{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HJM4MS3LGLURBHDSCKBZAK6O4P","short_pith_number":"pith:HJM4MS3L","canonical_record":{"source":{"id":"2410.23743","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T08:58:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c636f807ff69be9f06c21641802608580cd280c2eb8b738c6fc28f81b7e60763","abstract_canon_sha256":"e420d4ddfe804490544eded33d8d27592bd2fbd7a1d38c6c46c589d1cd1f19c8"},"schema_version":"1.0"},"canonical_sha256":"3a59c64b6b32e9109c721283902bcee3fb0a37c6239d0bcef3af30cc24532b22","source":{"kind":"arxiv","id":"2410.23743","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.23743","created_at":"2026-07-05T11:16:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.23743v2","created_at":"2026-07-05T11:16:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23743","created_at":"2026-07-05T11:16:04Z"},{"alias_kind":"pith_short_12","alias_value":"HJM4MS3LGLUR","created_at":"2026-07-05T11:16:04Z"},{"alias_kind":"pith_short_16","alias_value":"HJM4MS3LGLURBHDS","created_at":"2026-07-05T11:16:04Z"},{"alias_kind":"pith_short_8","alias_value":"HJM4MS3L","created_at":"2026-07-05T11:16:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HJM4MS3LGLURBHDSCKBZAK6O4P","target":"record","payload":{"canonical_record":{"source":{"id":"2410.23743","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T08:58:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c636f807ff69be9f06c21641802608580cd280c2eb8b738c6fc28f81b7e60763","abstract_canon_sha256":"e420d4ddfe804490544eded33d8d27592bd2fbd7a1d38c6c46c589d1cd1f19c8"},"schema_version":"1.0"},"canonical_sha256":"3a59c64b6b32e9109c721283902bcee3fb0a37c6239d0bcef3af30cc24532b22","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:04.445130Z","signature_b64":"JeAY22SenNk2gn5fCsWUF6leyAKiXoARyU8krmeTdPh3tulAVfni7MlLA/ZKw+lvQan3qBmVTfNgOVzmf9oUAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a59c64b6b32e9109c721283902bcee3fb0a37c6239d0bcef3af30cc24532b22","last_reissued_at":"2026-07-05T11:16:04.444403Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:04.444403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.23743","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":"2026-07-05T11:16:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xg3qMvWYwMgAjkmHZiOtdTZtB1yM4YMOmv/9mEnwdidI9Gxh4abR5/S7CCMDBHBmjhD2rteG8bUGOGDzV07EBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:03:33.190557Z"},"content_sha256":"c0b7082c001a0deb6dbe67c7ef2be65aa2cecfc89f716e1b3aeef7ff027baf0f","schema_version":"1.0","event_id":"sha256:c0b7082c001a0deb6dbe67c7ef2be65aa2cecfc89f716e1b3aeef7ff027baf0f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HJM4MS3LGLURBHDSCKBZAK6O4P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ming Li, Tianyi Zhou, Yanhong Li","submitted_at":"2024-10-31T08:58:06Z","abstract_excerpt":"What makes a difference in the post-training of LLMs? We investigate the training patterns of different layers in large language models (LLMs) through the lens of the gradient. We are specifically interested in how fast vs. slow thinking affects the layer-wise gradients, given the recent popularity of training LLMs on reasoning paths such as chain-of-thoughts (CoT) and process rewards. In our study, fast thinking without CoT leads to larger gradients and larger differences of gradients across layers than slow thinking (Detailed CoT), indicating the learning stability brought by the latter. Add"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23743","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/2410.23743/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":"2026-07-05T11:16:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C/ljqtgxkbZdiKm9BHhLB0Xg162r0pszvTm073SAYC8dlHXtWap1U6Foagix1MoFUzwROktDYMakFnI66DCmBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:03:33.191124Z"},"content_sha256":"33b334921e83f0e7e3ced858a3739f3bca37c381c2a73c5a351bfd9b88e6d905","schema_version":"1.0","event_id":"sha256:33b334921e83f0e7e3ced858a3739f3bca37c381c2a73c5a351bfd9b88e6d905"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HJM4MS3LGLURBHDSCKBZAK6O4P/bundle.json","state_url":"https://pith.science/pith/HJM4MS3LGLURBHDSCKBZAK6O4P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HJM4MS3LGLURBHDSCKBZAK6O4P/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":"2026-08-08T04:03:33Z","links":{"resolver":"https://pith.science/pith/HJM4MS3LGLURBHDSCKBZAK6O4P","bundle":"https://pith.science/pith/HJM4MS3LGLURBHDSCKBZAK6O4P/bundle.json","state":"https://pith.science/pith/HJM4MS3LGLURBHDSCKBZAK6O4P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HJM4MS3LGLURBHDSCKBZAK6O4P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HJM4MS3LGLURBHDSCKBZAK6O4P","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":"e420d4ddfe804490544eded33d8d27592bd2fbd7a1d38c6c46c589d1cd1f19c8","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T08:58:06Z","title_canon_sha256":"c636f807ff69be9f06c21641802608580cd280c2eb8b738c6fc28f81b7e60763"},"schema_version":"1.0","source":{"id":"2410.23743","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.23743","created_at":"2026-07-05T11:16:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.23743v2","created_at":"2026-07-05T11:16:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23743","created_at":"2026-07-05T11:16:04Z"},{"alias_kind":"pith_short_12","alias_value":"HJM4MS3LGLUR","created_at":"2026-07-05T11:16:04Z"},{"alias_kind":"pith_short_16","alias_value":"HJM4MS3LGLURBHDS","created_at":"2026-07-05T11:16:04Z"},{"alias_kind":"pith_short_8","alias_value":"HJM4MS3L","created_at":"2026-07-05T11:16:04Z"}],"graph_snapshots":[{"event_id":"sha256:33b334921e83f0e7e3ced858a3739f3bca37c381c2a73c5a351bfd9b88e6d905","target":"graph","created_at":"2026-07-05T11:16:04Z","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/2410.23743/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"What makes a difference in the post-training of LLMs? We investigate the training patterns of different layers in large language models (LLMs) through the lens of the gradient. We are specifically interested in how fast vs. slow thinking affects the layer-wise gradients, given the recent popularity of training LLMs on reasoning paths such as chain-of-thoughts (CoT) and process rewards. In our study, fast thinking without CoT leads to larger gradients and larger differences of gradients across layers than slow thinking (Detailed CoT), indicating the learning stability brought by the latter. Add","authors_text":"Ming Li, Tianyi Zhou, Yanhong Li","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T08:58:06Z","title":"What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23743","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:c0b7082c001a0deb6dbe67c7ef2be65aa2cecfc89f716e1b3aeef7ff027baf0f","target":"record","created_at":"2026-07-05T11:16:04Z","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":"e420d4ddfe804490544eded33d8d27592bd2fbd7a1d38c6c46c589d1cd1f19c8","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T08:58:06Z","title_canon_sha256":"c636f807ff69be9f06c21641802608580cd280c2eb8b738c6fc28f81b7e60763"},"schema_version":"1.0","source":{"id":"2410.23743","kind":"arxiv","version":2}},"canonical_sha256":"3a59c64b6b32e9109c721283902bcee3fb0a37c6239d0bcef3af30cc24532b22","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a59c64b6b32e9109c721283902bcee3fb0a37c6239d0bcef3af30cc24532b22","first_computed_at":"2026-07-05T11:16:04.444403Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:04.444403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JeAY22SenNk2gn5fCsWUF6leyAKiXoARyU8krmeTdPh3tulAVfni7MlLA/ZKw+lvQan3qBmVTfNgOVzmf9oUAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:04.445130Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.23743","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0b7082c001a0deb6dbe67c7ef2be65aa2cecfc89f716e1b3aeef7ff027baf0f","sha256:33b334921e83f0e7e3ced858a3739f3bca37c381c2a73c5a351bfd9b88e6d905"],"state_sha256":"aa32e3abb5ca6f0929b6deb41536bd25da0fc59c2e5bff3fcd1454e1379d9180"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5NSdwAyWvZfG0ZJOLCliq75dmzMC//xTlVYqvC6XaNJrX7lf3eyLfxCw9iaoQUL7nD4ER7ot1MOKp0Jn3NESAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T04:03:33.196219Z","bundle_sha256":"21c86806baebbc1d4c40a414ac80bb0ce518bfd8e012a2aa6eae98cebd1134d8"}}