{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:NN5NHW2CXMZMQUFT7DC45FZPSE","short_pith_number":"pith:NN5NHW2C","schema_version":"1.0","canonical_sha256":"6b7ad3db42bb32c850b3f8c5ce972f912490d7edca36c8d1058b893e9875d24a","source":{"kind":"arxiv","id":"1907.02547","version":2},"attestation_state":"computed","paper":{"title":"Exploiting Prunability for Person Re-Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Amran Bhuiyan, Eric Granger, Hugo Masson, Ismail Ben Ayed, Le Thanh Nguyen-Meidine, Mehrsan Javan, Parthipan Siva","submitted_at":"2019-07-04T18:02:53Z","abstract_excerpt":"Recent years have witnessed a substantial increase in the deep learning (DL)architectures proposed for visual recognition tasks like person re-identification,where individuals must be recognized over multiple distributed cameras. Althoughthese architectures have greatly improved the state-of-the-art accuracy, thecomputational complexity of the CNNs commonly used for feature extractionremains an issue, hindering their deployment on platforms with limited resources,or in applications with real-time constraints. There is an obvious advantage toaccelerating and compressing DL models without signif"},"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":"1907.02547","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-04T18:02:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6bacd6f8e89ea057f5db5383585e1f8212f03f46bd3245b02bd86a4c9712ebe9","abstract_canon_sha256":"d99cfb21c3a9e867cf58ade091b4326e24aa9705c0ca55203caaa0c2f36922ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:31:57.997622Z","signature_b64":"h/uHAfltVln/HQmW5ICTSL1YJ5JHsm+oiKyeN/t4FAZHPXB8Z0XVmbfBjmoho0e71XOvo2vOUC6EkPM/t1BwCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b7ad3db42bb32c850b3f8c5ce972f912490d7edca36c8d1058b893e9875d24a","last_reissued_at":"2026-07-05T02:31:57.997136Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:31:57.997136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploiting Prunability for Person Re-Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Amran Bhuiyan, Eric Granger, Hugo Masson, Ismail Ben Ayed, Le Thanh Nguyen-Meidine, Mehrsan Javan, Parthipan Siva","submitted_at":"2019-07-04T18:02:53Z","abstract_excerpt":"Recent years have witnessed a substantial increase in the deep learning (DL)architectures proposed for visual recognition tasks like person re-identification,where individuals must be recognized over multiple distributed cameras. Althoughthese architectures have greatly improved the state-of-the-art accuracy, thecomputational complexity of the CNNs commonly used for feature extractionremains an issue, hindering their deployment on platforms with limited resources,or in applications with real-time constraints. There is an obvious advantage toaccelerating and compressing DL models without signif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.02547","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/1907.02547/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":"1907.02547","created_at":"2026-07-05T02:31:57.997202+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.02547v2","created_at":"2026-07-05T02:31:57.997202+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.02547","created_at":"2026-07-05T02:31:57.997202+00:00"},{"alias_kind":"pith_short_12","alias_value":"NN5NHW2CXMZM","created_at":"2026-07-05T02:31:57.997202+00:00"},{"alias_kind":"pith_short_16","alias_value":"NN5NHW2CXMZMQUFT","created_at":"2026-07-05T02:31:57.997202+00:00"},{"alias_kind":"pith_short_8","alias_value":"NN5NHW2C","created_at":"2026-07-05T02:31:57.997202+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00506","citing_title":"SCING:Towards More Efficient and Robust Person Re-Identification through Selective Cross-modal Prompt Tuning","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NN5NHW2CXMZMQUFT7DC45FZPSE","json":"https://pith.science/pith/NN5NHW2CXMZMQUFT7DC45FZPSE.json","graph_json":"https://pith.science/api/pith-number/NN5NHW2CXMZMQUFT7DC45FZPSE/graph.json","events_json":"https://pith.science/api/pith-number/NN5NHW2CXMZMQUFT7DC45FZPSE/events.json","paper":"https://pith.science/paper/NN5NHW2C"},"agent_actions":{"view_html":"https://pith.science/pith/NN5NHW2CXMZMQUFT7DC45FZPSE","download_json":"https://pith.science/pith/NN5NHW2CXMZMQUFT7DC45FZPSE.json","view_paper":"https://pith.science/paper/NN5NHW2C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.02547&json=true","fetch_graph":"https://pith.science/api/pith-number/NN5NHW2CXMZMQUFT7DC45FZPSE/graph.json","fetch_events":"https://pith.science/api/pith-number/NN5NHW2CXMZMQUFT7DC45FZPSE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NN5NHW2CXMZMQUFT7DC45FZPSE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NN5NHW2CXMZMQUFT7DC45FZPSE/action/storage_attestation","attest_author":"https://pith.science/pith/NN5NHW2CXMZMQUFT7DC45FZPSE/action/author_attestation","sign_citation":"https://pith.science/pith/NN5NHW2CXMZMQUFT7DC45FZPSE/action/citation_signature","submit_replication":"https://pith.science/pith/NN5NHW2CXMZMQUFT7DC45FZPSE/action/replication_record"}},"created_at":"2026-07-05T02:31:57.997202+00:00","updated_at":"2026-07-05T02:31:57.997202+00:00"}