{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NOMXBGWQV6XYVGNIXUTZYD7M7V","short_pith_number":"pith:NOMXBGWQ","canonical_record":{"source":{"id":"2503.05920","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-07T20:35:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"eac60449e7fa6d794cca257ea6b7bc8f44df5a46a546ec117f3cb02a8ad850b3","abstract_canon_sha256":"66e5c4a42357511a77bb7e5c18e38ac9a83055115d7437b288d0492ddd363f6e"},"schema_version":"1.0"},"canonical_sha256":"6b99709ad0afaf8a99a8bd279c0fecfd5bef5d534e33b2d02401db25e2351449","source":{"kind":"arxiv","id":"2503.05920","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.05920","created_at":"2026-07-05T10:26:49Z"},{"alias_kind":"arxiv_version","alias_value":"2503.05920v1","created_at":"2026-07-05T10:26:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.05920","created_at":"2026-07-05T10:26:49Z"},{"alias_kind":"pith_short_12","alias_value":"NOMXBGWQV6XY","created_at":"2026-07-05T10:26:49Z"},{"alias_kind":"pith_short_16","alias_value":"NOMXBGWQV6XYVGNI","created_at":"2026-07-05T10:26:49Z"},{"alias_kind":"pith_short_8","alias_value":"NOMXBGWQ","created_at":"2026-07-05T10:26:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NOMXBGWQV6XYVGNIXUTZYD7M7V","target":"record","payload":{"canonical_record":{"source":{"id":"2503.05920","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-07T20:35:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"eac60449e7fa6d794cca257ea6b7bc8f44df5a46a546ec117f3cb02a8ad850b3","abstract_canon_sha256":"66e5c4a42357511a77bb7e5c18e38ac9a83055115d7437b288d0492ddd363f6e"},"schema_version":"1.0"},"canonical_sha256":"6b99709ad0afaf8a99a8bd279c0fecfd5bef5d534e33b2d02401db25e2351449","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:49.284566Z","signature_b64":"WQ+PaAgf1sX++N+0FOzsB6P675nclEVEfCPsMjgURm7VRKzdhUI8+rqpsDo1eF22aBA7RUXInOby8RitITLuAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b99709ad0afaf8a99a8bd279c0fecfd5bef5d534e33b2d02401db25e2351449","last_reissued_at":"2026-07-05T10:26:49.284073Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:49.284073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.05920","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":"2026-07-05T10:26:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mKyhY90c5r+mL9sKrrchT3tdGZ5OJw7fi5lvFF4wJrrG1LHlhckvWYqxIiUf4qUQpVV84/7PHg7B3R+Hjhx+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T05:50:27.489156Z"},"content_sha256":"a2b540995b8504618862501e339c6be501cb91e7899768213aad9858a3ca4882","schema_version":"1.0","event_id":"sha256:a2b540995b8504618862501e339c6be501cb91e7899768213aad9858a3ca4882"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NOMXBGWQV6XYVGNIXUTZYD7M7V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"IDEA Prune: An Integrated Enlarge-and-Prune Pipeline in Generative Language Model Pretraining","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ajay Jaiswal, Chong Wang, Jianyu Wang, Tao Lei, Tuo Zhao, Xianzhi Du, Yixiao Li","submitted_at":"2025-03-07T20:35:31Z","abstract_excerpt":"Recent advancements in large language models have intensified the need for efficient and deployable models within limited inference budgets. Structured pruning pipelines have shown promise in token efficiency compared to training target-size models from scratch. In this paper, we advocate incorporating enlarged model pretraining, which is often ignored in previous works, into pruning. We study the enlarge-and-prune pipeline as an integrated system to address two critical questions: whether it is worth pretraining an enlarged model even when the model is never deployed, and how to optimize the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.05920","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/2503.05920/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":"2026-07-05T10:26:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eLppzu10635ad7JzWQHjRGgJ0lQ/T169J3EybFBv87XpR7Ssvg9BF5X7KhfJk7jmyiNHRXrViWt5gP2GDGL7Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T05:50:27.489670Z"},"content_sha256":"b00b4be8bf0350ae6b76c6bb725db0888be651160bb1568b8f2a82718a13a803","schema_version":"1.0","event_id":"sha256:b00b4be8bf0350ae6b76c6bb725db0888be651160bb1568b8f2a82718a13a803"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NOMXBGWQV6XYVGNIXUTZYD7M7V/bundle.json","state_url":"https://pith.science/pith/NOMXBGWQV6XYVGNIXUTZYD7M7V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NOMXBGWQV6XYVGNIXUTZYD7M7V/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":"2026-08-11T05:50:27Z","links":{"resolver":"https://pith.science/pith/NOMXBGWQV6XYVGNIXUTZYD7M7V","bundle":"https://pith.science/pith/NOMXBGWQV6XYVGNIXUTZYD7M7V/bundle.json","state":"https://pith.science/pith/NOMXBGWQV6XYVGNIXUTZYD7M7V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NOMXBGWQV6XYVGNIXUTZYD7M7V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NOMXBGWQV6XYVGNIXUTZYD7M7V","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":"66e5c4a42357511a77bb7e5c18e38ac9a83055115d7437b288d0492ddd363f6e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-07T20:35:31Z","title_canon_sha256":"eac60449e7fa6d794cca257ea6b7bc8f44df5a46a546ec117f3cb02a8ad850b3"},"schema_version":"1.0","source":{"id":"2503.05920","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.05920","created_at":"2026-07-05T10:26:49Z"},{"alias_kind":"arxiv_version","alias_value":"2503.05920v1","created_at":"2026-07-05T10:26:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.05920","created_at":"2026-07-05T10:26:49Z"},{"alias_kind":"pith_short_12","alias_value":"NOMXBGWQV6XY","created_at":"2026-07-05T10:26:49Z"},{"alias_kind":"pith_short_16","alias_value":"NOMXBGWQV6XYVGNI","created_at":"2026-07-05T10:26:49Z"},{"alias_kind":"pith_short_8","alias_value":"NOMXBGWQ","created_at":"2026-07-05T10:26:49Z"}],"graph_snapshots":[{"event_id":"sha256:b00b4be8bf0350ae6b76c6bb725db0888be651160bb1568b8f2a82718a13a803","target":"graph","created_at":"2026-07-05T10:26:49Z","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/2503.05920/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in large language models have intensified the need for efficient and deployable models within limited inference budgets. Structured pruning pipelines have shown promise in token efficiency compared to training target-size models from scratch. In this paper, we advocate incorporating enlarged model pretraining, which is often ignored in previous works, into pruning. We study the enlarge-and-prune pipeline as an integrated system to address two critical questions: whether it is worth pretraining an enlarged model even when the model is never deployed, and how to optimize the ","authors_text":"Ajay Jaiswal, Chong Wang, Jianyu Wang, Tao Lei, Tuo Zhao, Xianzhi Du, Yixiao Li","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-07T20:35:31Z","title":"IDEA Prune: An Integrated Enlarge-and-Prune Pipeline in Generative Language Model Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.05920","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:a2b540995b8504618862501e339c6be501cb91e7899768213aad9858a3ca4882","target":"record","created_at":"2026-07-05T10:26:49Z","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":"66e5c4a42357511a77bb7e5c18e38ac9a83055115d7437b288d0492ddd363f6e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-07T20:35:31Z","title_canon_sha256":"eac60449e7fa6d794cca257ea6b7bc8f44df5a46a546ec117f3cb02a8ad850b3"},"schema_version":"1.0","source":{"id":"2503.05920","kind":"arxiv","version":1}},"canonical_sha256":"6b99709ad0afaf8a99a8bd279c0fecfd5bef5d534e33b2d02401db25e2351449","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b99709ad0afaf8a99a8bd279c0fecfd5bef5d534e33b2d02401db25e2351449","first_computed_at":"2026-07-05T10:26:49.284073Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:26:49.284073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WQ+PaAgf1sX++N+0FOzsB6P675nclEVEfCPsMjgURm7VRKzdhUI8+rqpsDo1eF22aBA7RUXInOby8RitITLuAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:26:49.284566Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.05920","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a2b540995b8504618862501e339c6be501cb91e7899768213aad9858a3ca4882","sha256:b00b4be8bf0350ae6b76c6bb725db0888be651160bb1568b8f2a82718a13a803"],"state_sha256":"c2fb8f9ace12fb79007e9018bd64534d273140a8d79893c075ca5fac91e7bd06"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"10215aK370QfeygsHHeuqduVGWV65OQnK+wEELJjik+zY4rgf9C9xxJj4b0l21tHXkcVXXb9BIFFS+Qbps/iDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T05:50:27.494132Z","bundle_sha256":"40f070f3f1222999875f3a479252cd72154ec57c8a61189fe222583637616c5f"}}