{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ZDMRGAF7GJB5SBVQAS6K3ZFKO6","short_pith_number":"pith:ZDMRGAF7","canonical_record":{"source":{"id":"2109.09310","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-20T06:07:14Z","cross_cats_sorted":[],"title_canon_sha256":"775ee8e05cd4cd0dd61f4c57dbc6515011e06f216f2e0c1d0444cd857b081f91","abstract_canon_sha256":"25a80489bfeabe1ea72ff62b57e691f10ae4e81a9a955ff11b2cf63dca017462"},"schema_version":"1.0"},"canonical_sha256":"c8d91300bf3243d906b004bcade4aa779e6f7e34aec1252f2fc5a828d5d3047a","source":{"kind":"arxiv","id":"2109.09310","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.09310","created_at":"2026-07-05T03:16:34Z"},{"alias_kind":"arxiv_version","alias_value":"2109.09310v1","created_at":"2026-07-05T03:16:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09310","created_at":"2026-07-05T03:16:34Z"},{"alias_kind":"pith_short_12","alias_value":"ZDMRGAF7GJB5","created_at":"2026-07-05T03:16:34Z"},{"alias_kind":"pith_short_16","alias_value":"ZDMRGAF7GJB5SBVQ","created_at":"2026-07-05T03:16:34Z"},{"alias_kind":"pith_short_8","alias_value":"ZDMRGAF7","created_at":"2026-07-05T03:16:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ZDMRGAF7GJB5SBVQAS6K3ZFKO6","target":"record","payload":{"canonical_record":{"source":{"id":"2109.09310","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-20T06:07:14Z","cross_cats_sorted":[],"title_canon_sha256":"775ee8e05cd4cd0dd61f4c57dbc6515011e06f216f2e0c1d0444cd857b081f91","abstract_canon_sha256":"25a80489bfeabe1ea72ff62b57e691f10ae4e81a9a955ff11b2cf63dca017462"},"schema_version":"1.0"},"canonical_sha256":"c8d91300bf3243d906b004bcade4aa779e6f7e34aec1252f2fc5a828d5d3047a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:16:34.631524Z","signature_b64":"W0KicJg5zJ5aSPUKfCbNmlO1h3MWUm3GYtWI9+UIAlS3x33/ZxI1qnzKI1YFRF46pIkGsVUnIlpf8NBrnu/JBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8d91300bf3243d906b004bcade4aa779e6f7e34aec1252f2fc5a828d5d3047a","last_reissued_at":"2026-07-05T03:16:34.631062Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:16:34.631062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.09310","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":"2026-07-05T03:16:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c49xOMCM8c2PICcLTc6jR7XnSLodfIcn4505m9jozGmSM95tCGRqGQ86RaepI7z0O91sYQDpt4d9k/GIrlGdAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:18:03.574907Z"},"content_sha256":"cd8c098234bb36f688d4b534133523f28c456117c9c5cdfcf887cac43ac51c68","schema_version":"1.0","event_id":"sha256:cd8c098234bb36f688d4b534133523f28c456117c9c5cdfcf887cac43ac51c68"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ZDMRGAF7GJB5SBVQAS6K3ZFKO6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Versatile Convolution Filters for Efficient Visual Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Xu, Chunjing Xu, Dacheng Tao, Enhua Wu, Kai Han, Yunhe Wang","submitted_at":"2021-09-20T06:07:14Z","abstract_excerpt":"This paper introduces versatile filters to construct efficient convolutional neural networks that are widely used in various visual recognition tasks. Considering the demands of efficient deep learning techniques running on cost-effective hardware, a number of methods have been developed to learn compact neural networks. Most of these works aim to slim down filters in different ways, \\eg,~investigating small, sparse or quantized filters. In contrast, we treat filters from an additive perspective. A series of secondary filters can be derived from a primary filter with the help of binary masks. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09310","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/2109.09310/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":"2026-07-05T03:16:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yc1qNqFd2rhJmgZ+sJvcVWOEhdqg5w0leeFAxmYv9o/ZbXOCrkpn57ZWxz9NTnfQU9c7rpnCevdfOE+LJCFHCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:18:03.575622Z"},"content_sha256":"ce3d85ef2b7a574e95f672132b9243e9696d0241517e9c58b1cfc796ff856d2f","schema_version":"1.0","event_id":"sha256:ce3d85ef2b7a574e95f672132b9243e9696d0241517e9c58b1cfc796ff856d2f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZDMRGAF7GJB5SBVQAS6K3ZFKO6/bundle.json","state_url":"https://pith.science/pith/ZDMRGAF7GJB5SBVQAS6K3ZFKO6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZDMRGAF7GJB5SBVQAS6K3ZFKO6/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":"2026-08-05T13:18:03Z","links":{"resolver":"https://pith.science/pith/ZDMRGAF7GJB5SBVQAS6K3ZFKO6","bundle":"https://pith.science/pith/ZDMRGAF7GJB5SBVQAS6K3ZFKO6/bundle.json","state":"https://pith.science/pith/ZDMRGAF7GJB5SBVQAS6K3ZFKO6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZDMRGAF7GJB5SBVQAS6K3ZFKO6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZDMRGAF7GJB5SBVQAS6K3ZFKO6","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":"25a80489bfeabe1ea72ff62b57e691f10ae4e81a9a955ff11b2cf63dca017462","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-20T06:07:14Z","title_canon_sha256":"775ee8e05cd4cd0dd61f4c57dbc6515011e06f216f2e0c1d0444cd857b081f91"},"schema_version":"1.0","source":{"id":"2109.09310","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.09310","created_at":"2026-07-05T03:16:34Z"},{"alias_kind":"arxiv_version","alias_value":"2109.09310v1","created_at":"2026-07-05T03:16:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09310","created_at":"2026-07-05T03:16:34Z"},{"alias_kind":"pith_short_12","alias_value":"ZDMRGAF7GJB5","created_at":"2026-07-05T03:16:34Z"},{"alias_kind":"pith_short_16","alias_value":"ZDMRGAF7GJB5SBVQ","created_at":"2026-07-05T03:16:34Z"},{"alias_kind":"pith_short_8","alias_value":"ZDMRGAF7","created_at":"2026-07-05T03:16:34Z"}],"graph_snapshots":[{"event_id":"sha256:ce3d85ef2b7a574e95f672132b9243e9696d0241517e9c58b1cfc796ff856d2f","target":"graph","created_at":"2026-07-05T03:16:34Z","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/2109.09310/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces versatile filters to construct efficient convolutional neural networks that are widely used in various visual recognition tasks. Considering the demands of efficient deep learning techniques running on cost-effective hardware, a number of methods have been developed to learn compact neural networks. Most of these works aim to slim down filters in different ways, \\eg,~investigating small, sparse or quantized filters. In contrast, we treat filters from an additive perspective. A series of secondary filters can be derived from a primary filter with the help of binary masks. ","authors_text":"Chang Xu, Chunjing Xu, Dacheng Tao, Enhua Wu, Kai Han, Yunhe Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-20T06:07:14Z","title":"Learning Versatile Convolution Filters for Efficient Visual Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09310","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:cd8c098234bb36f688d4b534133523f28c456117c9c5cdfcf887cac43ac51c68","target":"record","created_at":"2026-07-05T03:16:34Z","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":"25a80489bfeabe1ea72ff62b57e691f10ae4e81a9a955ff11b2cf63dca017462","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-20T06:07:14Z","title_canon_sha256":"775ee8e05cd4cd0dd61f4c57dbc6515011e06f216f2e0c1d0444cd857b081f91"},"schema_version":"1.0","source":{"id":"2109.09310","kind":"arxiv","version":1}},"canonical_sha256":"c8d91300bf3243d906b004bcade4aa779e6f7e34aec1252f2fc5a828d5d3047a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8d91300bf3243d906b004bcade4aa779e6f7e34aec1252f2fc5a828d5d3047a","first_computed_at":"2026-07-05T03:16:34.631062Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:16:34.631062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W0KicJg5zJ5aSPUKfCbNmlO1h3MWUm3GYtWI9+UIAlS3x33/ZxI1qnzKI1YFRF46pIkGsVUnIlpf8NBrnu/JBA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:16:34.631524Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.09310","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd8c098234bb36f688d4b534133523f28c456117c9c5cdfcf887cac43ac51c68","sha256:ce3d85ef2b7a574e95f672132b9243e9696d0241517e9c58b1cfc796ff856d2f"],"state_sha256":"1fd4743e35a0d45cdcd31f2bd51b205f95dadd7b023d95ca7d4134fdb4fb5bab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KDK6BnYT2DQuH4Rt5ZC6lmx3Y5gwcSlP5QItlJCCdgxuwnaz0t1RuxColnsM9L1DZ3U3j1slnNZ2zrl8A5HHBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T13:18:03.587339Z","bundle_sha256":"c2be2f89263a794cfe9c86190356be31a428c7ccd4759c8b6e5bdddb9037d820"}}