{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DAX7WQUBBTGGZYDAPAMW6EIAJQ","short_pith_number":"pith:DAX7WQUB","canonical_record":{"source":{"id":"2401.12200","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-22T18:39:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"840c4a1258673091dbceb3a9d87dfefc62b6f8810d49feea74de654315db8f99","abstract_canon_sha256":"94eab2a320ca32d26d16aa8411dcff9747298be5921c8bf34b2cdf0032a1ff85"},"schema_version":"1.0"},"canonical_sha256":"182ffb42810ccc6ce06078196f11004c041c6468bcceed0785bbc6ab32c75eb9","source":{"kind":"arxiv","id":"2401.12200","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.12200","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"arxiv_version","alias_value":"2401.12200v2","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12200","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"pith_short_12","alias_value":"DAX7WQUBBTGG","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"pith_short_16","alias_value":"DAX7WQUBBTGGZYDA","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"pith_short_8","alias_value":"DAX7WQUB","created_at":"2026-07-05T08:27:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DAX7WQUBBTGGZYDAPAMW6EIAJQ","target":"record","payload":{"canonical_record":{"source":{"id":"2401.12200","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-22T18:39:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"840c4a1258673091dbceb3a9d87dfefc62b6f8810d49feea74de654315db8f99","abstract_canon_sha256":"94eab2a320ca32d26d16aa8411dcff9747298be5921c8bf34b2cdf0032a1ff85"},"schema_version":"1.0"},"canonical_sha256":"182ffb42810ccc6ce06078196f11004c041c6468bcceed0785bbc6ab32c75eb9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:02.708733Z","signature_b64":"9m/c6xbCUwf/xGExn4azW7fG/CfQUeX897Y+SAjsjpl530C2Nbmusdq38IQbG3cgw1ehzggUS69eKbXPQTX+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"182ffb42810ccc6ce06078196f11004c041c6468bcceed0785bbc6ab32c75eb9","last_reissued_at":"2026-07-05T08:27:02.708245Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:02.708245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.12200","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":"2026-07-05T08:27:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1sUJsSYwDgMdz6o1MnTn57sfAbvfyy9qf3kccTT1zD5ncYGs3haFc1JMa/ZxpKbTdXlMQ9wW+EhLuBujTkC1Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:04:51.070750Z"},"content_sha256":"42a9711485463db887f710b221fb0a99afe74ab27048ea6895ffbd29aac57e89","schema_version":"1.0","event_id":"sha256:42a9711485463db887f710b221fb0a99afe74ab27048ea6895ffbd29aac57e89"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DAX7WQUBBTGGZYDAPAMW6EIAJQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bowen Zhao, Hannaneh Hajishirzi, Qingqing Cao","submitted_at":"2024-01-22T18:39:40Z","abstract_excerpt":"Fine-tuning and inference with large Language Models (LM) are generally known to be expensive. Parameter-efficient fine-tuning over pretrained LMs reduces training memory by updating a small number of LM parameters but does not improve inference efficiency. Structured pruning improves LM inference efficiency by removing consistent parameter blocks, yet often increases training memory and time. To improve both training and inference efficiency, we introduce APT that adaptively prunes and tunes parameters for the LMs. At the early stage of fine-tuning, APT dynamically adds salient tuning paramet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12200","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/2401.12200/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":"2026-07-05T08:27:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D+OxCo4BXrrqU49KcYTjY5BNC26xW+Awk1jHKt5nbm2DxS6CO34SYKrDUuTZRixZKPYfjf5uMyqPMHk8chXNDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:04:51.071332Z"},"content_sha256":"9f51e3b3d48d4cac7a9d5b18709bc9ca68adc02fdf081959638a30365fdf04eb","schema_version":"1.0","event_id":"sha256:9f51e3b3d48d4cac7a9d5b18709bc9ca68adc02fdf081959638a30365fdf04eb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DAX7WQUBBTGGZYDAPAMW6EIAJQ/bundle.json","state_url":"https://pith.science/pith/DAX7WQUBBTGGZYDAPAMW6EIAJQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DAX7WQUBBTGGZYDAPAMW6EIAJQ/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":"2026-08-06T09:04:51Z","links":{"resolver":"https://pith.science/pith/DAX7WQUBBTGGZYDAPAMW6EIAJQ","bundle":"https://pith.science/pith/DAX7WQUBBTGGZYDAPAMW6EIAJQ/bundle.json","state":"https://pith.science/pith/DAX7WQUBBTGGZYDAPAMW6EIAJQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DAX7WQUBBTGGZYDAPAMW6EIAJQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DAX7WQUBBTGGZYDAPAMW6EIAJQ","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":"94eab2a320ca32d26d16aa8411dcff9747298be5921c8bf34b2cdf0032a1ff85","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-22T18:39:40Z","title_canon_sha256":"840c4a1258673091dbceb3a9d87dfefc62b6f8810d49feea74de654315db8f99"},"schema_version":"1.0","source":{"id":"2401.12200","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.12200","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"arxiv_version","alias_value":"2401.12200v2","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12200","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"pith_short_12","alias_value":"DAX7WQUBBTGG","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"pith_short_16","alias_value":"DAX7WQUBBTGGZYDA","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"pith_short_8","alias_value":"DAX7WQUB","created_at":"2026-07-05T08:27:02Z"}],"graph_snapshots":[{"event_id":"sha256:9f51e3b3d48d4cac7a9d5b18709bc9ca68adc02fdf081959638a30365fdf04eb","target":"graph","created_at":"2026-07-05T08:27:02Z","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/2401.12200/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning and inference with large Language Models (LM) are generally known to be expensive. Parameter-efficient fine-tuning over pretrained LMs reduces training memory by updating a small number of LM parameters but does not improve inference efficiency. Structured pruning improves LM inference efficiency by removing consistent parameter blocks, yet often increases training memory and time. To improve both training and inference efficiency, we introduce APT that adaptively prunes and tunes parameters for the LMs. At the early stage of fine-tuning, APT dynamically adds salient tuning paramet","authors_text":"Bowen Zhao, Hannaneh Hajishirzi, Qingqing Cao","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-22T18:39:40Z","title":"APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12200","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":"sha256:42a9711485463db887f710b221fb0a99afe74ab27048ea6895ffbd29aac57e89","target":"record","created_at":"2026-07-05T08:27:02Z","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":"94eab2a320ca32d26d16aa8411dcff9747298be5921c8bf34b2cdf0032a1ff85","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-22T18:39:40Z","title_canon_sha256":"840c4a1258673091dbceb3a9d87dfefc62b6f8810d49feea74de654315db8f99"},"schema_version":"1.0","source":{"id":"2401.12200","kind":"arxiv","version":2}},"canonical_sha256":"182ffb42810ccc6ce06078196f11004c041c6468bcceed0785bbc6ab32c75eb9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"182ffb42810ccc6ce06078196f11004c041c6468bcceed0785bbc6ab32c75eb9","first_computed_at":"2026-07-05T08:27:02.708245Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:02.708245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9m/c6xbCUwf/xGExn4azW7fG/CfQUeX897Y+SAjsjpl530C2Nbmusdq38IQbG3cgw1ehzggUS69eKbXPQTX+DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:02.708733Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.12200","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42a9711485463db887f710b221fb0a99afe74ab27048ea6895ffbd29aac57e89","sha256:9f51e3b3d48d4cac7a9d5b18709bc9ca68adc02fdf081959638a30365fdf04eb"],"state_sha256":"99a1ecba623530a23feb39ae8c67064bc7d7f1d75f7721ace2155c9c9e008a5c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u4ev2P6LUD2liitCS57uppf7muP2hDfJCa5JmdpGe0vH9WQrWN5mI8O22nMHgFbvhm00gz5JcpGVNjmjLmxtCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T09:04:51.074735Z","bundle_sha256":"90286937a2afab9f819644dd2540893e84ae1e7209b7328fd8a4478b03dccb02"}}