{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4B6M3DR2QBJJEHDEB63JNXMDNC","short_pith_number":"pith:4B6M3DR2","canonical_record":{"source":{"id":"2311.00871","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-01T21:41:08Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"48882ed61e9b7ddca36d40c25f88860c7c6e78f9874062f2a56a18e0584a8d9d","abstract_canon_sha256":"2870257526ecac34b5838c410ad0a45fb96523be82016c3f239fb2c527540576"},"schema_version":"1.0"},"canonical_sha256":"e07ccd8e3a8052921c640fb696dd8368bf1fd4d78ac74e30165c7abbf300d0e6","source":{"kind":"arxiv","id":"2311.00871","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.00871","created_at":"2026-07-05T07:08:16Z"},{"alias_kind":"arxiv_version","alias_value":"2311.00871v1","created_at":"2026-07-05T07:08:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00871","created_at":"2026-07-05T07:08:16Z"},{"alias_kind":"pith_short_12","alias_value":"4B6M3DR2QBJJ","created_at":"2026-07-05T07:08:16Z"},{"alias_kind":"pith_short_16","alias_value":"4B6M3DR2QBJJEHDE","created_at":"2026-07-05T07:08:16Z"},{"alias_kind":"pith_short_8","alias_value":"4B6M3DR2","created_at":"2026-07-05T07:08:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4B6M3DR2QBJJEHDEB63JNXMDNC","target":"record","payload":{"canonical_record":{"source":{"id":"2311.00871","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-01T21:41:08Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"48882ed61e9b7ddca36d40c25f88860c7c6e78f9874062f2a56a18e0584a8d9d","abstract_canon_sha256":"2870257526ecac34b5838c410ad0a45fb96523be82016c3f239fb2c527540576"},"schema_version":"1.0"},"canonical_sha256":"e07ccd8e3a8052921c640fb696dd8368bf1fd4d78ac74e30165c7abbf300d0e6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:16.790495Z","signature_b64":"9DX0AY64sGLvhj75SyHV9LJqp9sslWod6Vq+64KrcSYLVxq5zgUr6gRfy6PnROazvtR2G26SiyEjhv9U+bveCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e07ccd8e3a8052921c640fb696dd8368bf1fd4d78ac74e30165c7abbf300d0e6","last_reissued_at":"2026-07-05T07:08:16.790032Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:16.790032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.00871","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":"2026-07-05T07:08:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BIY+dxNQ8hLVPcWGRqkCPBgPT7ri1L+pId0VNud5kWy8eYiz0iuXw4R9hYX6hittsjlYNodWV7a00zLjKu3xAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T13:00:55.575704Z"},"content_sha256":"9df521463339f86c7bca3bf32aa8abfe4af5cfa5fec1e3b3da1047bb3599f0de","schema_version":"1.0","event_id":"sha256:9df521463339f86c7bca3bf32aa8abfe4af5cfa5fec1e3b3da1047bb3599f0de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4B6M3DR2QBJJEHDEB63JNXMDNC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pretraining Data Mixtures Enable Narrow Model Selection Capabilities in Transformer Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lyric Doshi, Nilesh Tripuraneni, Steve Yadlowsky","submitted_at":"2023-11-01T21:41:08Z","abstract_excerpt":"Transformer models, notably large language models (LLMs), have the remarkable ability to perform in-context learning (ICL) -- to perform new tasks when prompted with unseen input-output examples without any explicit model training. In this work, we study how effectively transformers can bridge between their pretraining data mixture, comprised of multiple distinct task families, to identify and learn new tasks in-context which are both inside and outside the pretraining distribution. Building on previous work, we investigate this question in a controlled setting, where we study transformer mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00871","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/2311.00871/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":"2026-07-05T07:08:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CrLQVYrFSKVF9TdXZQ2NITG5ra+jvOzQqdKiZ2hSgSnn3DXbZvUhhmgkl6vjcKIH8l691GqTlnM4RekBs1J/Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T13:00:55.576615Z"},"content_sha256":"50380e56d097f5dd23a798b26b417dba8f403b79fd9d3acebb97d58521e1d11c","schema_version":"1.0","event_id":"sha256:50380e56d097f5dd23a798b26b417dba8f403b79fd9d3acebb97d58521e1d11c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4B6M3DR2QBJJEHDEB63JNXMDNC/bundle.json","state_url":"https://pith.science/pith/4B6M3DR2QBJJEHDEB63JNXMDNC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4B6M3DR2QBJJEHDEB63JNXMDNC/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":"2026-08-17T13:00:55Z","links":{"resolver":"https://pith.science/pith/4B6M3DR2QBJJEHDEB63JNXMDNC","bundle":"https://pith.science/pith/4B6M3DR2QBJJEHDEB63JNXMDNC/bundle.json","state":"https://pith.science/pith/4B6M3DR2QBJJEHDEB63JNXMDNC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4B6M3DR2QBJJEHDEB63JNXMDNC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4B6M3DR2QBJJEHDEB63JNXMDNC","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":"2870257526ecac34b5838c410ad0a45fb96523be82016c3f239fb2c527540576","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-01T21:41:08Z","title_canon_sha256":"48882ed61e9b7ddca36d40c25f88860c7c6e78f9874062f2a56a18e0584a8d9d"},"schema_version":"1.0","source":{"id":"2311.00871","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.00871","created_at":"2026-07-05T07:08:16Z"},{"alias_kind":"arxiv_version","alias_value":"2311.00871v1","created_at":"2026-07-05T07:08:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00871","created_at":"2026-07-05T07:08:16Z"},{"alias_kind":"pith_short_12","alias_value":"4B6M3DR2QBJJ","created_at":"2026-07-05T07:08:16Z"},{"alias_kind":"pith_short_16","alias_value":"4B6M3DR2QBJJEHDE","created_at":"2026-07-05T07:08:16Z"},{"alias_kind":"pith_short_8","alias_value":"4B6M3DR2","created_at":"2026-07-05T07:08:16Z"}],"graph_snapshots":[{"event_id":"sha256:50380e56d097f5dd23a798b26b417dba8f403b79fd9d3acebb97d58521e1d11c","target":"graph","created_at":"2026-07-05T07:08:16Z","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/2311.00871/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer models, notably large language models (LLMs), have the remarkable ability to perform in-context learning (ICL) -- to perform new tasks when prompted with unseen input-output examples without any explicit model training. In this work, we study how effectively transformers can bridge between their pretraining data mixture, comprised of multiple distinct task families, to identify and learn new tasks in-context which are both inside and outside the pretraining distribution. Building on previous work, we investigate this question in a controlled setting, where we study transformer mode","authors_text":"Lyric Doshi, Nilesh Tripuraneni, Steve Yadlowsky","cross_cats":["cs.CL","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-01T21:41:08Z","title":"Pretraining Data Mixtures Enable Narrow Model Selection Capabilities in Transformer Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00871","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":"sha256:9df521463339f86c7bca3bf32aa8abfe4af5cfa5fec1e3b3da1047bb3599f0de","target":"record","created_at":"2026-07-05T07:08:16Z","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":"2870257526ecac34b5838c410ad0a45fb96523be82016c3f239fb2c527540576","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-01T21:41:08Z","title_canon_sha256":"48882ed61e9b7ddca36d40c25f88860c7c6e78f9874062f2a56a18e0584a8d9d"},"schema_version":"1.0","source":{"id":"2311.00871","kind":"arxiv","version":1}},"canonical_sha256":"e07ccd8e3a8052921c640fb696dd8368bf1fd4d78ac74e30165c7abbf300d0e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e07ccd8e3a8052921c640fb696dd8368bf1fd4d78ac74e30165c7abbf300d0e6","first_computed_at":"2026-07-05T07:08:16.790032Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:08:16.790032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9DX0AY64sGLvhj75SyHV9LJqp9sslWod6Vq+64KrcSYLVxq5zgUr6gRfy6PnROazvtR2G26SiyEjhv9U+bveCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:08:16.790495Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.00871","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9df521463339f86c7bca3bf32aa8abfe4af5cfa5fec1e3b3da1047bb3599f0de","sha256:50380e56d097f5dd23a798b26b417dba8f403b79fd9d3acebb97d58521e1d11c"],"state_sha256":"ed3a8a5bb90d6e1162017ec1ec52c3e912bb6cf082d11e135eec17e3f31a9eb3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BEGaL7hCfBzPvQFIVWgKKSOVp5y+OyYMnJBmVzNSjBAyOaj1bHAnliJoG1EWXhmN7c0jq5TNb7fzwPgTspKHCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T13:00:55.647290Z","bundle_sha256":"142728a957c688346c970f1c44365c714ef51b9c3e80ea2ca60d3fe157a8c762"}}