{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NZ3U7IAKB3ARCOA6KVNUVOERKY","short_pith_number":"pith:NZ3U7IAK","canonical_record":{"source":{"id":"2511.04981","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-11-07T04:56:45Z","cross_cats_sorted":[],"title_canon_sha256":"2e61ede94508fea2be88f20cc53b824cfc70f98d717645d9a19951e5d20459a0","abstract_canon_sha256":"1edac4ee97eec4f628d123f1f141174006979975c6fccd4d0d4000bd52460542"},"schema_version":"1.0"},"canonical_sha256":"6e774fa00a0ec111381e555b4ab891561a10b628ccba76f1bdb1bc6afdfb2895","source":{"kind":"arxiv","id":"2511.04981","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.04981","created_at":"2026-06-02T02:04:10Z"},{"alias_kind":"arxiv_version","alias_value":"2511.04981v2","created_at":"2026-06-02T02:04:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.04981","created_at":"2026-06-02T02:04:10Z"},{"alias_kind":"pith_short_12","alias_value":"NZ3U7IAKB3AR","created_at":"2026-06-02T02:04:10Z"},{"alias_kind":"pith_short_16","alias_value":"NZ3U7IAKB3ARCOA6","created_at":"2026-06-02T02:04:10Z"},{"alias_kind":"pith_short_8","alias_value":"NZ3U7IAK","created_at":"2026-06-02T02:04:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NZ3U7IAKB3ARCOA6KVNUVOERKY","target":"record","payload":{"canonical_record":{"source":{"id":"2511.04981","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-11-07T04:56:45Z","cross_cats_sorted":[],"title_canon_sha256":"2e61ede94508fea2be88f20cc53b824cfc70f98d717645d9a19951e5d20459a0","abstract_canon_sha256":"1edac4ee97eec4f628d123f1f141174006979975c6fccd4d0d4000bd52460542"},"schema_version":"1.0"},"canonical_sha256":"6e774fa00a0ec111381e555b4ab891561a10b628ccba76f1bdb1bc6afdfb2895","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:10.532676Z","signature_b64":"lkTusNjUrhYpK9NiPpp1zSvWckbesQwxpqwnsrs1cxoobYbi20OWzplhKRpYZVzqp7gpfuN62oSeOQbzQ8bPAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e774fa00a0ec111381e555b4ab891561a10b628ccba76f1bdb1bc6afdfb2895","last_reissued_at":"2026-06-02T02:04:10.532202Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:10.532202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2511.04981","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":"2026-06-02T02:04:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YfICIbIY5kEE8Z3iUAsIc6MeYBJA/aFY38z/HU8yNXFxearTpK8ndPDpjPhu5A9G6xmZj+NFnEK/uh8/TZgmCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T02:02:59.358395Z"},"content_sha256":"4074c223521b897c8077e59e7034dde0e5ed9d8a098f34c37927b8f69eb0c47e","schema_version":"1.0","event_id":"sha256:4074c223521b897c8077e59e7034dde0e5ed9d8a098f34c37927b8f69eb0c47e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NZ3U7IAKB3ARCOA6KVNUVOERKY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling depth capacity via zero/one-layer model expansion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Zhiqi Bu","submitted_at":"2025-11-07T04:56:45Z","abstract_excerpt":"Model depth is a double-edged sword in deep learning: deeper models achieve higher accuracy but require higher computational cost. To efficiently train models at scale, progressive training (also known as model expansion) scales up model capacity during training and significantly reduces computation with little performance degradation. In this work, we study the depth expansion of large-scale models through the lens of optimization theory and feature learning, offering insights on the initialization of new layers, hyperparameter transfer, learning rate schedule, and timing of model expansion. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.04981","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/2511.04981/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":"2026-06-02T02:04:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y0w8GpussC2OTOU14ks3A+aNtaXOjJBp+zOiCctTFLWwi4U7gjTbhu12Sq40kQ6ziAAmjdHqxtqDqOVEXVdiDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T02:02:59.359112Z"},"content_sha256":"82c7e2e60796ecb97460b300219e8f0213785083edac94e62414f6be10bbf261","schema_version":"1.0","event_id":"sha256:82c7e2e60796ecb97460b300219e8f0213785083edac94e62414f6be10bbf261"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NZ3U7IAKB3ARCOA6KVNUVOERKY/bundle.json","state_url":"https://pith.science/pith/NZ3U7IAKB3ARCOA6KVNUVOERKY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NZ3U7IAKB3ARCOA6KVNUVOERKY/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":"2026-06-08T02:02:59Z","links":{"resolver":"https://pith.science/pith/NZ3U7IAKB3ARCOA6KVNUVOERKY","bundle":"https://pith.science/pith/NZ3U7IAKB3ARCOA6KVNUVOERKY/bundle.json","state":"https://pith.science/pith/NZ3U7IAKB3ARCOA6KVNUVOERKY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NZ3U7IAKB3ARCOA6KVNUVOERKY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NZ3U7IAKB3ARCOA6KVNUVOERKY","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":"1edac4ee97eec4f628d123f1f141174006979975c6fccd4d0d4000bd52460542","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-11-07T04:56:45Z","title_canon_sha256":"2e61ede94508fea2be88f20cc53b824cfc70f98d717645d9a19951e5d20459a0"},"schema_version":"1.0","source":{"id":"2511.04981","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.04981","created_at":"2026-06-02T02:04:10Z"},{"alias_kind":"arxiv_version","alias_value":"2511.04981v2","created_at":"2026-06-02T02:04:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.04981","created_at":"2026-06-02T02:04:10Z"},{"alias_kind":"pith_short_12","alias_value":"NZ3U7IAKB3AR","created_at":"2026-06-02T02:04:10Z"},{"alias_kind":"pith_short_16","alias_value":"NZ3U7IAKB3ARCOA6","created_at":"2026-06-02T02:04:10Z"},{"alias_kind":"pith_short_8","alias_value":"NZ3U7IAK","created_at":"2026-06-02T02:04:10Z"}],"graph_snapshots":[{"event_id":"sha256:82c7e2e60796ecb97460b300219e8f0213785083edac94e62414f6be10bbf261","target":"graph","created_at":"2026-06-02T02:04:10Z","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/2511.04981/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model depth is a double-edged sword in deep learning: deeper models achieve higher accuracy but require higher computational cost. To efficiently train models at scale, progressive training (also known as model expansion) scales up model capacity during training and significantly reduces computation with little performance degradation. In this work, we study the depth expansion of large-scale models through the lens of optimization theory and feature learning, offering insights on the initialization of new layers, hyperparameter transfer, learning rate schedule, and timing of model expansion. ","authors_text":"Zhiqi Bu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-11-07T04:56:45Z","title":"Scaling depth capacity via zero/one-layer model expansion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.04981","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":"sha256:4074c223521b897c8077e59e7034dde0e5ed9d8a098f34c37927b8f69eb0c47e","target":"record","created_at":"2026-06-02T02:04:10Z","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":"1edac4ee97eec4f628d123f1f141174006979975c6fccd4d0d4000bd52460542","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-11-07T04:56:45Z","title_canon_sha256":"2e61ede94508fea2be88f20cc53b824cfc70f98d717645d9a19951e5d20459a0"},"schema_version":"1.0","source":{"id":"2511.04981","kind":"arxiv","version":2}},"canonical_sha256":"6e774fa00a0ec111381e555b4ab891561a10b628ccba76f1bdb1bc6afdfb2895","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e774fa00a0ec111381e555b4ab891561a10b628ccba76f1bdb1bc6afdfb2895","first_computed_at":"2026-06-02T02:04:10.532202Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:10.532202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lkTusNjUrhYpK9NiPpp1zSvWckbesQwxpqwnsrs1cxoobYbi20OWzplhKRpYZVzqp7gpfuN62oSeOQbzQ8bPAw==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:10.532676Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.04981","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4074c223521b897c8077e59e7034dde0e5ed9d8a098f34c37927b8f69eb0c47e","sha256:82c7e2e60796ecb97460b300219e8f0213785083edac94e62414f6be10bbf261"],"state_sha256":"2aa9bf3fe2f7be466a0ed6b4a713bd15782712d9baa3437907095ed7e29698fe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1fuG3hMrpLM3rGfRYlEu3Y3eKTcutZZiedS9cC8HjMGMvjzNQtq3tKy/W9ejNA1gfa8jnxV+4xIVPN4qzvRhBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T02:02:59.362772Z","bundle_sha256":"d51962fd207c00a61ab451f5d2b6544ccac6c433b9cdb9e5328001ad45d2e978"}}