{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QH7BB27ABTKNLM6BUUU3IED56O","short_pith_number":"pith:QH7BB27A","canonical_record":{"source":{"id":"2606.10722","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T11:32:58Z","cross_cats_sorted":[],"title_canon_sha256":"75b29590d8c2ebd24bdc01b3c86f32d2fde8cac5a6e558815bbc4260e06c6adc","abstract_canon_sha256":"d6393d1fba881d6e5c3ac998aab94f6ef6b1d4ccc2b8adb629f89eab1f1a52e1"},"schema_version":"1.0"},"canonical_sha256":"81fe10ebe00cd4d5b3c1a529b4107df3967ab5ca8ecaec9b2d22dfab21ec1ddd","source":{"kind":"arxiv","id":"2606.10722","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10722","created_at":"2026-06-10T01:10:36Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10722v1","created_at":"2026-06-10T01:10:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10722","created_at":"2026-06-10T01:10:36Z"},{"alias_kind":"pith_short_12","alias_value":"QH7BB27ABTKN","created_at":"2026-06-10T01:10:36Z"},{"alias_kind":"pith_short_16","alias_value":"QH7BB27ABTKNLM6B","created_at":"2026-06-10T01:10:36Z"},{"alias_kind":"pith_short_8","alias_value":"QH7BB27A","created_at":"2026-06-10T01:10:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QH7BB27ABTKNLM6BUUU3IED56O","target":"record","payload":{"canonical_record":{"source":{"id":"2606.10722","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T11:32:58Z","cross_cats_sorted":[],"title_canon_sha256":"75b29590d8c2ebd24bdc01b3c86f32d2fde8cac5a6e558815bbc4260e06c6adc","abstract_canon_sha256":"d6393d1fba881d6e5c3ac998aab94f6ef6b1d4ccc2b8adb629f89eab1f1a52e1"},"schema_version":"1.0"},"canonical_sha256":"81fe10ebe00cd4d5b3c1a529b4107df3967ab5ca8ecaec9b2d22dfab21ec1ddd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:36.487005Z","signature_b64":"OUgsH6mIihsFFxYXvieABDuwD34z2WYrJbV7jD7bNEpmrCsHOEw2Yw/xS4Cohk/HWZ4pSdl91me5ChNrAhRzCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81fe10ebe00cd4d5b3c1a529b4107df3967ab5ca8ecaec9b2d22dfab21ec1ddd","last_reissued_at":"2026-06-10T01:10:36.486196Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:36.486196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.10722","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":"2026-06-10T01:10:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XtZgboBWdDc+09yuB6OkGiVR3kN19b1wue7GQFRlplrSqnKl2qvaekIkVubT/pX9ImH+z3GUBHzbDohDPIi7BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T02:51:28.184895Z"},"content_sha256":"306a851332bd471c2d6713dd365718d0c15d33a5358f4c1b47f8d25182f374f9","schema_version":"1.0","event_id":"sha256:306a851332bd471c2d6713dd365718d0c15d33a5358f4c1b47f8d25182f374f9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QH7BB27ABTKNLM6BUUU3IED56O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Continual LLM Upcycling: A Predictor-Gated Bank-Wise Sparsity Training Recipe for Dense-to-Sparse LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hantao Huang, Hao Zeng, Ian En-Hsu Yen, Jinyuan Shi, Minghui Yu, Ruixuan Huang, Yifan Huang, Ziyi Guan","submitted_at":"2026-06-09T11:32:58Z","abstract_excerpt":"We study dense-to-sparse continual training as a way to construct channel-sparse large language models from dense checkpoints. Starting from a Qwen2.5-8B dense backbone, we continue training at 32K context and introduce a predictor-gated sparse SwiGLU FFN in the 32K stage. For each token and layer, we use a low-rank predictor to produce FFN-channel routing logits. We then apply a bank-wise top-k rule to retain 16 channels in every 64-channel bank, yielding 4x sparsity in the FFN intermediate activation. Unlike post-hoc sparse inference methods, the routing module is placed on the main language"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10722","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/2606.10722/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":"2026-06-10T01:10:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BWVOpZ8cEOx0h05kIC0DIItp2Z6f4wicw6y3/A8+78dBDA/rZfHghfXa2hEdSO0TGMVHxoRu6Nlk+jQ52XF/Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T02:51:28.185275Z"},"content_sha256":"5c12913fa4cd64d6f4c960eed727e8b322575a480e2003cb785a5a17f287aa82","schema_version":"1.0","event_id":"sha256:5c12913fa4cd64d6f4c960eed727e8b322575a480e2003cb785a5a17f287aa82"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QH7BB27ABTKNLM6BUUU3IED56O/bundle.json","state_url":"https://pith.science/pith/QH7BB27ABTKNLM6BUUU3IED56O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QH7BB27ABTKNLM6BUUU3IED56O/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":"2026-06-30T02:51:28Z","links":{"resolver":"https://pith.science/pith/QH7BB27ABTKNLM6BUUU3IED56O","bundle":"https://pith.science/pith/QH7BB27ABTKNLM6BUUU3IED56O/bundle.json","state":"https://pith.science/pith/QH7BB27ABTKNLM6BUUU3IED56O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QH7BB27ABTKNLM6BUUU3IED56O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QH7BB27ABTKNLM6BUUU3IED56O","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":"d6393d1fba881d6e5c3ac998aab94f6ef6b1d4ccc2b8adb629f89eab1f1a52e1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T11:32:58Z","title_canon_sha256":"75b29590d8c2ebd24bdc01b3c86f32d2fde8cac5a6e558815bbc4260e06c6adc"},"schema_version":"1.0","source":{"id":"2606.10722","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10722","created_at":"2026-06-10T01:10:36Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10722v1","created_at":"2026-06-10T01:10:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10722","created_at":"2026-06-10T01:10:36Z"},{"alias_kind":"pith_short_12","alias_value":"QH7BB27ABTKN","created_at":"2026-06-10T01:10:36Z"},{"alias_kind":"pith_short_16","alias_value":"QH7BB27ABTKNLM6B","created_at":"2026-06-10T01:10:36Z"},{"alias_kind":"pith_short_8","alias_value":"QH7BB27A","created_at":"2026-06-10T01:10:36Z"}],"graph_snapshots":[{"event_id":"sha256:5c12913fa4cd64d6f4c960eed727e8b322575a480e2003cb785a5a17f287aa82","target":"graph","created_at":"2026-06-10T01:10:36Z","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/2606.10722/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study dense-to-sparse continual training as a way to construct channel-sparse large language models from dense checkpoints. Starting from a Qwen2.5-8B dense backbone, we continue training at 32K context and introduce a predictor-gated sparse SwiGLU FFN in the 32K stage. For each token and layer, we use a low-rank predictor to produce FFN-channel routing logits. We then apply a bank-wise top-k rule to retain 16 channels in every 64-channel bank, yielding 4x sparsity in the FFN intermediate activation. Unlike post-hoc sparse inference methods, the routing module is placed on the main language","authors_text":"Hantao Huang, Hao Zeng, Ian En-Hsu Yen, Jinyuan Shi, Minghui Yu, Ruixuan Huang, Yifan Huang, Ziyi Guan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T11:32:58Z","title":"Continual LLM Upcycling: A Predictor-Gated Bank-Wise Sparsity Training Recipe for Dense-to-Sparse LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10722","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":"sha256:306a851332bd471c2d6713dd365718d0c15d33a5358f4c1b47f8d25182f374f9","target":"record","created_at":"2026-06-10T01:10:36Z","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":"d6393d1fba881d6e5c3ac998aab94f6ef6b1d4ccc2b8adb629f89eab1f1a52e1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T11:32:58Z","title_canon_sha256":"75b29590d8c2ebd24bdc01b3c86f32d2fde8cac5a6e558815bbc4260e06c6adc"},"schema_version":"1.0","source":{"id":"2606.10722","kind":"arxiv","version":1}},"canonical_sha256":"81fe10ebe00cd4d5b3c1a529b4107df3967ab5ca8ecaec9b2d22dfab21ec1ddd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81fe10ebe00cd4d5b3c1a529b4107df3967ab5ca8ecaec9b2d22dfab21ec1ddd","first_computed_at":"2026-06-10T01:10:36.486196Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:10:36.486196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OUgsH6mIihsFFxYXvieABDuwD34z2WYrJbV7jD7bNEpmrCsHOEw2Yw/xS4Cohk/HWZ4pSdl91me5ChNrAhRzCw==","signature_status":"signed_v1","signed_at":"2026-06-10T01:10:36.487005Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10722","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:306a851332bd471c2d6713dd365718d0c15d33a5358f4c1b47f8d25182f374f9","sha256:5c12913fa4cd64d6f4c960eed727e8b322575a480e2003cb785a5a17f287aa82"],"state_sha256":"31338302bfefefd86f1162eadbd7e268143d4efcfca26eb5fb66de79d3b118d6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l2d7lQwaMHmn/J7OHG231J7E0lS8wPSqQDL/AzpP16GHMXW2qu4QYaxZfcnhPrHwrerEpHKuJnYEwlFQXbi7AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T02:51:28.187416Z","bundle_sha256":"8fb5ed601d3d7072d716466a7f2d09646a80875a7fecc066c1da8ed8c7af4f0b"}}