{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NS2EEQJXNUWHYJLTCIL6TKDIVM","short_pith_number":"pith:NS2EEQJX","canonical_record":{"source":{"id":"2407.11681","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-16T12:59:44Z","cross_cats_sorted":[],"title_canon_sha256":"d46590d1af8958e8938f271f187b926586e4b5b3b8ee72a3125cf48f4cf7c781","abstract_canon_sha256":"de5d946276adc77b11c773dcdc04c97f7c638d57327b8e595c6b9e0df01e9b05"},"schema_version":"1.0"},"canonical_sha256":"6cb44241376d2c7c25731217e9a868ab0d6c3cc7bed64946c8eb20ef6ae81389","source":{"kind":"arxiv","id":"2407.11681","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.11681","created_at":"2026-07-05T08:44:27Z"},{"alias_kind":"arxiv_version","alias_value":"2407.11681v1","created_at":"2026-07-05T08:44:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11681","created_at":"2026-07-05T08:44:27Z"},{"alias_kind":"pith_short_12","alias_value":"NS2EEQJXNUWH","created_at":"2026-07-05T08:44:27Z"},{"alias_kind":"pith_short_16","alias_value":"NS2EEQJXNUWHYJLT","created_at":"2026-07-05T08:44:27Z"},{"alias_kind":"pith_short_8","alias_value":"NS2EEQJX","created_at":"2026-07-05T08:44:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NS2EEQJXNUWHYJLTCIL6TKDIVM","target":"record","payload":{"canonical_record":{"source":{"id":"2407.11681","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-16T12:59:44Z","cross_cats_sorted":[],"title_canon_sha256":"d46590d1af8958e8938f271f187b926586e4b5b3b8ee72a3125cf48f4cf7c781","abstract_canon_sha256":"de5d946276adc77b11c773dcdc04c97f7c638d57327b8e595c6b9e0df01e9b05"},"schema_version":"1.0"},"canonical_sha256":"6cb44241376d2c7c25731217e9a868ab0d6c3cc7bed64946c8eb20ef6ae81389","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:27.755017Z","signature_b64":"4YboA9+vxQmVfex/IE75v+ZuiP/VBvhgrzl0vcFmBMaITvPWxGOHGAtD87hRu4gkpdWqEsYoNQTcEJc6rsnCCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cb44241376d2c7c25731217e9a868ab0d6c3cc7bed64946c8eb20ef6ae81389","last_reissued_at":"2026-07-05T08:44:27.754611Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:27.754611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.11681","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":"2026-07-05T08:44:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5hARoQj9+Pl+YntSXAdmbv9zv4wQJkSelRl0yL6Oxr8pRiFifMDsA4P9xEVQBP9izk9FNlWFyeWW/JAqflJIAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T13:57:54.892320Z"},"content_sha256":"feb075ed4b1e0e65c388b0c93bc779e46de1fda26d594ab1a936ac55ce0ca581","schema_version":"1.0","event_id":"sha256:feb075ed4b1e0e65c388b0c93bc779e46de1fda26d594ab1a936ac55ce0ca581"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NS2EEQJXNUWHYJLTCIL6TKDIVM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MINI-LLM: Memory-Efficient Structured Pruning for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongrong Cheng, Javen Qinfeng Shi, Miao Zhang","submitted_at":"2024-07-16T12:59:44Z","abstract_excerpt":"As Large Language Models (LLMs) grow dramatically in size, there is an increasing trend in compressing and speeding up these models. Previous studies have highlighted the usefulness of gradients for importance scoring in neural network compressing, especially in pruning medium-size networks. However, the substantial memory requirements involved in calculating gradients with backpropagation impede the utilization of gradients in guiding LLM pruning. As a result, most pruning strategies for LLMs rely on gradient-free criteria, such as weight magnitudes or a mix of magnitudes and activations. In "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11681","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/2407.11681/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":"2026-07-05T08:44:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"88h9yF7C+Pp2ggrLjEFpiBxJqutQ9LrG5RdgLbNldNkQbrQz8MSaCD6f6/snRXFdpYBbI2a8ngOpYYV9IKSpCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T13:57:54.892811Z"},"content_sha256":"2df55021f9a6a15eb053f0edafa8c992296e0c7e528e2f4a87bc4f970b7bdc06","schema_version":"1.0","event_id":"sha256:2df55021f9a6a15eb053f0edafa8c992296e0c7e528e2f4a87bc4f970b7bdc06"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NS2EEQJXNUWHYJLTCIL6TKDIVM/bundle.json","state_url":"https://pith.science/pith/NS2EEQJXNUWHYJLTCIL6TKDIVM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NS2EEQJXNUWHYJLTCIL6TKDIVM/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":"2026-08-12T13:57:54Z","links":{"resolver":"https://pith.science/pith/NS2EEQJXNUWHYJLTCIL6TKDIVM","bundle":"https://pith.science/pith/NS2EEQJXNUWHYJLTCIL6TKDIVM/bundle.json","state":"https://pith.science/pith/NS2EEQJXNUWHYJLTCIL6TKDIVM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NS2EEQJXNUWHYJLTCIL6TKDIVM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NS2EEQJXNUWHYJLTCIL6TKDIVM","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":"de5d946276adc77b11c773dcdc04c97f7c638d57327b8e595c6b9e0df01e9b05","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-16T12:59:44Z","title_canon_sha256":"d46590d1af8958e8938f271f187b926586e4b5b3b8ee72a3125cf48f4cf7c781"},"schema_version":"1.0","source":{"id":"2407.11681","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.11681","created_at":"2026-07-05T08:44:27Z"},{"alias_kind":"arxiv_version","alias_value":"2407.11681v1","created_at":"2026-07-05T08:44:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11681","created_at":"2026-07-05T08:44:27Z"},{"alias_kind":"pith_short_12","alias_value":"NS2EEQJXNUWH","created_at":"2026-07-05T08:44:27Z"},{"alias_kind":"pith_short_16","alias_value":"NS2EEQJXNUWHYJLT","created_at":"2026-07-05T08:44:27Z"},{"alias_kind":"pith_short_8","alias_value":"NS2EEQJX","created_at":"2026-07-05T08:44:27Z"}],"graph_snapshots":[{"event_id":"sha256:2df55021f9a6a15eb053f0edafa8c992296e0c7e528e2f4a87bc4f970b7bdc06","target":"graph","created_at":"2026-07-05T08:44:27Z","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/2407.11681/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As Large Language Models (LLMs) grow dramatically in size, there is an increasing trend in compressing and speeding up these models. Previous studies have highlighted the usefulness of gradients for importance scoring in neural network compressing, especially in pruning medium-size networks. However, the substantial memory requirements involved in calculating gradients with backpropagation impede the utilization of gradients in guiding LLM pruning. As a result, most pruning strategies for LLMs rely on gradient-free criteria, such as weight magnitudes or a mix of magnitudes and activations. In ","authors_text":"Hongrong Cheng, Javen Qinfeng Shi, Miao Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-16T12:59:44Z","title":"MINI-LLM: Memory-Efficient Structured Pruning for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11681","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:feb075ed4b1e0e65c388b0c93bc779e46de1fda26d594ab1a936ac55ce0ca581","target":"record","created_at":"2026-07-05T08:44:27Z","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":"de5d946276adc77b11c773dcdc04c97f7c638d57327b8e595c6b9e0df01e9b05","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-16T12:59:44Z","title_canon_sha256":"d46590d1af8958e8938f271f187b926586e4b5b3b8ee72a3125cf48f4cf7c781"},"schema_version":"1.0","source":{"id":"2407.11681","kind":"arxiv","version":1}},"canonical_sha256":"6cb44241376d2c7c25731217e9a868ab0d6c3cc7bed64946c8eb20ef6ae81389","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6cb44241376d2c7c25731217e9a868ab0d6c3cc7bed64946c8eb20ef6ae81389","first_computed_at":"2026-07-05T08:44:27.754611Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:27.754611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4YboA9+vxQmVfex/IE75v+ZuiP/VBvhgrzl0vcFmBMaITvPWxGOHGAtD87hRu4gkpdWqEsYoNQTcEJc6rsnCCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:27.755017Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.11681","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:feb075ed4b1e0e65c388b0c93bc779e46de1fda26d594ab1a936ac55ce0ca581","sha256:2df55021f9a6a15eb053f0edafa8c992296e0c7e528e2f4a87bc4f970b7bdc06"],"state_sha256":"99ca93c10714e27ad478deca117f819edbd045235b01d3aa31032c28bbb77e55"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LmjxkHL6Gh8AXt5dTi4rQSZm2JVRaoUJ9OwR9ork0kXMpHHT6WXkcRVFj/wRWZj7gb3N3VQYeIde9QC3/wc+BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T13:57:54.896603Z","bundle_sha256":"c3287f8ccfa85e798cee91ee7bd0680958aaf6c5c2c83ed399a17076b62758c6"}}