{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:T3UT3B3PEZ3QY7PBTYPXMWEUZJ","short_pith_number":"pith:T3UT3B3P","canonical_record":{"source":{"id":"2102.03214","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-02-05T14:59:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"85ea4f4088cc3dd75ba0309f4c80e5180b3dd91e9fa414899a5f630aefec06e6","abstract_canon_sha256":"44d1fb3843d7a60e3a06b3e018caf90fba4773a652d3e6aec4e917c4c54e7e55"},"schema_version":"1.0"},"canonical_sha256":"9ee93d876f26770c7de19e1f765894ca5c942e7b4b2420b3744bcbe905b4670d","source":{"kind":"arxiv","id":"2102.03214","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.03214","created_at":"2026-07-05T04:36:31Z"},{"alias_kind":"arxiv_version","alias_value":"2102.03214v2","created_at":"2026-07-05T04:36:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.03214","created_at":"2026-07-05T04:36:31Z"},{"alias_kind":"pith_short_12","alias_value":"T3UT3B3PEZ3Q","created_at":"2026-07-05T04:36:31Z"},{"alias_kind":"pith_short_16","alias_value":"T3UT3B3PEZ3QY7PB","created_at":"2026-07-05T04:36:31Z"},{"alias_kind":"pith_short_8","alias_value":"T3UT3B3P","created_at":"2026-07-05T04:36:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:T3UT3B3PEZ3QY7PBTYPXMWEUZJ","target":"record","payload":{"canonical_record":{"source":{"id":"2102.03214","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-02-05T14:59:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"85ea4f4088cc3dd75ba0309f4c80e5180b3dd91e9fa414899a5f630aefec06e6","abstract_canon_sha256":"44d1fb3843d7a60e3a06b3e018caf90fba4773a652d3e6aec4e917c4c54e7e55"},"schema_version":"1.0"},"canonical_sha256":"9ee93d876f26770c7de19e1f765894ca5c942e7b4b2420b3744bcbe905b4670d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:31.918248Z","signature_b64":"Fm5aHXJc8wnSZWWvhoO8+buXqEaqYpXNIqDpBI2m3RscjH5kfocHs6/UZX1Lph6IcI36nDYyPbi8/nxDcR0lCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ee93d876f26770c7de19e1f765894ca5c942e7b4b2420b3744bcbe905b4670d","last_reissued_at":"2026-07-05T04:36:31.917722Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:31.917722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.03214","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:36:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IKDg6ZjqHCTXmcPmyptdaawq0g5eHnh/A4cbZXY4aT11KkZkf1O5Zyim7W2NuH80vZ9+pHfu913zu3SWzTgfDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:46:34.776522Z"},"content_sha256":"0371fed077847b950071e15614ccd37acd069d889bea9e32ad31b00744315ef1","schema_version":"1.0","event_id":"sha256:0371fed077847b950071e15614ccd37acd069d889bea9e32ad31b00744315ef1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:T3UT3B3PEZ3QY7PBTYPXMWEUZJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ali Jannesari, Arya Mazaheri, Sixing Yu","submitted_at":"2021-02-05T14:59:32Z","abstract_excerpt":"Model compression is an essential technique for deploying deep neural networks (DNNs) on power and memory-constrained resources. However, existing model-compression methods often rely on human expertise and focus on parameters' local importance, ignoring the rich topology information within DNNs. In this paper, we propose a novel multi-stage graph embedding technique based on graph neural networks (GNNs) to identify DNN topologies and use reinforcement learning (RL) to find a suitable compression policy. We performed resource-constrained (i.e., FLOPs) channel pruning and compared our approach "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.03214","kind":"arxiv","version":2},"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/2102.03214/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":"2026-07-05T04:36:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yunbNYkvn50S8UJP7cp5cum4+GaW6B00NJ3IMoNlQrnGQthdMwd69uebgqmSemgs/7GQ5eaFYBfNZdhcZgN5DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:46:34.777109Z"},"content_sha256":"8a894ea479d5496a9cb23a1692b7cff587bad15c5a1ab162a6de449b33449a5c","schema_version":"1.0","event_id":"sha256:8a894ea479d5496a9cb23a1692b7cff587bad15c5a1ab162a6de449b33449a5c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T3UT3B3PEZ3QY7PBTYPXMWEUZJ/bundle.json","state_url":"https://pith.science/pith/T3UT3B3PEZ3QY7PBTYPXMWEUZJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T3UT3B3PEZ3QY7PBTYPXMWEUZJ/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":"2026-08-05T20:46:34Z","links":{"resolver":"https://pith.science/pith/T3UT3B3PEZ3QY7PBTYPXMWEUZJ","bundle":"https://pith.science/pith/T3UT3B3PEZ3QY7PBTYPXMWEUZJ/bundle.json","state":"https://pith.science/pith/T3UT3B3PEZ3QY7PBTYPXMWEUZJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T3UT3B3PEZ3QY7PBTYPXMWEUZJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:T3UT3B3PEZ3QY7PBTYPXMWEUZJ","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":"44d1fb3843d7a60e3a06b3e018caf90fba4773a652d3e6aec4e917c4c54e7e55","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-02-05T14:59:32Z","title_canon_sha256":"85ea4f4088cc3dd75ba0309f4c80e5180b3dd91e9fa414899a5f630aefec06e6"},"schema_version":"1.0","source":{"id":"2102.03214","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.03214","created_at":"2026-07-05T04:36:31Z"},{"alias_kind":"arxiv_version","alias_value":"2102.03214v2","created_at":"2026-07-05T04:36:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.03214","created_at":"2026-07-05T04:36:31Z"},{"alias_kind":"pith_short_12","alias_value":"T3UT3B3PEZ3Q","created_at":"2026-07-05T04:36:31Z"},{"alias_kind":"pith_short_16","alias_value":"T3UT3B3PEZ3QY7PB","created_at":"2026-07-05T04:36:31Z"},{"alias_kind":"pith_short_8","alias_value":"T3UT3B3P","created_at":"2026-07-05T04:36:31Z"}],"graph_snapshots":[{"event_id":"sha256:8a894ea479d5496a9cb23a1692b7cff587bad15c5a1ab162a6de449b33449a5c","target":"graph","created_at":"2026-07-05T04:36:31Z","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/2102.03214/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model compression is an essential technique for deploying deep neural networks (DNNs) on power and memory-constrained resources. However, existing model-compression methods often rely on human expertise and focus on parameters' local importance, ignoring the rich topology information within DNNs. In this paper, we propose a novel multi-stage graph embedding technique based on graph neural networks (GNNs) to identify DNN topologies and use reinforcement learning (RL) to find a suitable compression policy. We performed resource-constrained (i.e., FLOPs) channel pruning and compared our approach ","authors_text":"Ali Jannesari, Arya Mazaheri, Sixing Yu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-02-05T14:59:32Z","title":"Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.03214","kind":"arxiv","version":2},"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":"sha256:0371fed077847b950071e15614ccd37acd069d889bea9e32ad31b00744315ef1","target":"record","created_at":"2026-07-05T04:36:31Z","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":"44d1fb3843d7a60e3a06b3e018caf90fba4773a652d3e6aec4e917c4c54e7e55","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-02-05T14:59:32Z","title_canon_sha256":"85ea4f4088cc3dd75ba0309f4c80e5180b3dd91e9fa414899a5f630aefec06e6"},"schema_version":"1.0","source":{"id":"2102.03214","kind":"arxiv","version":2}},"canonical_sha256":"9ee93d876f26770c7de19e1f765894ca5c942e7b4b2420b3744bcbe905b4670d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ee93d876f26770c7de19e1f765894ca5c942e7b4b2420b3744bcbe905b4670d","first_computed_at":"2026-07-05T04:36:31.917722Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:36:31.917722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fm5aHXJc8wnSZWWvhoO8+buXqEaqYpXNIqDpBI2m3RscjH5kfocHs6/UZX1Lph6IcI36nDYyPbi8/nxDcR0lCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:36:31.918248Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.03214","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0371fed077847b950071e15614ccd37acd069d889bea9e32ad31b00744315ef1","sha256:8a894ea479d5496a9cb23a1692b7cff587bad15c5a1ab162a6de449b33449a5c"],"state_sha256":"369098f16b9075686c0d4c854df301257817a139f511e0c9c72868d9e5c6a330"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f8xY3Ik+5fbXswvzoBuwANGE02IJLa/Ycx11MKp2c3Ya8CgkaSqSymgAPY1BBTiuhNRWS4B+Eh56iKo1NFHCAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T20:46:34.781180Z","bundle_sha256":"a2ff63384e698df252400b4e4c1516f578c595afcc8667384dce6f8e5c00020c"}}