{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:G6G37HBXJFFQIPG7A5D5D5XSSO","short_pith_number":"pith:G6G37HBX","canonical_record":{"source":{"id":"2412.06245","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-09T06:37:35Z","cross_cats_sorted":[],"title_canon_sha256":"d3b0752be883568ce7b16aa792729f01f82696fc52c76aee501e2a5cda8c38aa","abstract_canon_sha256":"57bc03101cc51cbe62bf75b665d0badfe809197f9412b297858f7ade89af82cc"},"schema_version":"1.0"},"canonical_sha256":"378dbf9c37494b043cdf0747d1f6f29381ca291fe1cf50095be9081fde6e9559","source":{"kind":"arxiv","id":"2412.06245","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06245","created_at":"2026-07-05T11:05:37Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06245v2","created_at":"2026-07-05T11:05:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06245","created_at":"2026-07-05T11:05:37Z"},{"alias_kind":"pith_short_12","alias_value":"G6G37HBXJFFQ","created_at":"2026-07-05T11:05:37Z"},{"alias_kind":"pith_short_16","alias_value":"G6G37HBXJFFQIPG7","created_at":"2026-07-05T11:05:37Z"},{"alias_kind":"pith_short_8","alias_value":"G6G37HBX","created_at":"2026-07-05T11:05:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:G6G37HBXJFFQIPG7A5D5D5XSSO","target":"record","payload":{"canonical_record":{"source":{"id":"2412.06245","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-09T06:37:35Z","cross_cats_sorted":[],"title_canon_sha256":"d3b0752be883568ce7b16aa792729f01f82696fc52c76aee501e2a5cda8c38aa","abstract_canon_sha256":"57bc03101cc51cbe62bf75b665d0badfe809197f9412b297858f7ade89af82cc"},"schema_version":"1.0"},"canonical_sha256":"378dbf9c37494b043cdf0747d1f6f29381ca291fe1cf50095be9081fde6e9559","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:37.159458Z","signature_b64":"FW7Vh4EWXMWzQlPVHH52QrUoN/SrIBKxB+Uu2hEiuY+pP9dMM+GOOJenY3akQGL3uZKXT/JscZOasDqfuqY7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"378dbf9c37494b043cdf0747d1f6f29381ca291fe1cf50095be9081fde6e9559","last_reissued_at":"2026-07-05T11:05:37.158981Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:37.158981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.06245","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":"2026-07-05T11:05:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MuBDOQyFrgu6Wy0cC7JRfgqiXJ9o/Xaq4Q3ZbaHtNu0fU3hGpRym6QMGRDOhycDphuciQBAnuq42CzhYj2CLBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T04:36:25.253216Z"},"content_sha256":"65ad9a295d9ac5f63d8970ae2db737f329a1c6f6445e1480dbfb7d5cb7ef4200","schema_version":"1.0","event_id":"sha256:65ad9a295d9ac5f63d8970ae2db737f329a1c6f6445e1480dbfb7d5cb7ef4200"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:G6G37HBXJFFQIPG7A5D5D5XSSO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Comparative Study of Learning Paradigms in Large Language Models via Intrinsic Dimension","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Saahith Janapati, Yangfeng Ji","submitted_at":"2024-12-09T06:37:35Z","abstract_excerpt":"The performance of Large Language Models (LLMs) on natural language tasks can be improved through both supervised fine-tuning (SFT) and in-context learning (ICL), which operate via distinct mechanisms. Supervised fine-tuning updates the model's weights by minimizing loss on training data, whereas in-context learning leverages task demonstrations embedded in the prompt, without changing the model's parameters. This study investigates the effects of these learning paradigms on the hidden representations of LLMs using Intrinsic Dimension (ID). We use ID to estimate the number of degrees of freedo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06245","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/2412.06245/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":"2026-07-05T11:05:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AxQdoKkAD7hDIvsrN+XV+WXZO6qs5nALaOZ5RjLycG+gEgEMM9wi0aZ17Di4KMX1qPGFtgR3K0p/isxRLs8eDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T04:36:25.253597Z"},"content_sha256":"932e2c269b2034e6d9fda4c20176daae1d43c7ad26054568cb40044acf77c87b","schema_version":"1.0","event_id":"sha256:932e2c269b2034e6d9fda4c20176daae1d43c7ad26054568cb40044acf77c87b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G6G37HBXJFFQIPG7A5D5D5XSSO/bundle.json","state_url":"https://pith.science/pith/G6G37HBXJFFQIPG7A5D5D5XSSO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G6G37HBXJFFQIPG7A5D5D5XSSO/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":"2026-07-21T04:36:25Z","links":{"resolver":"https://pith.science/pith/G6G37HBXJFFQIPG7A5D5D5XSSO","bundle":"https://pith.science/pith/G6G37HBXJFFQIPG7A5D5D5XSSO/bundle.json","state":"https://pith.science/pith/G6G37HBXJFFQIPG7A5D5D5XSSO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G6G37HBXJFFQIPG7A5D5D5XSSO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:G6G37HBXJFFQIPG7A5D5D5XSSO","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":"57bc03101cc51cbe62bf75b665d0badfe809197f9412b297858f7ade89af82cc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-09T06:37:35Z","title_canon_sha256":"d3b0752be883568ce7b16aa792729f01f82696fc52c76aee501e2a5cda8c38aa"},"schema_version":"1.0","source":{"id":"2412.06245","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06245","created_at":"2026-07-05T11:05:37Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06245v2","created_at":"2026-07-05T11:05:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06245","created_at":"2026-07-05T11:05:37Z"},{"alias_kind":"pith_short_12","alias_value":"G6G37HBXJFFQ","created_at":"2026-07-05T11:05:37Z"},{"alias_kind":"pith_short_16","alias_value":"G6G37HBXJFFQIPG7","created_at":"2026-07-05T11:05:37Z"},{"alias_kind":"pith_short_8","alias_value":"G6G37HBX","created_at":"2026-07-05T11:05:37Z"}],"graph_snapshots":[{"event_id":"sha256:932e2c269b2034e6d9fda4c20176daae1d43c7ad26054568cb40044acf77c87b","target":"graph","created_at":"2026-07-05T11:05:37Z","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/2412.06245/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The performance of Large Language Models (LLMs) on natural language tasks can be improved through both supervised fine-tuning (SFT) and in-context learning (ICL), which operate via distinct mechanisms. Supervised fine-tuning updates the model's weights by minimizing loss on training data, whereas in-context learning leverages task demonstrations embedded in the prompt, without changing the model's parameters. This study investigates the effects of these learning paradigms on the hidden representations of LLMs using Intrinsic Dimension (ID). We use ID to estimate the number of degrees of freedo","authors_text":"Saahith Janapati, Yangfeng Ji","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-09T06:37:35Z","title":"A Comparative Study of Learning Paradigms in Large Language Models via Intrinsic Dimension"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06245","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":"sha256:65ad9a295d9ac5f63d8970ae2db737f329a1c6f6445e1480dbfb7d5cb7ef4200","target":"record","created_at":"2026-07-05T11:05:37Z","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":"57bc03101cc51cbe62bf75b665d0badfe809197f9412b297858f7ade89af82cc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-09T06:37:35Z","title_canon_sha256":"d3b0752be883568ce7b16aa792729f01f82696fc52c76aee501e2a5cda8c38aa"},"schema_version":"1.0","source":{"id":"2412.06245","kind":"arxiv","version":2}},"canonical_sha256":"378dbf9c37494b043cdf0747d1f6f29381ca291fe1cf50095be9081fde6e9559","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"378dbf9c37494b043cdf0747d1f6f29381ca291fe1cf50095be9081fde6e9559","first_computed_at":"2026-07-05T11:05:37.158981Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:37.158981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FW7Vh4EWXMWzQlPVHH52QrUoN/SrIBKxB+Uu2hEiuY+pP9dMM+GOOJenY3akQGL3uZKXT/JscZOasDqfuqY7Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:37.159458Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.06245","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65ad9a295d9ac5f63d8970ae2db737f329a1c6f6445e1480dbfb7d5cb7ef4200","sha256:932e2c269b2034e6d9fda4c20176daae1d43c7ad26054568cb40044acf77c87b"],"state_sha256":"207bb3d58e40005c714a334276794f302831c8f8b379bd60728da7e302f65aee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0J148ny4zbyVZuq2/ZDgIcZYlL0fdWoVZDjXVdcArDdRQDO8bjAZ8mTbjUAXd/kx5pAKEZEt9CfU7tc1kNIlAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-21T04:36:25.256049Z","bundle_sha256":"b5a55e751fb73649263f46f236e0389d22e9c6faaa79a803c28715a53d18f7e6"}}