{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EOHYVNWO726P6KGCIXDF75NHV3","short_pith_number":"pith:EOHYVNWO","canonical_record":{"source":{"id":"2606.28251","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2026-06-26T16:37:06Z","cross_cats_sorted":[],"title_canon_sha256":"4dae20c65669ac8ed972598d4e18814eabd62af8b6d62892d88371a214cc3f91","abstract_canon_sha256":"8313aa6444f9d60ae21170ec38a9babd73e6778903a55b9a7d680ec878cfc83b"},"schema_version":"1.0"},"canonical_sha256":"238f8ab6cefebcff28c245c65ff5a7aeef279805746999caa7282b6159751c25","source":{"kind":"arxiv","id":"2606.28251","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.28251","created_at":"2026-06-29T01:15:10Z"},{"alias_kind":"arxiv_version","alias_value":"2606.28251v1","created_at":"2026-06-29T01:15:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28251","created_at":"2026-06-29T01:15:10Z"},{"alias_kind":"pith_short_12","alias_value":"EOHYVNWO726P","created_at":"2026-06-29T01:15:10Z"},{"alias_kind":"pith_short_16","alias_value":"EOHYVNWO726P6KGC","created_at":"2026-06-29T01:15:10Z"},{"alias_kind":"pith_short_8","alias_value":"EOHYVNWO","created_at":"2026-06-29T01:15:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EOHYVNWO726P6KGCIXDF75NHV3","target":"record","payload":{"canonical_record":{"source":{"id":"2606.28251","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2026-06-26T16:37:06Z","cross_cats_sorted":[],"title_canon_sha256":"4dae20c65669ac8ed972598d4e18814eabd62af8b6d62892d88371a214cc3f91","abstract_canon_sha256":"8313aa6444f9d60ae21170ec38a9babd73e6778903a55b9a7d680ec878cfc83b"},"schema_version":"1.0"},"canonical_sha256":"238f8ab6cefebcff28c245c65ff5a7aeef279805746999caa7282b6159751c25","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:15:10.420649Z","signature_b64":"mFpMi34fYLbnGE4mlEnlpZHN0jRVtpcnVx/T5y/fQJ3nXmbYetGRePdtd6u3DHk5UqK/chcTE64L6RWyC3tpAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"238f8ab6cefebcff28c245c65ff5a7aeef279805746999caa7282b6159751c25","last_reissued_at":"2026-06-29T01:15:10.420266Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:15:10.420266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.28251","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":"2026-06-29T01:15:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YHEthfrI57QnBanKJvAeGx9IKZ30OzoCU2IUEt+uDkNfy9keNSrW5S1wO3AMqAakzF5UELA89oRNhnF2aBKYBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T20:57:09.368500Z"},"content_sha256":"4435d9ea09063c9660b83acdc67d9fe450ce80386e1650845d76697f8af68620","schema_version":"1.0","event_id":"sha256:4435d9ea09063c9660b83acdc67d9fe450ce80386e1650845d76697f8af68620"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EOHYVNWO726P6KGCIXDF75NHV3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Push Puppet Networks: Structured Bayesian Pruning Algorithm for Language Model Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.AP","authors_text":"Robert Kubinec","submitted_at":"2026-06-26T16:37:06Z","abstract_excerpt":"This paper presents push puppet networks, a novel Bayesian algorithm for structured pruning of large language models. The push puppet network learns a hierarchical function during training that can optimally determine specific network layers to keep for a given target size. By adding a small number of gating parameters via a hierarchical penalty function, the learned smooth function can allow for a network to be resized to very specific sizes without loading the full model into memory or requiring further post-training computation. The method compares favorably with existing approaches (Sparse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28251","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/2606.28251/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":"2026-06-29T01:15:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vw8fQbJN1nM99h2VTwF6fWBVxHZcbiWCgeBeG1RE8lXcp1VtfYVrzR1dFULPG+0UQ4Ode+xkvddKCJ+kT6XRDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T20:57:09.368864Z"},"content_sha256":"38bd097184386d4473f3cda6f569c31c80ef9a5e083f450929c71788d9126b19","schema_version":"1.0","event_id":"sha256:38bd097184386d4473f3cda6f569c31c80ef9a5e083f450929c71788d9126b19"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EOHYVNWO726P6KGCIXDF75NHV3/bundle.json","state_url":"https://pith.science/pith/EOHYVNWO726P6KGCIXDF75NHV3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EOHYVNWO726P6KGCIXDF75NHV3/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":"2026-06-29T20:57:09Z","links":{"resolver":"https://pith.science/pith/EOHYVNWO726P6KGCIXDF75NHV3","bundle":"https://pith.science/pith/EOHYVNWO726P6KGCIXDF75NHV3/bundle.json","state":"https://pith.science/pith/EOHYVNWO726P6KGCIXDF75NHV3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EOHYVNWO726P6KGCIXDF75NHV3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EOHYVNWO726P6KGCIXDF75NHV3","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":"8313aa6444f9d60ae21170ec38a9babd73e6778903a55b9a7d680ec878cfc83b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2026-06-26T16:37:06Z","title_canon_sha256":"4dae20c65669ac8ed972598d4e18814eabd62af8b6d62892d88371a214cc3f91"},"schema_version":"1.0","source":{"id":"2606.28251","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.28251","created_at":"2026-06-29T01:15:10Z"},{"alias_kind":"arxiv_version","alias_value":"2606.28251v1","created_at":"2026-06-29T01:15:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28251","created_at":"2026-06-29T01:15:10Z"},{"alias_kind":"pith_short_12","alias_value":"EOHYVNWO726P","created_at":"2026-06-29T01:15:10Z"},{"alias_kind":"pith_short_16","alias_value":"EOHYVNWO726P6KGC","created_at":"2026-06-29T01:15:10Z"},{"alias_kind":"pith_short_8","alias_value":"EOHYVNWO","created_at":"2026-06-29T01:15:10Z"}],"graph_snapshots":[{"event_id":"sha256:38bd097184386d4473f3cda6f569c31c80ef9a5e083f450929c71788d9126b19","target":"graph","created_at":"2026-06-29T01:15:10Z","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/2606.28251/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents push puppet networks, a novel Bayesian algorithm for structured pruning of large language models. The push puppet network learns a hierarchical function during training that can optimally determine specific network layers to keep for a given target size. By adding a small number of gating parameters via a hierarchical penalty function, the learned smooth function can allow for a network to be resized to very specific sizes without loading the full model into memory or requiring further post-training computation. The method compares favorably with existing approaches (Sparse","authors_text":"Robert Kubinec","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2026-06-26T16:37:06Z","title":"Push Puppet Networks: Structured Bayesian Pruning Algorithm for Language Model Compression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28251","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":"sha256:4435d9ea09063c9660b83acdc67d9fe450ce80386e1650845d76697f8af68620","target":"record","created_at":"2026-06-29T01:15:10Z","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":"8313aa6444f9d60ae21170ec38a9babd73e6778903a55b9a7d680ec878cfc83b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2026-06-26T16:37:06Z","title_canon_sha256":"4dae20c65669ac8ed972598d4e18814eabd62af8b6d62892d88371a214cc3f91"},"schema_version":"1.0","source":{"id":"2606.28251","kind":"arxiv","version":1}},"canonical_sha256":"238f8ab6cefebcff28c245c65ff5a7aeef279805746999caa7282b6159751c25","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"238f8ab6cefebcff28c245c65ff5a7aeef279805746999caa7282b6159751c25","first_computed_at":"2026-06-29T01:15:10.420266Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-29T01:15:10.420266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mFpMi34fYLbnGE4mlEnlpZHN0jRVtpcnVx/T5y/fQJ3nXmbYetGRePdtd6u3DHk5UqK/chcTE64L6RWyC3tpAA==","signature_status":"signed_v1","signed_at":"2026-06-29T01:15:10.420649Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.28251","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4435d9ea09063c9660b83acdc67d9fe450ce80386e1650845d76697f8af68620","sha256:38bd097184386d4473f3cda6f569c31c80ef9a5e083f450929c71788d9126b19"],"state_sha256":"056b7388eb0b8662b360bc6e0f1e3ea97ac560b6d5099722102569e3182f0418"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"flm8A12Z1DC+0+tubKmtqtcBqPqjQQ0ANdaUJhQL6sNrz9dIaPld/yIUDwtWNMwveFIwIktJAP0ekjrew5rvCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T20:57:09.370843Z","bundle_sha256":"2b00f4c1cba51e4fd711cab25850714643ff085bdf7167643fcfc68cd0e4f17a"}}