{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:LZFEQJUGEGONUZ62TUHFI3WPEO","short_pith_number":"pith:LZFEQJUG","canonical_record":{"source":{"id":"2312.09299","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-14T19:08:56Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"22743095bcb8c20bc5aed95f63da66977baefc16c148d303c6c8e3456e4dbc03","abstract_canon_sha256":"ca707a4f83c234d411edb80aa38e46be683473d2a0c1f7944db2f7fe9e5fe089"},"schema_version":"1.0"},"canonical_sha256":"5e4a482686219cda67da9d0e546ecf238ef8aa083838cbd42d0f5ebedefaabf7","source":{"kind":"arxiv","id":"2312.09299","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.09299","created_at":"2026-07-05T07:24:22Z"},{"alias_kind":"arxiv_version","alias_value":"2312.09299v1","created_at":"2026-07-05T07:24:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.09299","created_at":"2026-07-05T07:24:22Z"},{"alias_kind":"pith_short_12","alias_value":"LZFEQJUGEGON","created_at":"2026-07-05T07:24:22Z"},{"alias_kind":"pith_short_16","alias_value":"LZFEQJUGEGONUZ62","created_at":"2026-07-05T07:24:22Z"},{"alias_kind":"pith_short_8","alias_value":"LZFEQJUG","created_at":"2026-07-05T07:24:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:LZFEQJUGEGONUZ62TUHFI3WPEO","target":"record","payload":{"canonical_record":{"source":{"id":"2312.09299","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-14T19:08:56Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"22743095bcb8c20bc5aed95f63da66977baefc16c148d303c6c8e3456e4dbc03","abstract_canon_sha256":"ca707a4f83c234d411edb80aa38e46be683473d2a0c1f7944db2f7fe9e5fe089"},"schema_version":"1.0"},"canonical_sha256":"5e4a482686219cda67da9d0e546ecf238ef8aa083838cbd42d0f5ebedefaabf7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:22.946492Z","signature_b64":"GsQR/PwT8dLGz4iJmpXVUwo1gCcBUbjJH/L1h40oMr7xhFZBQJnJTsjX3cq0pC5Fwz1TnxX3VcQANOx1y/l7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e4a482686219cda67da9d0e546ecf238ef8aa083838cbd42d0f5ebedefaabf7","last_reissued_at":"2026-07-05T07:24:22.946006Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:22.946006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.09299","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":"2026-07-05T07:24:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5jIxXvRO8yVJBsx8yyvn5E4e6EGoAW1QdwjGl7/3ctqJp99s1dt1HvGwG+HiRFsyJR2svU6HIDUHO4RvVKOmAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:05:05.395840Z"},"content_sha256":"31bc9ccc663ff1ee24798002ee624a9760ce5151e512fb5a3d1505529486c05f","schema_version":"1.0","event_id":"sha256:31bc9ccc663ff1ee24798002ee624a9760ce5151e512fb5a3d1505529486c05f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:LZFEQJUGEGONUZ62TUHFI3WPEO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Weight subcloning: direct initialization of transformers using larger pretrained ones","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Devang Naik, Fartash Faghri, Mehrdad Farajtabar, Mohammad Rastegari, Mohammad Samragh, Oncel Tuzel, Raviteja Vemulapalli, Sachin Mehta","submitted_at":"2023-12-14T19:08:56Z","abstract_excerpt":"Training large transformer models from scratch for a target task requires lots of data and is computationally demanding. The usual practice of transfer learning overcomes this challenge by initializing the model with weights of a pretrained model of the same size and specification to increase the convergence and training speed. However, what if no pretrained model of the required size is available? In this paper, we introduce a simple yet effective technique to transfer the knowledge of a pretrained model to smaller variants. Our approach called weight subcloning expedites the training of scal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.09299","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/2312.09299/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":"2026-07-05T07:24:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fUhdgY6RAfBcv8GgaXF7xNDCl9ckt17YKEvfBICHfKtQa1aT+qTjonUrkC4u85zSksfktG4hYCNIgnwK54ENCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:05:05.396520Z"},"content_sha256":"fad3868b5bd80844621110089f4a33aa101f5eccadf17df1bd6651a141d07404","schema_version":"1.0","event_id":"sha256:fad3868b5bd80844621110089f4a33aa101f5eccadf17df1bd6651a141d07404"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LZFEQJUGEGONUZ62TUHFI3WPEO/bundle.json","state_url":"https://pith.science/pith/LZFEQJUGEGONUZ62TUHFI3WPEO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LZFEQJUGEGONUZ62TUHFI3WPEO/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":"2026-08-08T22:05:05Z","links":{"resolver":"https://pith.science/pith/LZFEQJUGEGONUZ62TUHFI3WPEO","bundle":"https://pith.science/pith/LZFEQJUGEGONUZ62TUHFI3WPEO/bundle.json","state":"https://pith.science/pith/LZFEQJUGEGONUZ62TUHFI3WPEO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LZFEQJUGEGONUZ62TUHFI3WPEO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LZFEQJUGEGONUZ62TUHFI3WPEO","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":"ca707a4f83c234d411edb80aa38e46be683473d2a0c1f7944db2f7fe9e5fe089","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-14T19:08:56Z","title_canon_sha256":"22743095bcb8c20bc5aed95f63da66977baefc16c148d303c6c8e3456e4dbc03"},"schema_version":"1.0","source":{"id":"2312.09299","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.09299","created_at":"2026-07-05T07:24:22Z"},{"alias_kind":"arxiv_version","alias_value":"2312.09299v1","created_at":"2026-07-05T07:24:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.09299","created_at":"2026-07-05T07:24:22Z"},{"alias_kind":"pith_short_12","alias_value":"LZFEQJUGEGON","created_at":"2026-07-05T07:24:22Z"},{"alias_kind":"pith_short_16","alias_value":"LZFEQJUGEGONUZ62","created_at":"2026-07-05T07:24:22Z"},{"alias_kind":"pith_short_8","alias_value":"LZFEQJUG","created_at":"2026-07-05T07:24:22Z"}],"graph_snapshots":[{"event_id":"sha256:fad3868b5bd80844621110089f4a33aa101f5eccadf17df1bd6651a141d07404","target":"graph","created_at":"2026-07-05T07:24:22Z","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/2312.09299/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training large transformer models from scratch for a target task requires lots of data and is computationally demanding. The usual practice of transfer learning overcomes this challenge by initializing the model with weights of a pretrained model of the same size and specification to increase the convergence and training speed. However, what if no pretrained model of the required size is available? In this paper, we introduce a simple yet effective technique to transfer the knowledge of a pretrained model to smaller variants. Our approach called weight subcloning expedites the training of scal","authors_text":"Devang Naik, Fartash Faghri, Mehrdad Farajtabar, Mohammad Rastegari, Mohammad Samragh, Oncel Tuzel, Raviteja Vemulapalli, Sachin Mehta","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-14T19:08:56Z","title":"Weight subcloning: direct initialization of transformers using larger pretrained ones"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.09299","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":"sha256:31bc9ccc663ff1ee24798002ee624a9760ce5151e512fb5a3d1505529486c05f","target":"record","created_at":"2026-07-05T07:24:22Z","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":"ca707a4f83c234d411edb80aa38e46be683473d2a0c1f7944db2f7fe9e5fe089","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-14T19:08:56Z","title_canon_sha256":"22743095bcb8c20bc5aed95f63da66977baefc16c148d303c6c8e3456e4dbc03"},"schema_version":"1.0","source":{"id":"2312.09299","kind":"arxiv","version":1}},"canonical_sha256":"5e4a482686219cda67da9d0e546ecf238ef8aa083838cbd42d0f5ebedefaabf7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e4a482686219cda67da9d0e546ecf238ef8aa083838cbd42d0f5ebedefaabf7","first_computed_at":"2026-07-05T07:24:22.946006Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:24:22.946006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GsQR/PwT8dLGz4iJmpXVUwo1gCcBUbjJH/L1h40oMr7xhFZBQJnJTsjX3cq0pC5Fwz1TnxX3VcQANOx1y/l7Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T07:24:22.946492Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.09299","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31bc9ccc663ff1ee24798002ee624a9760ce5151e512fb5a3d1505529486c05f","sha256:fad3868b5bd80844621110089f4a33aa101f5eccadf17df1bd6651a141d07404"],"state_sha256":"e68a56a6ca83325a83e68ff356a483d60a65f46c39fb2bb029499951ce9b724f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B9r74CfU2o+OBYD6idO8urqh9jd22cpxAUu0mDfmQatY0r9XCfNncmDj4ABJ7NgSTv9mtCp7corfExYorkY9Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:05:05.401661Z","bundle_sha256":"a5f94b91e6fb93f342fedcec1339f98dfc5d10b5b44c66206b12cf588aa75951"}}