{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WTAUZOHFTPVDNLUNYLI4ILQDRF","short_pith_number":"pith:WTAUZOHF","canonical_record":{"source":{"id":"2505.06475","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-10T00:22:40Z","cross_cats_sorted":[],"title_canon_sha256":"54ee1d1557187e6af25c78c882b28cd80d3580475e009aa292cb61b819d1bd75","abstract_canon_sha256":"ccefeb6ea506bf3ad0bb93ac62f6b73cec5f40310f1d184cb429ac2cf23b66bb"},"schema_version":"1.0"},"canonical_sha256":"b4c14cb8e59bea36ae8dc2d1c42e03897679294a58f72cf75b860da6fbb51768","source":{"kind":"arxiv","id":"2505.06475","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.06475","created_at":"2026-07-05T11:01:10Z"},{"alias_kind":"arxiv_version","alias_value":"2505.06475v1","created_at":"2026-07-05T11:01:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06475","created_at":"2026-07-05T11:01:10Z"},{"alias_kind":"pith_short_12","alias_value":"WTAUZOHFTPVD","created_at":"2026-07-05T11:01:10Z"},{"alias_kind":"pith_short_16","alias_value":"WTAUZOHFTPVDNLUN","created_at":"2026-07-05T11:01:10Z"},{"alias_kind":"pith_short_8","alias_value":"WTAUZOHF","created_at":"2026-07-05T11:01:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WTAUZOHFTPVDNLUNYLI4ILQDRF","target":"record","payload":{"canonical_record":{"source":{"id":"2505.06475","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-10T00:22:40Z","cross_cats_sorted":[],"title_canon_sha256":"54ee1d1557187e6af25c78c882b28cd80d3580475e009aa292cb61b819d1bd75","abstract_canon_sha256":"ccefeb6ea506bf3ad0bb93ac62f6b73cec5f40310f1d184cb429ac2cf23b66bb"},"schema_version":"1.0"},"canonical_sha256":"b4c14cb8e59bea36ae8dc2d1c42e03897679294a58f72cf75b860da6fbb51768","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:10.174304Z","signature_b64":"jqwbaFtCn1efbDvVoqeNBS/jNW7kDsI004GhZzpy6EVJXrtFJIEGg3wQ74B2BGkQ6rGnEO1On35yABXpICfJDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4c14cb8e59bea36ae8dc2d1c42e03897679294a58f72cf75b860da6fbb51768","last_reissued_at":"2026-07-05T11:01:10.173816Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:10.173816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.06475","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":"2026-07-05T11:01:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ttal5kTEBAcYX1EsA7vUs2lGUeYF7qako56d5YkDZB6Y3hG464jgwTEQcHpynGoGpSPcjoo5fh8SRrJAaAFHCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:49:40.004800Z"},"content_sha256":"b4876eb07053914ea8a1806d1af698c7830431a3d0546d684269a6a073dcc9a0","schema_version":"1.0","event_id":"sha256:b4876eb07053914ea8a1806d1af698c7830431a3d0546d684269a6a073dcc9a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WTAUZOHFTPVDNLUNYLI4ILQDRF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Probing In-Context Learning: Impact of Task Complexity and Model Architecture on Generalization and Efficiency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Binwen Liu, Peiyu Xu, Quan Yuan, Yihong Chen","submitted_at":"2025-05-10T00:22:40Z","abstract_excerpt":"We investigate in-context learning (ICL) through a meticulous experimental framework that systematically varies task complexity and model architecture. Extending beyond the linear regression baseline, we introduce Gaussian kernel regression and nonlinear dynamical system tasks, which emphasize temporal and recursive reasoning. We evaluate four distinct models: a GPT2-style Transformer, a Transformer with FlashAttention mechanism, a convolutional Hyena-based model, and the Mamba state-space model. Each model is trained from scratch on synthetic datasets and assessed for generalization during te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06475","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/2505.06475/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":"2026-07-05T11:01:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N2AtUWYyXpDZLJYuxiUdb/RBUxj18oOj+OZHhlRWGFrIkOb8YjeO0slp/VbxAnVqHqegSFCXJFiOASTJba6uDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:49:40.005169Z"},"content_sha256":"0104ff67808e0346eb2c3ef08445cb4dbd09866f23be9465b5a0fb3077ed8520","schema_version":"1.0","event_id":"sha256:0104ff67808e0346eb2c3ef08445cb4dbd09866f23be9465b5a0fb3077ed8520"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WTAUZOHFTPVDNLUNYLI4ILQDRF/bundle.json","state_url":"https://pith.science/pith/WTAUZOHFTPVDNLUNYLI4ILQDRF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WTAUZOHFTPVDNLUNYLI4ILQDRF/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":"2026-07-07T07:49:40Z","links":{"resolver":"https://pith.science/pith/WTAUZOHFTPVDNLUNYLI4ILQDRF","bundle":"https://pith.science/pith/WTAUZOHFTPVDNLUNYLI4ILQDRF/bundle.json","state":"https://pith.science/pith/WTAUZOHFTPVDNLUNYLI4ILQDRF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WTAUZOHFTPVDNLUNYLI4ILQDRF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WTAUZOHFTPVDNLUNYLI4ILQDRF","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":"ccefeb6ea506bf3ad0bb93ac62f6b73cec5f40310f1d184cb429ac2cf23b66bb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-10T00:22:40Z","title_canon_sha256":"54ee1d1557187e6af25c78c882b28cd80d3580475e009aa292cb61b819d1bd75"},"schema_version":"1.0","source":{"id":"2505.06475","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.06475","created_at":"2026-07-05T11:01:10Z"},{"alias_kind":"arxiv_version","alias_value":"2505.06475v1","created_at":"2026-07-05T11:01:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06475","created_at":"2026-07-05T11:01:10Z"},{"alias_kind":"pith_short_12","alias_value":"WTAUZOHFTPVD","created_at":"2026-07-05T11:01:10Z"},{"alias_kind":"pith_short_16","alias_value":"WTAUZOHFTPVDNLUN","created_at":"2026-07-05T11:01:10Z"},{"alias_kind":"pith_short_8","alias_value":"WTAUZOHF","created_at":"2026-07-05T11:01:10Z"}],"graph_snapshots":[{"event_id":"sha256:0104ff67808e0346eb2c3ef08445cb4dbd09866f23be9465b5a0fb3077ed8520","target":"graph","created_at":"2026-07-05T11:01:10Z","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/2505.06475/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate in-context learning (ICL) through a meticulous experimental framework that systematically varies task complexity and model architecture. Extending beyond the linear regression baseline, we introduce Gaussian kernel regression and nonlinear dynamical system tasks, which emphasize temporal and recursive reasoning. We evaluate four distinct models: a GPT2-style Transformer, a Transformer with FlashAttention mechanism, a convolutional Hyena-based model, and the Mamba state-space model. Each model is trained from scratch on synthetic datasets and assessed for generalization during te","authors_text":"Binwen Liu, Peiyu Xu, Quan Yuan, Yihong Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-10T00:22:40Z","title":"Probing In-Context Learning: Impact of Task Complexity and Model Architecture on Generalization and Efficiency"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06475","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:b4876eb07053914ea8a1806d1af698c7830431a3d0546d684269a6a073dcc9a0","target":"record","created_at":"2026-07-05T11:01:10Z","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":"ccefeb6ea506bf3ad0bb93ac62f6b73cec5f40310f1d184cb429ac2cf23b66bb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-10T00:22:40Z","title_canon_sha256":"54ee1d1557187e6af25c78c882b28cd80d3580475e009aa292cb61b819d1bd75"},"schema_version":"1.0","source":{"id":"2505.06475","kind":"arxiv","version":1}},"canonical_sha256":"b4c14cb8e59bea36ae8dc2d1c42e03897679294a58f72cf75b860da6fbb51768","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4c14cb8e59bea36ae8dc2d1c42e03897679294a58f72cf75b860da6fbb51768","first_computed_at":"2026-07-05T11:01:10.173816Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:10.173816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jqwbaFtCn1efbDvVoqeNBS/jNW7kDsI004GhZzpy6EVJXrtFJIEGg3wQ74B2BGkQ6rGnEO1On35yABXpICfJDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:10.174304Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.06475","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4876eb07053914ea8a1806d1af698c7830431a3d0546d684269a6a073dcc9a0","sha256:0104ff67808e0346eb2c3ef08445cb4dbd09866f23be9465b5a0fb3077ed8520"],"state_sha256":"8b65e091c17b2ff3a0368f3438573026526264578dd7d14c030d4dcc28d66c81"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nujY0gGh3SjpUdjU7XUezpNDZm+UIqNgcpDwrXjADIxY9nHeyenS4E5orBT72wZutMLSqMB6XyElwsuw/BHpBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:49:40.007194Z","bundle_sha256":"58550dbf23b8aecd4e38757854c879da8e036411217dbc0744bb3e2ab6b0dfc8"}}