{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:K7UHUSGUGZWEKNRQW5VYX4R6GJ","short_pith_number":"pith:K7UHUSGU","canonical_record":{"source":{"id":"2308.14605","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-28T14:19:13Z","cross_cats_sorted":[],"title_canon_sha256":"1f4c7174ec6742e1af15e6891006f386dd4784ce6519a4963550b312e192273f","abstract_canon_sha256":"06c3989ca1de432c426ca5bf905dd4d35c2d2887a055479fbc9a8031ae83db05"},"schema_version":"1.0"},"canonical_sha256":"57e87a48d4366c453630b76b8bf23e3262a37f7a15faebdcc1c03ff3a999fd89","source":{"kind":"arxiv","id":"2308.14605","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.14605","created_at":"2026-07-05T06:45:28Z"},{"alias_kind":"arxiv_version","alias_value":"2308.14605v1","created_at":"2026-07-05T06:45:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.14605","created_at":"2026-07-05T06:45:28Z"},{"alias_kind":"pith_short_12","alias_value":"K7UHUSGUGZWE","created_at":"2026-07-05T06:45:28Z"},{"alias_kind":"pith_short_16","alias_value":"K7UHUSGUGZWEKNRQ","created_at":"2026-07-05T06:45:28Z"},{"alias_kind":"pith_short_8","alias_value":"K7UHUSGU","created_at":"2026-07-05T06:45:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:K7UHUSGUGZWEKNRQW5VYX4R6GJ","target":"record","payload":{"canonical_record":{"source":{"id":"2308.14605","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-28T14:19:13Z","cross_cats_sorted":[],"title_canon_sha256":"1f4c7174ec6742e1af15e6891006f386dd4784ce6519a4963550b312e192273f","abstract_canon_sha256":"06c3989ca1de432c426ca5bf905dd4d35c2d2887a055479fbc9a8031ae83db05"},"schema_version":"1.0"},"canonical_sha256":"57e87a48d4366c453630b76b8bf23e3262a37f7a15faebdcc1c03ff3a999fd89","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:45:28.558652Z","signature_b64":"B+IKCEFP3nWc5vsQVUwGg3LC530Z9JAI2A6SXhTP4uXTwV8ZIV+sDJCi7Vw4gPTEe1KKXqFnsdo5LACa1xgkBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57e87a48d4366c453630b76b8bf23e3262a37f7a15faebdcc1c03ff3a999fd89","last_reissued_at":"2026-07-05T06:45:28.558088Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:45:28.558088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.14605","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":"2026-07-05T06:45:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zs6s17D1jhIqmE3q6Q7p2hq5SusqSyvBgBePiM+ZTQP5XeuIjuJ0gWvjTCRyO84qAJ6VTmITyYTsi0yPX15bDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T09:06:26.493808Z"},"content_sha256":"030fe59c5ea41cff47326f35e8620106dfed181bbd57523aad93de4da2df1b6a","schema_version":"1.0","event_id":"sha256:030fe59c5ea41cff47326f35e8620106dfed181bbd57523aad93de4da2df1b6a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:K7UHUSGUGZWEKNRQW5VYX4R6GJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Generalization of Continuous Relaxation in Structured Pruning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bishal Upadhyaya, Brad Larson, Luke McDermott, Siddha Ganju","submitted_at":"2023-08-28T14:19:13Z","abstract_excerpt":"Deep learning harnesses massive parallel floating-point processing to train and evaluate large neural networks. Trends indicate that deeper and larger neural networks with an increasing number of parameters achieve higher accuracy than smaller neural networks. This performance improvement, which often requires heavy compute for both training and evaluation, eventually needs to translate well to resource-constrained hardware for practical value. Structured pruning asserts that while large networks enable us to find solutions to complex computer vision problems, a smaller, computationally effici"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.14605","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/2308.14605/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":"2026-07-05T06:45:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"owpI8jW+sKLJjpQyac07ri/WiratbfA7d43lxglQgfZF/OzCxHbir7SjJ8ygxqiVRpX8ilXnUvUsEFmBdEaiAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T09:06:26.494297Z"},"content_sha256":"3156767338c58026966ce79002d2910573a0529fd4ec7d10324571d38489be00","schema_version":"1.0","event_id":"sha256:3156767338c58026966ce79002d2910573a0529fd4ec7d10324571d38489be00"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K7UHUSGUGZWEKNRQW5VYX4R6GJ/bundle.json","state_url":"https://pith.science/pith/K7UHUSGUGZWEKNRQW5VYX4R6GJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K7UHUSGUGZWEKNRQW5VYX4R6GJ/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":"2026-08-22T09:06:26Z","links":{"resolver":"https://pith.science/pith/K7UHUSGUGZWEKNRQW5VYX4R6GJ","bundle":"https://pith.science/pith/K7UHUSGUGZWEKNRQW5VYX4R6GJ/bundle.json","state":"https://pith.science/pith/K7UHUSGUGZWEKNRQW5VYX4R6GJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K7UHUSGUGZWEKNRQW5VYX4R6GJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:K7UHUSGUGZWEKNRQW5VYX4R6GJ","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":"06c3989ca1de432c426ca5bf905dd4d35c2d2887a055479fbc9a8031ae83db05","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-28T14:19:13Z","title_canon_sha256":"1f4c7174ec6742e1af15e6891006f386dd4784ce6519a4963550b312e192273f"},"schema_version":"1.0","source":{"id":"2308.14605","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.14605","created_at":"2026-07-05T06:45:28Z"},{"alias_kind":"arxiv_version","alias_value":"2308.14605v1","created_at":"2026-07-05T06:45:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.14605","created_at":"2026-07-05T06:45:28Z"},{"alias_kind":"pith_short_12","alias_value":"K7UHUSGUGZWE","created_at":"2026-07-05T06:45:28Z"},{"alias_kind":"pith_short_16","alias_value":"K7UHUSGUGZWEKNRQ","created_at":"2026-07-05T06:45:28Z"},{"alias_kind":"pith_short_8","alias_value":"K7UHUSGU","created_at":"2026-07-05T06:45:28Z"}],"graph_snapshots":[{"event_id":"sha256:3156767338c58026966ce79002d2910573a0529fd4ec7d10324571d38489be00","target":"graph","created_at":"2026-07-05T06:45:28Z","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/2308.14605/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep learning harnesses massive parallel floating-point processing to train and evaluate large neural networks. Trends indicate that deeper and larger neural networks with an increasing number of parameters achieve higher accuracy than smaller neural networks. This performance improvement, which often requires heavy compute for both training and evaluation, eventually needs to translate well to resource-constrained hardware for practical value. Structured pruning asserts that while large networks enable us to find solutions to complex computer vision problems, a smaller, computationally effici","authors_text":"Bishal Upadhyaya, Brad Larson, Luke McDermott, Siddha Ganju","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-28T14:19:13Z","title":"A Generalization of Continuous Relaxation in Structured Pruning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.14605","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":"sha256:030fe59c5ea41cff47326f35e8620106dfed181bbd57523aad93de4da2df1b6a","target":"record","created_at":"2026-07-05T06:45:28Z","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":"06c3989ca1de432c426ca5bf905dd4d35c2d2887a055479fbc9a8031ae83db05","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-28T14:19:13Z","title_canon_sha256":"1f4c7174ec6742e1af15e6891006f386dd4784ce6519a4963550b312e192273f"},"schema_version":"1.0","source":{"id":"2308.14605","kind":"arxiv","version":1}},"canonical_sha256":"57e87a48d4366c453630b76b8bf23e3262a37f7a15faebdcc1c03ff3a999fd89","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57e87a48d4366c453630b76b8bf23e3262a37f7a15faebdcc1c03ff3a999fd89","first_computed_at":"2026-07-05T06:45:28.558088Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:45:28.558088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B+IKCEFP3nWc5vsQVUwGg3LC530Z9JAI2A6SXhTP4uXTwV8ZIV+sDJCi7Vw4gPTEe1KKXqFnsdo5LACa1xgkBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:45:28.558652Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.14605","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:030fe59c5ea41cff47326f35e8620106dfed181bbd57523aad93de4da2df1b6a","sha256:3156767338c58026966ce79002d2910573a0529fd4ec7d10324571d38489be00"],"state_sha256":"c4ea7e6918b66514d91d803a87c3a8024d527105877a95c0e870ed3f62ce2048"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Wyrivl1v9y2XlOwMrPmvbuqqDmA+1HM39c7EyKkqFwr/wXbE/z2MUeApiItFiOH9VZoy5K/7nZiwVB8CIKRDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T09:06:26.499011Z","bundle_sha256":"8957feb64f2d55ffc9186a91c1de40cf21edc7d0115556f5ccf0bc7800247a97"}}