{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:62ZSN3XB3SP7UP5MZTO6EFRMSB","short_pith_number":"pith:62ZSN3XB","canonical_record":{"source":{"id":"2406.10935","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-16T13:33:09Z","cross_cats_sorted":[],"title_canon_sha256":"fa19199ffde9b735115d25d686e4e4ba62df3474650777ead57ffca644335460","abstract_canon_sha256":"f279c285d819335b704263cb4ac405aa10eca7a7d697b406c6dedfe5c931f509"},"schema_version":"1.0"},"canonical_sha256":"f6b326eee1dc9ffa3facccdde2162c9061d24db2a561ed168c49f91550b77ab7","source":{"kind":"arxiv","id":"2406.10935","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10935","created_at":"2026-07-05T08:32:46Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10935v1","created_at":"2026-07-05T08:32:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10935","created_at":"2026-07-05T08:32:46Z"},{"alias_kind":"pith_short_12","alias_value":"62ZSN3XB3SP7","created_at":"2026-07-05T08:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"62ZSN3XB3SP7UP5M","created_at":"2026-07-05T08:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"62ZSN3XB","created_at":"2026-07-05T08:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:62ZSN3XB3SP7UP5MZTO6EFRMSB","target":"record","payload":{"canonical_record":{"source":{"id":"2406.10935","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-16T13:33:09Z","cross_cats_sorted":[],"title_canon_sha256":"fa19199ffde9b735115d25d686e4e4ba62df3474650777ead57ffca644335460","abstract_canon_sha256":"f279c285d819335b704263cb4ac405aa10eca7a7d697b406c6dedfe5c931f509"},"schema_version":"1.0"},"canonical_sha256":"f6b326eee1dc9ffa3facccdde2162c9061d24db2a561ed168c49f91550b77ab7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:46.644452Z","signature_b64":"L79K9vs7Y8oIIKLDjuqfOeUcpKhztsyXWK/Zl04RZ9vCRcvb12kWDIXlL1uUbjtRERaTIJYEqlLS3SW7PZOODg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6b326eee1dc9ffa3facccdde2162c9061d24db2a561ed168c49f91550b77ab7","last_reissued_at":"2026-07-05T08:32:46.643975Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:46.643975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.10935","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":"2026-07-05T08:32:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0MXS0GR+fb1lPqEImCOrZo10OnDRp3FnRZDP9V6JgNB6nCid2qqCjKvk0mE+qoN9ESNBmRrhVDlyswO6MyrJBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T01:32:45.504580Z"},"content_sha256":"c9f8e528987ae4f3966d2346bb6a0e445416c34d3388b41698d91d41e54a81dd","schema_version":"1.0","event_id":"sha256:c9f8e528987ae4f3966d2346bb6a0e445416c34d3388b41698d91d41e54a81dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:62ZSN3XB3SP7UP5MZTO6EFRMSB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pick-or-Mix: Dynamic Channel Sampling for ConvNets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ashish Kumar, Daneul Kim, Jaesik Park, Laxmidhar Behera","submitted_at":"2024-06-16T13:33:09Z","abstract_excerpt":"Channel pruning approaches for convolutional neural networks (ConvNets) deactivate the channels, statically or dynamically, and require special implementation. In addition, channel squeezing in representative ConvNets is carried out via 1x1 convolutions which dominates a large portion of computations and network parameters. Given these challenges, we propose an effective multi-purpose module for dynamic channel sampling, namely Pick-or-Mix (PiX), which does not require special implementation. PiX divides a set of channels into subsets and then picks from them, where the picking decision is dyn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10935","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/2406.10935/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":"2026-07-05T08:32:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sdmf8cCwABRerewKKPVnYJjS45gFsy+GfVwAWT6xpJsTuz5l12CUQPPy5XLqIhBfNf2Dc2Odti9JJJ3YGcMyCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T01:32:45.504949Z"},"content_sha256":"8a1cd1325935ab2b6d2528430b69a62319a5056b9bac7f78067b059c5f445689","schema_version":"1.0","event_id":"sha256:8a1cd1325935ab2b6d2528430b69a62319a5056b9bac7f78067b059c5f445689"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/62ZSN3XB3SP7UP5MZTO6EFRMSB/bundle.json","state_url":"https://pith.science/pith/62ZSN3XB3SP7UP5MZTO6EFRMSB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/62ZSN3XB3SP7UP5MZTO6EFRMSB/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":"2026-07-12T01:32:45Z","links":{"resolver":"https://pith.science/pith/62ZSN3XB3SP7UP5MZTO6EFRMSB","bundle":"https://pith.science/pith/62ZSN3XB3SP7UP5MZTO6EFRMSB/bundle.json","state":"https://pith.science/pith/62ZSN3XB3SP7UP5MZTO6EFRMSB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/62ZSN3XB3SP7UP5MZTO6EFRMSB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:62ZSN3XB3SP7UP5MZTO6EFRMSB","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":"f279c285d819335b704263cb4ac405aa10eca7a7d697b406c6dedfe5c931f509","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-16T13:33:09Z","title_canon_sha256":"fa19199ffde9b735115d25d686e4e4ba62df3474650777ead57ffca644335460"},"schema_version":"1.0","source":{"id":"2406.10935","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10935","created_at":"2026-07-05T08:32:46Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10935v1","created_at":"2026-07-05T08:32:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10935","created_at":"2026-07-05T08:32:46Z"},{"alias_kind":"pith_short_12","alias_value":"62ZSN3XB3SP7","created_at":"2026-07-05T08:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"62ZSN3XB3SP7UP5M","created_at":"2026-07-05T08:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"62ZSN3XB","created_at":"2026-07-05T08:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:8a1cd1325935ab2b6d2528430b69a62319a5056b9bac7f78067b059c5f445689","target":"graph","created_at":"2026-07-05T08:32:46Z","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/2406.10935/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Channel pruning approaches for convolutional neural networks (ConvNets) deactivate the channels, statically or dynamically, and require special implementation. In addition, channel squeezing in representative ConvNets is carried out via 1x1 convolutions which dominates a large portion of computations and network parameters. Given these challenges, we propose an effective multi-purpose module for dynamic channel sampling, namely Pick-or-Mix (PiX), which does not require special implementation. PiX divides a set of channels into subsets and then picks from them, where the picking decision is dyn","authors_text":"Ashish Kumar, Daneul Kim, Jaesik Park, Laxmidhar Behera","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-16T13:33:09Z","title":"Pick-or-Mix: Dynamic Channel Sampling for ConvNets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10935","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:c9f8e528987ae4f3966d2346bb6a0e445416c34d3388b41698d91d41e54a81dd","target":"record","created_at":"2026-07-05T08:32:46Z","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":"f279c285d819335b704263cb4ac405aa10eca7a7d697b406c6dedfe5c931f509","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-16T13:33:09Z","title_canon_sha256":"fa19199ffde9b735115d25d686e4e4ba62df3474650777ead57ffca644335460"},"schema_version":"1.0","source":{"id":"2406.10935","kind":"arxiv","version":1}},"canonical_sha256":"f6b326eee1dc9ffa3facccdde2162c9061d24db2a561ed168c49f91550b77ab7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f6b326eee1dc9ffa3facccdde2162c9061d24db2a561ed168c49f91550b77ab7","first_computed_at":"2026-07-05T08:32:46.643975Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:46.643975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L79K9vs7Y8oIIKLDjuqfOeUcpKhztsyXWK/Zl04RZ9vCRcvb12kWDIXlL1uUbjtRERaTIJYEqlLS3SW7PZOODg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:46.644452Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10935","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9f8e528987ae4f3966d2346bb6a0e445416c34d3388b41698d91d41e54a81dd","sha256:8a1cd1325935ab2b6d2528430b69a62319a5056b9bac7f78067b059c5f445689"],"state_sha256":"290a198bcc817c5384c21e0dbc14a2a4047eab13c623aebc52a711c59e94c689"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5awEAn4o3XWccTbri4i3fsEEkKYFWaL32gT85gCMQhmTQZBEjLFvbJ1j3sVpbFqy0QbymWQoW6fd3wTrbXrnDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T01:32:45.507167Z","bundle_sha256":"e125e2b83fc5fe7d04737aa1da3345cfbebf02b1505805512d5d17aff4c80099"}}