":{"canonical_record":{"source":{"id":"2409.12440","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-19T03:48:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a5217b279d937075656f697eb06b9f39de27314931f227e9d229b7fd77be66f7","abstract_canon_sha256":"10f0af1f485696478c3ec2167b50859e84b0cb5890bc805bb98171ee21f01f19"},"schema_version":"1.0"},"canonical_sha256":"a7c7bea9e5fbea10bf7e41c055c8de36338c75c83467eeac45b936a0b34b6a9c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:54.312953Z","signature_b64":"3IBgqCS6Rq0tQafDWAsSzmeXaFjm3U8spqCrbZsKPF2PGVXhdcevv2RzM34CuyM7m3uTRQacbvjSqNOtiD2eAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7c7bea9e5fbea10bf7e41c055c8de36338c75c83467eeac45b936a0b34b6a9c","last_reissued_at":"2026-07-05T09:08:54.312344Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:54.312344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.12440","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":"2026-07-05T09:08:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t3kBnZmaoU8a+Bx2FagSxXCIXN0g21xHcvfQrm8jx561DrCu+1YQwi+x2I7akXQlz3TGl+1yWtw9usebb2qxCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:15:42.927157Z"},"content_sha256":"83cdcb65aaca954f02cddea1137a5ffae2b4aeb24adf2df1a40fc0b1fa062403","schema_version":"1.0","event_id":"sha256:83cdcb65aaca954f02cddea1137a5ffae2b4aeb24adf2df1a40fc0b1fa062403"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:U7D35KPF7PVBBP36IHAFLSG6GY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Incremental and Data-Efficient Concept Formation to Support Masked Word Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Christopher J. MacLellan, Nishant Baglodi, Xin Lian","submitted_at":"2024-09-19T03:48:31Z","abstract_excerpt":"This paper introduces Cobweb4L, a novel approach for efficient language model learning that supports masked word prediction. The approach builds on Cobweb, an incremental system that learns a hierarchy of probabilistic concepts. Each concept stores the frequencies of words that appear in instances tagged with that concept label. The system utilizes an attribute value representation to encode words and their surrounding context into instances. Cobweb4L uses the information theoretic variant of category utility and a new performance mechanism that leverages multiple concepts to generate predicti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12440","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/2409.12440/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":"2026-07-05T09:08:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gqd50BKI0XYe63yH/X6PXIpjqQ27rk3g9xCj/NCzs/lTizAYeRy6438XuSPXOdzuzn5wW5dCKmGYF0lvsufXCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:15:42.927749Z"},"content_sha256":"5c6f51d50775cb0ccde12e0ed21bd08dcf58a7d7a2a03e300ddb816231398b9e","schema_version":"1.0","event_id":"sha256:5c6f51d50775cb0ccde12e0ed21bd08dcf58a7d7a2a03e300ddb816231398b9e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U7D35KPF7PVBBP36IHAFLSG6GY/bundle.json","state_url":"https://pith.science/pith/U7D35KPF7PVBBP36IHAFLSG6GY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U7D35KPF7PVBBP36IHAFLSG6GY/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":"2026-08-10T12:15:42Z","links":{"resolver":"https://pith.science/pith/U7D35KPF7PVBBP36IHAFLSG6GY","bundle":"https://pith.science/pith/U7D35KPF7PVBBP36IHAFLSG6GY/bundle.json","state":"https://pith.science/pith/U7D35KPF7PVBBP36IHAFLSG6GY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U7D35KPF7PVBBP36IHAFLSG6GY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:U7D35KPF7PVBBP36IHAFLSG6GY","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":"10f0af1f485696478c3ec2167b50859e84b0cb5890bc805bb98171ee21f01f19","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-19T03:48:31Z","title_canon_sha256":"a5217b279d937075656f697eb06b9f39de27314931f227e9d229b7fd77be66f7"},"schema_version":"1.0","source":{"id":"2409.12440","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.12440","created_at":"2026-07-05T09:08:54Z"},{"alias_kind":"arxiv_version","alias_value":"2409.12440v1","created_at":"2026-07-05T09:08:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12440","created_at":"2026-07-05T09:08:54Z"},{"alias_kind":"pith_short_12","alias_value":"U7D35KPF7PVB","created_at":"2026-07-05T09:08:54Z"},{"alias_kind":"pith_short_16","alias_value":"U7D35KPF7PVBBP36","created_at":"2026-07-05T09:08:54Z"},{"alias_kind":"pith_short_8","alias_value":"U7D35KPF","created_at":"2026-07-05T09:08:54Z"}],"graph_snapshots":[{"event_id":"sha256:5c6f51d50775cb0ccde12e0ed21bd08dcf58a7d7a2a03e300ddb816231398b9e","target":"graph","created_at":"2026-07-05T09:08:54Z","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/2409.12440/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces Cobweb4L, a novel approach for efficient language model learning that supports masked word prediction. The approach builds on Cobweb, an incremental system that learns a hierarchy of probabilistic concepts. Each concept stores the frequencies of words that appear in instances tagged with that concept label. The system utilizes an attribute value representation to encode words and their surrounding context into instances. Cobweb4L uses the information theoretic variant of category utility and a new performance mechanism that leverages multiple concepts to generate predicti","authors_text":"Christopher J. MacLellan, Nishant Baglodi, Xin Lian","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-19T03:48:31Z","title":"Incremental and Data-Efficient Concept Formation to Support Masked Word Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12440","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":"sha256:83cdcb65aaca954f02cddea1137a5ffae2b4aeb24adf2df1a40fc0b1fa062403","target":"record","created_at":"2026-07-05T09:08:54Z","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":"10f0af1f485696478c3ec2167b50859e84b0cb5890bc805bb98171ee21f01f19","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-19T03:48:31Z","title_canon_sha256":"a5217b279d937075656f697eb06b9f39de27314931f227e9d229b7fd77be66f7"},"schema_version":"1.0","source":{"id":"2409.12440","kind":"arxiv","version":1}},"canonical_sha256":"a7c7bea9e5fbea10bf7e41c055c8de36338c75c83467eeac45b936a0b34b6a9c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7c7bea9e5fbea10bf7e41c055c8de36338c75c83467eeac45b936a0b34b6a9c","first_computed_at":"2026-07-05T09:08:54.312344Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:08:54.312344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3IBgqCS6Rq0tQafDWAsSzmeXaFjm3U8spqCrbZsKPF2PGVXhdcevv2RzM34CuyM7m3uTRQacbvjSqNOtiD2eAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:08:54.312953Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.12440","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:83cdcb65aaca954f02cddea1137a5ffae2b4aeb24adf2df1a40fc0b1fa062403","sha256:5c6f51d50775cb0ccde12e0ed21bd08dcf58a7d7a2a03e300ddb816231398b9e"],"state_sha256":"7e660a142b34812203940fd9fe7b0d242cc79e04dacbf5df33de701c6d3f0f47"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UPM6lTVxD/hfv4Re7qT6MCk23IoUSFtrXteFoSb13lqfsuVIxC/QkFf5UlhRdfiyeV8iq+N6ghfs4Nebc9qvAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T12:15:42.936482Z","bundle_sha256":"a31ead2e41e051628080d8a745c4ebbd0fea84540f9a5aa80e11b3cfddae4005"}}