{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:INTJUYICIHFXWQG5JVOY2TLOAN","short_pith_number":"pith:INTJUYIC","canonical_record":{"source":{"id":"2608.12953","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-13T08:32:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4803396f9ceea562096c138f9ba2c1e28d0f5fcc6f1cdb29fc249445db46f32a","abstract_canon_sha256":"d75c8cb14a6135114405933c8322236fae8c45756cfa3a261e359a7e13cc5b84"},"schema_version":"1.0"},"canonical_sha256":"43669a610241cb7b40dd4d5d8d4d6e036bf65b1bb04de40192b4ae0512f883b0","source":{"kind":"arxiv","id":"2608.12953","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.12953","created_at":"2026-08-14T00:59:35Z"},{"alias_kind":"arxiv_version","alias_value":"2608.12953v1","created_at":"2026-08-14T00:59:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12953","created_at":"2026-08-14T00:59:35Z"},{"alias_kind":"pith_short_12","alias_value":"INTJUYICIHFX","created_at":"2026-08-14T00:59:35Z"},{"alias_kind":"pith_short_16","alias_value":"INTJUYICIHFXWQG5","created_at":"2026-08-14T00:59:35Z"},{"alias_kind":"pith_short_8","alias_value":"INTJUYIC","created_at":"2026-08-14T00:59:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:INTJUYICIHFXWQG5JVOY2TLOAN","target":"record","payload":{"canonical_record":{"source":{"id":"2608.12953","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-13T08:32:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4803396f9ceea562096c138f9ba2c1e28d0f5fcc6f1cdb29fc249445db46f32a","abstract_canon_sha256":"d75c8cb14a6135114405933c8322236fae8c45756cfa3a261e359a7e13cc5b84"},"schema_version":"1.0"},"canonical_sha256":"43669a610241cb7b40dd4d5d8d4d6e036bf65b1bb04de40192b4ae0512f883b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T00:59:35.984616Z","signature_b64":"C8WYiX8Bt2V1Y+tpdl05z1FE5k+H/2V3iw/Usyja2Jio0W1qpGI40k7m9X3N6Gg/OpLd7OhtOUIB/KZS13rTAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43669a610241cb7b40dd4d5d8d4d6e036bf65b1bb04de40192b4ae0512f883b0","last_reissued_at":"2026-08-14T00:59:35.963465Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T00:59:35.963465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.12953","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":"2026-08-14T00:59:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7qpcXm5cqEQJZxmq5mbSGNnsdrqSk1Alb/JVJlccnb2/JBEHrtLc3JEqKc6710D6ivmi0xL65w0T2062eApDCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T08:37:24.185473Z"},"content_sha256":"ee549dcd3f965e4b0f3b97e114cf636b2809984ba104cbbf5fa125906342f292","schema_version":"1.0","event_id":"sha256:ee549dcd3f965e4b0f3b97e114cf636b2809984ba104cbbf5fa125906342f292"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:INTJUYICIHFXWQG5JVOY2TLOAN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unifying Depth and Width Pruning for LLMs via Binary Knapsack Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Akshay Nambi, Ayan Sengupta, Palaash Goel, Tanmoy Chakraborty","submitted_at":"2026-08-13T08:32:18Z","abstract_excerpt":"Structured pruning is a promising approach for compressing large language models (LLMs), yet existing methods rely heavily on greedy heuristics that produce myopic decisions, and often fail to precisely meet target compression budgets. We present SNIPER, a two-stage structured pruning framework that solves a knapsack optimization over coarse-granularity components to yield conditionally optimal parameter allocations with respect to fixed importance estimates, followed by a fine-grained pruning stage to meet strict budget constraints. We introduce the Compression Ratio Adherence Factor (CRAFT) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12953","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/2608.12953/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":"2026-08-14T00:59:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q4HZOd1SbKm7ZvVgjGrXXdwbus1NflUVK9jCBFC6F6CIeHQU3z5lrAlZIpRH9K78M8TAskNFfLtkVgvWYH+nCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T08:37:24.186201Z"},"content_sha256":"4dd12e01e848d97adf45695aec5f11ff5814062192b86a787be80fc0aa8c4d15","schema_version":"1.0","event_id":"sha256:4dd12e01e848d97adf45695aec5f11ff5814062192b86a787be80fc0aa8c4d15"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/INTJUYICIHFXWQG5JVOY2TLOAN/bundle.json","state_url":"https://pith.science/pith/INTJUYICIHFXWQG5JVOY2TLOAN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/INTJUYICIHFXWQG5JVOY2TLOAN/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":"2026-08-18T08:37:24Z","links":{"resolver":"https://pith.science/pith/INTJUYICIHFXWQG5JVOY2TLOAN","bundle":"https://pith.science/pith/INTJUYICIHFXWQG5JVOY2TLOAN/bundle.json","state":"https://pith.science/pith/INTJUYICIHFXWQG5JVOY2TLOAN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/INTJUYICIHFXWQG5JVOY2TLOAN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:INTJUYICIHFXWQG5JVOY2TLOAN","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":"d75c8cb14a6135114405933c8322236fae8c45756cfa3a261e359a7e13cc5b84","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-13T08:32:18Z","title_canon_sha256":"4803396f9ceea562096c138f9ba2c1e28d0f5fcc6f1cdb29fc249445db46f32a"},"schema_version":"1.0","source":{"id":"2608.12953","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.12953","created_at":"2026-08-14T00:59:35Z"},{"alias_kind":"arxiv_version","alias_value":"2608.12953v1","created_at":"2026-08-14T00:59:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12953","created_at":"2026-08-14T00:59:35Z"},{"alias_kind":"pith_short_12","alias_value":"INTJUYICIHFX","created_at":"2026-08-14T00:59:35Z"},{"alias_kind":"pith_short_16","alias_value":"INTJUYICIHFXWQG5","created_at":"2026-08-14T00:59:35Z"},{"alias_kind":"pith_short_8","alias_value":"INTJUYIC","created_at":"2026-08-14T00:59:35Z"}],"graph_snapshots":[{"event_id":"sha256:4dd12e01e848d97adf45695aec5f11ff5814062192b86a787be80fc0aa8c4d15","target":"graph","created_at":"2026-08-14T00:59:35Z","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/2608.12953/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Structured pruning is a promising approach for compressing large language models (LLMs), yet existing methods rely heavily on greedy heuristics that produce myopic decisions, and often fail to precisely meet target compression budgets. We present SNIPER, a two-stage structured pruning framework that solves a knapsack optimization over coarse-granularity components to yield conditionally optimal parameter allocations with respect to fixed importance estimates, followed by a fine-grained pruning stage to meet strict budget constraints. We introduce the Compression Ratio Adherence Factor (CRAFT) ","authors_text":"Akshay Nambi, Ayan Sengupta, Palaash Goel, Tanmoy Chakraborty","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-13T08:32:18Z","title":"Unifying Depth and Width Pruning for LLMs via Binary Knapsack Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12953","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:ee549dcd3f965e4b0f3b97e114cf636b2809984ba104cbbf5fa125906342f292","target":"record","created_at":"2026-08-14T00:59:35Z","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":"d75c8cb14a6135114405933c8322236fae8c45756cfa3a261e359a7e13cc5b84","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-13T08:32:18Z","title_canon_sha256":"4803396f9ceea562096c138f9ba2c1e28d0f5fcc6f1cdb29fc249445db46f32a"},"schema_version":"1.0","source":{"id":"2608.12953","kind":"arxiv","version":1}},"canonical_sha256":"43669a610241cb7b40dd4d5d8d4d6e036bf65b1bb04de40192b4ae0512f883b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43669a610241cb7b40dd4d5d8d4d6e036bf65b1bb04de40192b4ae0512f883b0","first_computed_at":"2026-08-14T00:59:35.963465Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-14T00:59:35.963465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C8WYiX8Bt2V1Y+tpdl05z1FE5k+H/2V3iw/Usyja2Jio0W1qpGI40k7m9X3N6Gg/OpLd7OhtOUIB/KZS13rTAw==","signature_status":"signed_v1","signed_at":"2026-08-14T00:59:35.984616Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.12953","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee549dcd3f965e4b0f3b97e114cf636b2809984ba104cbbf5fa125906342f292","sha256:4dd12e01e848d97adf45695aec5f11ff5814062192b86a787be80fc0aa8c4d15"],"state_sha256":"e0451bf2aeb04ca724c6d8f25b8d8e5a8590f50018cb1bf0090c2b5b2f685bd9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XcmmgWL6nzj84EoqTuR7Rz0b1qb9bXvEW4OT1htUmeJoc0G4YhkaGepnx1gy4BkTnCzgUcO1v1Ry2AG5+qVmCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T08:37:24.192016Z","bundle_sha256":"ba3281a9c9d32a8d2ebe40c9dfc365ae837ec5b3fcfd2f3dc4e122895fdd861f"}}