{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:DDA5ASN7NES5CU5EEOEEVUZGCH","short_pith_number":"pith:DDA5ASN7","canonical_record":{"source":{"id":"2607.21985","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-07-24T05:19:41Z","cross_cats_sorted":["cs.AI","cs.AR","cs.LG"],"title_canon_sha256":"a70449d497bfb426f6a148b4f6e28994122d810178e836599842e313f3bdfe16","abstract_canon_sha256":"9167c61320ddf65719b09381c52f216f52fecd4118083de6d68116a164011ddf"},"schema_version":"1.0"},"canonical_sha256":"18c1d049bf6925d153a423884ad32611e36a13387559eb0fccf2b8c0361fdf96","source":{"kind":"arxiv","id":"2607.21985","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21985","created_at":"2026-07-27T00:20:31Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21985v1","created_at":"2026-07-27T00:20:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21985","created_at":"2026-07-27T00:20:31Z"},{"alias_kind":"pith_short_12","alias_value":"DDA5ASN7NES5","created_at":"2026-07-27T00:20:31Z"},{"alias_kind":"pith_short_16","alias_value":"DDA5ASN7NES5CU5E","created_at":"2026-07-27T00:20:31Z"},{"alias_kind":"pith_short_8","alias_value":"DDA5ASN7","created_at":"2026-07-27T00:20:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:DDA5ASN7NES5CU5EEOEEVUZGCH","target":"record","payload":{"canonical_record":{"source":{"id":"2607.21985","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-07-24T05:19:41Z","cross_cats_sorted":["cs.AI","cs.AR","cs.LG"],"title_canon_sha256":"a70449d497bfb426f6a148b4f6e28994122d810178e836599842e313f3bdfe16","abstract_canon_sha256":"9167c61320ddf65719b09381c52f216f52fecd4118083de6d68116a164011ddf"},"schema_version":"1.0"},"canonical_sha256":"18c1d049bf6925d153a423884ad32611e36a13387559eb0fccf2b8c0361fdf96","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T00:20:31.272889Z","signature_b64":"ziO3DLV05kyOSvT/tVpAEyHtNaRSQJ8UVjIfx2YSUKLQSMM26qYMVn7bL2bRPfSJ9iorxbsSSuKcZCCltIn5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18c1d049bf6925d153a423884ad32611e36a13387559eb0fccf2b8c0361fdf96","last_reissued_at":"2026-07-27T00:20:31.272021Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T00:20:31.272021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.21985","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":"2026-07-27T00:20:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iralG6hY/GTOJan5e6tSKfiQV92yzN+aOGUJIEOLZBQ0Ts2F3QdhCs5BquOjqubB9akmfh4x/TSOR5sHfiY2Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:59:02.519796Z"},"content_sha256":"5303d2ff4190e8287fee24582e1640f76e9f072d84d4b32ffd9208987bc1f714","schema_version":"1.0","event_id":"sha256:5303d2ff4190e8287fee24582e1640f76e9f072d84d4b32ffd9208987bc1f714"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:DDA5ASN7NES5CU5EEOEEVUZGCH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unified Static-Dynamic Pruning for Efficient LLM Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.AR","cs.LG"],"primary_cat":"cs.DC","authors_text":"Jaeyoung Do, Jinhyeok Kim, Yejoon Lee","submitted_at":"2026-07-24T05:19:41Z","abstract_excerpt":"The increasing deployment of large language models (LLMs) has magnified the computational and memory bottlenecks of autoregressive decoding, where low compute intensity and bandwidth-bound kernels dominate inference cost. Weight pruning offers a promising remedy,\n  but existing methods remain confined to either static pruning (SP), which permanently removes redundant weights but lacks adaptivity, or dynamic pruning (DP), which adapts to input sparsity but introduces runtime irregularity. This paper presents SPDP, a unified\n  sparse-inference framework that integrates unstructured SP with input"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21985","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/2607.21985/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":"2026-07-27T00:20:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lDoFv/9z3qzaAC3jpqEwP1ICRBFlv69jcRpiSYbOcvH4IpiAg8644ae45ZSFGrwIo+gnO7rcOLnMgNjx479UAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:59:02.520745Z"},"content_sha256":"34025304b9f6e2befdc32ab3fe7db52c96f44141a2edb59b9b9ded3b47e1631c","schema_version":"1.0","event_id":"sha256:34025304b9f6e2befdc32ab3fe7db52c96f44141a2edb59b9b9ded3b47e1631c"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:DDA5ASN7NES5CU5EEOEEVUZGCH","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.18653/v1/2023.acl-long.660) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Hritik Bansal, Karthik Gopalakrishnan, Saket Dingliwal, Sravan Bodapati, Katrin Kirchhoff, and Dan Roth. 2023. Rethinking the Role of Scale for In-Context Learn- ing: An Interpretability-based Case Study at 66 Billion Scale. InACL, Anna Rog","arxiv_id":"2607.21985","detector":"doi_compliance","evidence":{"ref_index":6,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.18653/v1/2023.acl-","reconstructed_doi":"10.18653/v1/2023.acl-long.660"},"severity":"advisory","ref_index":6,"audited_at":"2026-08-01T06:28:40.231634Z","event_type":"pith.integrity.v1","detected_doi":"10.18653/v1/2023.acl-long.660","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"b2621232a35a3102aaf4582563ff6205c2e748330bd365d87dda0a16130ee897","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":15266,"payload_sha256":"8c97efe37dfba7b359f4e8d7e12d9fec8002292d78ac8b790169a79596f37460","signature_b64":"82Ef1akENcDW+rVJtY7t+qdPALjOug4zG8ETsDEIBHz3FVFiG+zbfuK3nIldL+uGYyrlt4Jx/zEKvj0MCGxJAA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-01T06:33:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lxZKgnWSbshxXpG8FxOkJ+Ecpx7MyFqOv2X/o+WqsslhpzRBS+FwuymvZ7KSP3y8dDBKiE1vjIq0jgg6PvENCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:59:02.524628Z"},"content_sha256":"2e8729cc0f821e2af73de8fef278f34a30f1be78ba26d883a66d7e4f4e2b203f","schema_version":"1.0","event_id":"sha256:2e8729cc0f821e2af73de8fef278f34a30f1be78ba26d883a66d7e4f4e2b203f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DDA5ASN7NES5CU5EEOEEVUZGCH/bundle.json","state_url":"https://pith.science/pith/DDA5ASN7NES5CU5EEOEEVUZGCH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DDA5ASN7NES5CU5EEOEEVUZGCH/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":"2026-08-04T09:59:02Z","links":{"resolver":"https://pith.science/pith/DDA5ASN7NES5CU5EEOEEVUZGCH","bundle":"https://pith.science/pith/DDA5ASN7NES5CU5EEOEEVUZGCH/bundle.json","state":"https://pith.science/pith/DDA5ASN7NES5CU5EEOEEVUZGCH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DDA5ASN7NES5CU5EEOEEVUZGCH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DDA5ASN7NES5CU5EEOEEVUZGCH","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9167c61320ddf65719b09381c52f216f52fecd4118083de6d68116a164011ddf","cross_cats_sorted":["cs.AI","cs.AR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-07-24T05:19:41Z","title_canon_sha256":"a70449d497bfb426f6a148b4f6e28994122d810178e836599842e313f3bdfe16"},"schema_version":"1.0","source":{"id":"2607.21985","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21985","created_at":"2026-07-27T00:20:31Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21985v1","created_at":"2026-07-27T00:20:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21985","created_at":"2026-07-27T00:20:31Z"},{"alias_kind":"pith_short_12","alias_value":"DDA5ASN7NES5","created_at":"2026-07-27T00:20:31Z"},{"alias_kind":"pith_short_16","alias_value":"DDA5ASN7NES5CU5E","created_at":"2026-07-27T00:20:31Z"},{"alias_kind":"pith_short_8","alias_value":"DDA5ASN7","created_at":"2026-07-27T00:20:31Z"}],"graph_snapshots":[{"event_id":"sha256:34025304b9f6e2befdc32ab3fe7db52c96f44141a2edb59b9b9ded3b47e1631c","target":"graph","created_at":"2026-07-27T00:20:31Z","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/2607.21985/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The increasing deployment of large language models (LLMs) has magnified the computational and memory bottlenecks of autoregressive decoding, where low compute intensity and bandwidth-bound kernels dominate inference cost. Weight pruning offers a promising remedy,\n  but existing methods remain confined to either static pruning (SP), which permanently removes redundant weights but lacks adaptivity, or dynamic pruning (DP), which adapts to input sparsity but introduces runtime irregularity. This paper presents SPDP, a unified\n  sparse-inference framework that integrates unstructured SP with input","authors_text":"Jaeyoung Do, Jinhyeok Kim, Yejoon Lee","cross_cats":["cs.AI","cs.AR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-07-24T05:19:41Z","title":"Unified Static-Dynamic Pruning for Efficient LLM Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21985","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":"sha256:5303d2ff4190e8287fee24582e1640f76e9f072d84d4b32ffd9208987bc1f714","target":"record","created_at":"2026-07-27T00:20:31Z","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":"9167c61320ddf65719b09381c52f216f52fecd4118083de6d68116a164011ddf","cross_cats_sorted":["cs.AI","cs.AR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-07-24T05:19:41Z","title_canon_sha256":"a70449d497bfb426f6a148b4f6e28994122d810178e836599842e313f3bdfe16"},"schema_version":"1.0","source":{"id":"2607.21985","kind":"arxiv","version":1}},"canonical_sha256":"18c1d049bf6925d153a423884ad32611e36a13387559eb0fccf2b8c0361fdf96","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18c1d049bf6925d153a423884ad32611e36a13387559eb0fccf2b8c0361fdf96","first_computed_at":"2026-07-27T00:20:31.272021Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-27T00:20:31.272021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ziO3DLV05kyOSvT/tVpAEyHtNaRSQJ8UVjIfx2YSUKLQSMM26qYMVn7bL2bRPfSJ9iorxbsSSuKcZCCltIn5Ag==","signature_status":"signed_v1","signed_at":"2026-07-27T00:20:31.272889Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.21985","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5303d2ff4190e8287fee24582e1640f76e9f072d84d4b32ffd9208987bc1f714","sha256:34025304b9f6e2befdc32ab3fe7db52c96f44141a2edb59b9b9ded3b47e1631c","sha256:2e8729cc0f821e2af73de8fef278f34a30f1be78ba26d883a66d7e4f4e2b203f"],"state_sha256":"ba2db2bfe63ea86ecb9379b3d9d46b154c35728acf132301ca4be8ecd521a0cc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G8vHomyREbkw0jP7okzBci3DBdNNyQbZAnSbEtb/0tkH8QMjQdHYlSrmPKN9AawKxEgeaMJi59aunit0GZ59DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T09:59:02.528585Z","bundle_sha256":"929767b7d59f0014c7ee43dc377c8c0ce08de0c127f7c37a4aa0fdbc4ccc4de0"}}