{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LWFNJ7ARCFRWI3BFPTULG3RF32","short_pith_number":"pith:LWFNJ7AR","canonical_record":{"source":{"id":"2412.06419","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-09T11:57:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"73e68accb755e15f17f196b1e17e5964da49cde11d6415e5bc7d772975a4d632","abstract_canon_sha256":"13cf415b886d42486a4b098445828b721702794f5c65f3532c450194325aa9d2"},"schema_version":"1.0"},"canonical_sha256":"5d8ad4fc111163646c257ce8b36e25dea0087d506f02d3ad6621360d968a9b4e","source":{"kind":"arxiv","id":"2412.06419","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06419","created_at":"2026-07-05T09:46:20Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06419v1","created_at":"2026-07-05T09:46:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06419","created_at":"2026-07-05T09:46:20Z"},{"alias_kind":"pith_short_12","alias_value":"LWFNJ7ARCFRW","created_at":"2026-07-05T09:46:20Z"},{"alias_kind":"pith_short_16","alias_value":"LWFNJ7ARCFRWI3BF","created_at":"2026-07-05T09:46:20Z"},{"alias_kind":"pith_short_8","alias_value":"LWFNJ7AR","created_at":"2026-07-05T09:46:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LWFNJ7ARCFRWI3BFPTULG3RF32","target":"record","payload":{"canonical_record":{"source":{"id":"2412.06419","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-09T11:57:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"73e68accb755e15f17f196b1e17e5964da49cde11d6415e5bc7d772975a4d632","abstract_canon_sha256":"13cf415b886d42486a4b098445828b721702794f5c65f3532c450194325aa9d2"},"schema_version":"1.0"},"canonical_sha256":"5d8ad4fc111163646c257ce8b36e25dea0087d506f02d3ad6621360d968a9b4e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:20.344238Z","signature_b64":"yTBsnMHH+T8DxRAgHOJMDQ0ra94VZ42zR3ACvHaAEExPqPQKUYD04GmBD8k+ALSmOpTMxiA4i451LjCcZA2NBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d8ad4fc111163646c257ce8b36e25dea0087d506f02d3ad6621360d968a9b4e","last_reissued_at":"2026-07-05T09:46:20.343841Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:20.343841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.06419","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":"2026-07-05T09:46:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wJkmHNl/0VZfn7Uxro9Tj29q6ZZe14v8lKku8Sag7vC/3jpcR0I9pHWZL/r/I/mvmuVAw7oHKxFm1yyu9FBfBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:52:56.060444Z"},"content_sha256":"5d44cb103b864185a651ba9315573c5e0b4cd5df616c1a80a3c619feb529e1a0","schema_version":"1.0","event_id":"sha256:5d44cb103b864185a651ba9315573c5e0b4cd5df616c1a80a3c619feb529e1a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LWFNJ7ARCFRWI3BFPTULG3RF32","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM-BIP: Structured Pruning for Large Language Models with Block-Wise Forward Importance Propagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haihang Wu","submitted_at":"2024-12-09T11:57:16Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable performance across various language tasks, but their widespread deployment is impeded by their large size and high computational costs. Structural pruning is a prevailing technique used to introduce sparsity into pre-trained models and facilitate direct hardware acceleration during inference by removing redundant connections (structurally-grouped parameters), such as channels and attention heads. Existing structural pruning approaches often employ either global or layer-wise pruning criteria; however, they are hindered by ineffectivenes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06419","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/2412.06419/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":"2026-07-05T09:46:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xq7P/eBhwQ1h3NFooLWKE2vWw1pNmYkwVIlQXDu0ejSEFx3Zc43pFyyEmaZ+NGHUTR7+uKKAL5eHE1PjTrbaCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:52:56.060937Z"},"content_sha256":"8e3d2caedc3d4f3ad3d8f0ea49ed6fd2846446013e66d866fe956b33c1eea1f9","schema_version":"1.0","event_id":"sha256:8e3d2caedc3d4f3ad3d8f0ea49ed6fd2846446013e66d866fe956b33c1eea1f9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LWFNJ7ARCFRWI3BFPTULG3RF32/bundle.json","state_url":"https://pith.science/pith/LWFNJ7ARCFRWI3BFPTULG3RF32/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LWFNJ7ARCFRWI3BFPTULG3RF32/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":"2026-08-09T03:52:56Z","links":{"resolver":"https://pith.science/pith/LWFNJ7ARCFRWI3BFPTULG3RF32","bundle":"https://pith.science/pith/LWFNJ7ARCFRWI3BFPTULG3RF32/bundle.json","state":"https://pith.science/pith/LWFNJ7ARCFRWI3BFPTULG3RF32/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LWFNJ7ARCFRWI3BFPTULG3RF32/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LWFNJ7ARCFRWI3BFPTULG3RF32","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":"13cf415b886d42486a4b098445828b721702794f5c65f3532c450194325aa9d2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-09T11:57:16Z","title_canon_sha256":"73e68accb755e15f17f196b1e17e5964da49cde11d6415e5bc7d772975a4d632"},"schema_version":"1.0","source":{"id":"2412.06419","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06419","created_at":"2026-07-05T09:46:20Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06419v1","created_at":"2026-07-05T09:46:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06419","created_at":"2026-07-05T09:46:20Z"},{"alias_kind":"pith_short_12","alias_value":"LWFNJ7ARCFRW","created_at":"2026-07-05T09:46:20Z"},{"alias_kind":"pith_short_16","alias_value":"LWFNJ7ARCFRWI3BF","created_at":"2026-07-05T09:46:20Z"},{"alias_kind":"pith_short_8","alias_value":"LWFNJ7AR","created_at":"2026-07-05T09:46:20Z"}],"graph_snapshots":[{"event_id":"sha256:8e3d2caedc3d4f3ad3d8f0ea49ed6fd2846446013e66d866fe956b33c1eea1f9","target":"graph","created_at":"2026-07-05T09:46:20Z","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/2412.06419/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable performance across various language tasks, but their widespread deployment is impeded by their large size and high computational costs. Structural pruning is a prevailing technique used to introduce sparsity into pre-trained models and facilitate direct hardware acceleration during inference by removing redundant connections (structurally-grouped parameters), such as channels and attention heads. Existing structural pruning approaches often employ either global or layer-wise pruning criteria; however, they are hindered by ineffectivenes","authors_text":"Haihang Wu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-09T11:57:16Z","title":"LLM-BIP: Structured Pruning for Large Language Models with Block-Wise Forward Importance Propagation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06419","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":"sha256:5d44cb103b864185a651ba9315573c5e0b4cd5df616c1a80a3c619feb529e1a0","target":"record","created_at":"2026-07-05T09:46:20Z","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":"13cf415b886d42486a4b098445828b721702794f5c65f3532c450194325aa9d2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-09T11:57:16Z","title_canon_sha256":"73e68accb755e15f17f196b1e17e5964da49cde11d6415e5bc7d772975a4d632"},"schema_version":"1.0","source":{"id":"2412.06419","kind":"arxiv","version":1}},"canonical_sha256":"5d8ad4fc111163646c257ce8b36e25dea0087d506f02d3ad6621360d968a9b4e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d8ad4fc111163646c257ce8b36e25dea0087d506f02d3ad6621360d968a9b4e","first_computed_at":"2026-07-05T09:46:20.343841Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:46:20.343841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yTBsnMHH+T8DxRAgHOJMDQ0ra94VZ42zR3ACvHaAEExPqPQKUYD04GmBD8k+ALSmOpTMxiA4i451LjCcZA2NBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:46:20.344238Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.06419","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d44cb103b864185a651ba9315573c5e0b4cd5df616c1a80a3c619feb529e1a0","sha256:8e3d2caedc3d4f3ad3d8f0ea49ed6fd2846446013e66d866fe956b33c1eea1f9"],"state_sha256":"005f00131863f992cf903444bd5ee4705fde5f96765f995bcc91b892ce84cd48"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"avvjqaurE5PRQA3Q3gID1r0tUU/Wk33GTyaAPwjY4K6akor7/qavOpid6fmgRmvwpYMXJIPSRS7t/TDjy4CeAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:52:56.064284Z","bundle_sha256":"2bc3e7a08de48906a2a65d378cce5d8ec727e409f71f44b1036dc23fe7b87ae6"}}