{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NV5GOH7OGRW2EJCALDMYRE4HFE","short_pith_number":"pith:NV5GOH7O","schema_version":"1.0","canonical_sha256":"6d7a671fee346da2244058d9889387292f844dfcef20c8f95cdfe2a4005a4540","source":{"kind":"arxiv","id":"2212.10774","version":1},"attestation_state":"computed","paper":{"title":"Towards Efficient Visual Simplification of Computational Graphs in Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.HC","authors_text":"Caleb Chen Cao, Gongchang Ou, Han Gao, Jingli Xu, Rusheng Pan, Tong Xu, Wei Chen, Yating Wei, Zhiyong Wang","submitted_at":"2022-12-21T05:17:13Z","abstract_excerpt":"A computational graph in a deep neural network (DNN) denotes a specific data flow diagram (DFD) composed of many tensors and operators. Existing toolkits for visualizing computational graphs are not applicable when the structure is highly complicated and large-scale (e.g., BERT [1]). To address this problem, we propose leveraging a suite of visual simplification techniques, including a cycle-removing method, a module-based edge-pruning algorithm, and an isomorphic subgraph stacking strategy. We design and implement an interactive visualization system that is suitable for computational graphs w"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2212.10774","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2022-12-21T05:17:13Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"62f3fb3f4de4c4f3dde6695c14314e995767a852e74b5de6693af9e5a670185a","abstract_canon_sha256":"7266ef497f2963d3a7b0f0cbcb629df233a85f4acfb828567630363eda7c4871"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:29:04.774345Z","signature_b64":"fbsNcK/x14qkYEcNfkUxl8fm/aE0BbUOulE/vbNcsh0NyLNq+0qgUMjhI0VCz/pQdPaKTNRkLoz8r8hUocGODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d7a671fee346da2244058d9889387292f844dfcef20c8f95cdfe2a4005a4540","last_reissued_at":"2026-07-05T05:29:04.773745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:29:04.773745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Efficient Visual Simplification of Computational Graphs in Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.HC","authors_text":"Caleb Chen Cao, Gongchang Ou, Han Gao, Jingli Xu, Rusheng Pan, Tong Xu, Wei Chen, Yating Wei, Zhiyong Wang","submitted_at":"2022-12-21T05:17:13Z","abstract_excerpt":"A computational graph in a deep neural network (DNN) denotes a specific data flow diagram (DFD) composed of many tensors and operators. Existing toolkits for visualizing computational graphs are not applicable when the structure is highly complicated and large-scale (e.g., BERT [1]). To address this problem, we propose leveraging a suite of visual simplification techniques, including a cycle-removing method, a module-based edge-pruning algorithm, and an isomorphic subgraph stacking strategy. We design and implement an interactive visualization system that is suitable for computational graphs w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10774","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/2212.10774/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2212.10774","created_at":"2026-07-05T05:29:04.773803+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.10774v1","created_at":"2026-07-05T05:29:04.773803+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10774","created_at":"2026-07-05T05:29:04.773803+00:00"},{"alias_kind":"pith_short_12","alias_value":"NV5GOH7OGRW2","created_at":"2026-07-05T05:29:04.773803+00:00"},{"alias_kind":"pith_short_16","alias_value":"NV5GOH7OGRW2EJCA","created_at":"2026-07-05T05:29:04.773803+00:00"},{"alias_kind":"pith_short_8","alias_value":"NV5GOH7O","created_at":"2026-07-05T05:29:04.773803+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NV5GOH7OGRW2EJCALDMYRE4HFE","json":"https://pith.science/pith/NV5GOH7OGRW2EJCALDMYRE4HFE.json","graph_json":"https://pith.science/api/pith-number/NV5GOH7OGRW2EJCALDMYRE4HFE/graph.json","events_json":"https://pith.science/api/pith-number/NV5GOH7OGRW2EJCALDMYRE4HFE/events.json","paper":"https://pith.science/paper/NV5GOH7O"},"agent_actions":{"view_html":"https://pith.science/pith/NV5GOH7OGRW2EJCALDMYRE4HFE","download_json":"https://pith.science/pith/NV5GOH7OGRW2EJCALDMYRE4HFE.json","view_paper":"https://pith.science/paper/NV5GOH7O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.10774&json=true","fetch_graph":"https://pith.science/api/pith-number/NV5GOH7OGRW2EJCALDMYRE4HFE/graph.json","fetch_events":"https://pith.science/api/pith-number/NV5GOH7OGRW2EJCALDMYRE4HFE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NV5GOH7OGRW2EJCALDMYRE4HFE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NV5GOH7OGRW2EJCALDMYRE4HFE/action/storage_attestation","attest_author":"https://pith.science/pith/NV5GOH7OGRW2EJCALDMYRE4HFE/action/author_attestation","sign_citation":"https://pith.science/pith/NV5GOH7OGRW2EJCALDMYRE4HFE/action/citation_signature","submit_replication":"https://pith.science/pith/NV5GOH7OGRW2EJCALDMYRE4HFE/action/replication_record"}},"created_at":"2026-07-05T05:29:04.773803+00:00","updated_at":"2026-07-05T05:29:04.773803+00:00"}