{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:R5U2N2MYB3RXLUN62FZPE5LLBE","short_pith_number":"pith:R5U2N2MY","canonical_record":{"source":{"id":"2505.11569","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T10:06:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3acfaac97508cbbb54f2f4574525c74bdd84fe83fc7443836ad7f4ff7e6f8fa6","abstract_canon_sha256":"2c6e78df16ce52ce850dc6c0f4db078fbf7899e1e50c1325c9f3b580544e2d49"},"schema_version":"1.0"},"canonical_sha256":"8f69a6e9980ee375d1bed172f2756b093f4be9a97f60924b7baad365ab943d11","source":{"kind":"arxiv","id":"2505.11569","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11569","created_at":"2026-07-05T11:04:23Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11569v1","created_at":"2026-07-05T11:04:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11569","created_at":"2026-07-05T11:04:23Z"},{"alias_kind":"pith_short_12","alias_value":"R5U2N2MYB3RX","created_at":"2026-07-05T11:04:23Z"},{"alias_kind":"pith_short_16","alias_value":"R5U2N2MYB3RXLUN6","created_at":"2026-07-05T11:04:23Z"},{"alias_kind":"pith_short_8","alias_value":"R5U2N2MY","created_at":"2026-07-05T11:04:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:R5U2N2MYB3RXLUN62FZPE5LLBE","target":"record","payload":{"canonical_record":{"source":{"id":"2505.11569","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T10:06:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3acfaac97508cbbb54f2f4574525c74bdd84fe83fc7443836ad7f4ff7e6f8fa6","abstract_canon_sha256":"2c6e78df16ce52ce850dc6c0f4db078fbf7899e1e50c1325c9f3b580544e2d49"},"schema_version":"1.0"},"canonical_sha256":"8f69a6e9980ee375d1bed172f2756b093f4be9a97f60924b7baad365ab943d11","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:23.843060Z","signature_b64":"OUoZDR75bPKzsN3H5loxwzRhYfYfFMtd9u4a6AEOfPPmKVfOIJhReHrWxpJY9ttTCQoUN5p1A5KjekfFxv3QDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f69a6e9980ee375d1bed172f2756b093f4be9a97f60924b7baad365ab943d11","last_reissued_at":"2026-07-05T11:04:23.842566Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:23.842566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.11569","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":"2026-07-05T11:04:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SqiHeRbb+7xex9XiBeLOBkSFvxf0Y3RJC/6In8FGDsTU+IRJ3/iP54NNFrO2ZeTnOXbmtXJTnYhvgt7Ur/dHDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T07:14:19.651436Z"},"content_sha256":"d4839548fe675a4815aa2a5e8003f3326808638e4bee36055a396e2b9a880da2","schema_version":"1.0","event_id":"sha256:d4839548fe675a4815aa2a5e8003f3326808638e4bee36055a396e2b9a880da2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:R5U2N2MYB3RXLUN62FZPE5LLBE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Adaptive Deep Learning: Model Elasticity via Prune-and-Grow CNN Architectures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dolly Sapra, Pooja Mangal, Sudaksh Kalra","submitted_at":"2025-05-16T10:06:55Z","abstract_excerpt":"Deploying deep convolutional neural networks (CNNs) on resource-constrained devices presents significant challenges due to their high computational demands and rigid, static architectures. To overcome these limitations, this thesis explores methods for enabling CNNs to dynamically adjust their computational complexity based on available hardware resources. We introduce adaptive CNN architectures capable of scaling their capacity at runtime, thus efficiently balancing performance and resource utilization. To achieve this adaptability, we propose a structured pruning and dynamic re-construction "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11569","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/2505.11569/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":"2026-07-05T11:04:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4AmrYp6I7BhgDULj0wL2H/IS14Qg7cd/dieIINTLT5s+k1jtpvO6gjZyXcbv3Bj0be5rrl+PARnebbI9qPdNDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T07:14:19.651945Z"},"content_sha256":"e84ce9991bb5deffdeaa0d74137e11a26e3e036471d96f7bbdfac5f81ef4dde0","schema_version":"1.0","event_id":"sha256:e84ce9991bb5deffdeaa0d74137e11a26e3e036471d96f7bbdfac5f81ef4dde0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R5U2N2MYB3RXLUN62FZPE5LLBE/bundle.json","state_url":"https://pith.science/pith/R5U2N2MYB3RXLUN62FZPE5LLBE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R5U2N2MYB3RXLUN62FZPE5LLBE/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":"2026-08-20T07:14:19Z","links":{"resolver":"https://pith.science/pith/R5U2N2MYB3RXLUN62FZPE5LLBE","bundle":"https://pith.science/pith/R5U2N2MYB3RXLUN62FZPE5LLBE/bundle.json","state":"https://pith.science/pith/R5U2N2MYB3RXLUN62FZPE5LLBE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R5U2N2MYB3RXLUN62FZPE5LLBE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:R5U2N2MYB3RXLUN62FZPE5LLBE","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":"2c6e78df16ce52ce850dc6c0f4db078fbf7899e1e50c1325c9f3b580544e2d49","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T10:06:55Z","title_canon_sha256":"3acfaac97508cbbb54f2f4574525c74bdd84fe83fc7443836ad7f4ff7e6f8fa6"},"schema_version":"1.0","source":{"id":"2505.11569","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11569","created_at":"2026-07-05T11:04:23Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11569v1","created_at":"2026-07-05T11:04:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11569","created_at":"2026-07-05T11:04:23Z"},{"alias_kind":"pith_short_12","alias_value":"R5U2N2MYB3RX","created_at":"2026-07-05T11:04:23Z"},{"alias_kind":"pith_short_16","alias_value":"R5U2N2MYB3RXLUN6","created_at":"2026-07-05T11:04:23Z"},{"alias_kind":"pith_short_8","alias_value":"R5U2N2MY","created_at":"2026-07-05T11:04:23Z"}],"graph_snapshots":[{"event_id":"sha256:e84ce9991bb5deffdeaa0d74137e11a26e3e036471d96f7bbdfac5f81ef4dde0","target":"graph","created_at":"2026-07-05T11:04:23Z","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/2505.11569/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deploying deep convolutional neural networks (CNNs) on resource-constrained devices presents significant challenges due to their high computational demands and rigid, static architectures. To overcome these limitations, this thesis explores methods for enabling CNNs to dynamically adjust their computational complexity based on available hardware resources. We introduce adaptive CNN architectures capable of scaling their capacity at runtime, thus efficiently balancing performance and resource utilization. To achieve this adaptability, we propose a structured pruning and dynamic re-construction ","authors_text":"Dolly Sapra, Pooja Mangal, Sudaksh Kalra","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T10:06:55Z","title":"Towards Adaptive Deep Learning: Model Elasticity via Prune-and-Grow CNN Architectures"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11569","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:d4839548fe675a4815aa2a5e8003f3326808638e4bee36055a396e2b9a880da2","target":"record","created_at":"2026-07-05T11:04:23Z","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":"2c6e78df16ce52ce850dc6c0f4db078fbf7899e1e50c1325c9f3b580544e2d49","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T10:06:55Z","title_canon_sha256":"3acfaac97508cbbb54f2f4574525c74bdd84fe83fc7443836ad7f4ff7e6f8fa6"},"schema_version":"1.0","source":{"id":"2505.11569","kind":"arxiv","version":1}},"canonical_sha256":"8f69a6e9980ee375d1bed172f2756b093f4be9a97f60924b7baad365ab943d11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f69a6e9980ee375d1bed172f2756b093f4be9a97f60924b7baad365ab943d11","first_computed_at":"2026-07-05T11:04:23.842566Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:23.842566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OUoZDR75bPKzsN3H5loxwzRhYfYfFMtd9u4a6AEOfPPmKVfOIJhReHrWxpJY9ttTCQoUN5p1A5KjekfFxv3QDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:23.843060Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11569","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4839548fe675a4815aa2a5e8003f3326808638e4bee36055a396e2b9a880da2","sha256:e84ce9991bb5deffdeaa0d74137e11a26e3e036471d96f7bbdfac5f81ef4dde0"],"state_sha256":"8efc5c78719b947aab374d04aa1dfab41008490d30f3083c42dc27f62766bdc5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cf0Sz4q0yA5+NloNAkbLP6FDYkH7lyXdYRevNXVwexMHdXNfyBnfdUkrpuTeEwbqjeXxY+OIB7wrxoySaXh/Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T07:14:19.657615Z","bundle_sha256":"bce48076953a6c26de5a5d5396938c492c5bff207df3c8aaa566a00b624ee89e"}}