{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:EPY4VOHZ6SIB44UK7BCSA5U5QR","short_pith_number":"pith:EPY4VOHZ","canonical_record":{"source":{"id":"1807.09810","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-25T18:26:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e0e63349c977c732539d36d56cb9adb75f910efd8b3d166acc040d4b515ab286","abstract_canon_sha256":"db4bdc8dad5c756200232e9c7147f51c6328e90215381b541e780707d499c08a"},"schema_version":"1.0"},"canonical_sha256":"23f1cab8f9f4901e728af84520769d844181ae4b7347302d8e31fa44b27d5dfe","source":{"kind":"arxiv","id":"1807.09810","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.09810","created_at":"2026-05-18T00:09:46Z"},{"alias_kind":"arxiv_version","alias_value":"1807.09810v1","created_at":"2026-05-18T00:09:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.09810","created_at":"2026-05-18T00:09:46Z"},{"alias_kind":"pith_short_12","alias_value":"EPY4VOHZ6SIB","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EPY4VOHZ6SIB44UK","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EPY4VOHZ","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:EPY4VOHZ6SIB44UK7BCSA5U5QR","target":"record","payload":{"canonical_record":{"source":{"id":"1807.09810","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-25T18:26:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e0e63349c977c732539d36d56cb9adb75f910efd8b3d166acc040d4b515ab286","abstract_canon_sha256":"db4bdc8dad5c756200232e9c7147f51c6328e90215381b541e780707d499c08a"},"schema_version":"1.0"},"canonical_sha256":"23f1cab8f9f4901e728af84520769d844181ae4b7347302d8e31fa44b27d5dfe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:46.556995Z","signature_b64":"oOnEfKK+n8LsAkrebTpWl2dCOOz+bfl4DNcQL4FZRJyj8vYNPWyjfugsPVuZBh6Q8wrcizmrIWdlHo0YquvOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23f1cab8f9f4901e728af84520769d844181ae4b7347302d8e31fa44b27d5dfe","last_reissued_at":"2026-05-18T00:09:46.556271Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:46.556271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.09810","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":"2026-05-18T00:09:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TbC8M2wpmejiHVe4tSu/dbjjqH+pv0U31XlmIKiTHQXBrKqF4Qxb2si3drqiI0nbd3g0V3sTH/RDtxSkbTOvAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T10:01:29.166382Z"},"content_sha256":"f5b5c94cf17ddf6efe2c8859b708e486cec2fc865bcc53cfea668dae6679bf45","schema_version":"1.0","event_id":"sha256:f5b5c94cf17ddf6efe2c8859b708e486cec2fc865bcc53cfea668dae6679bf45"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:EPY4VOHZ6SIB44UK7BCSA5U5QR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Coreset-Based Neural Network Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhimanyu Dubey, Moitreya Chatterjee, Narendra Ahuja","submitted_at":"2018-07-25T18:26:49Z","abstract_excerpt":"We propose a novel Convolutional Neural Network (CNN) compression algorithm based on coreset representations of filters. We exploit the redundancies extant in the space of CNN weights and neuronal activations (across samples) in order to obtain compression. Our method requires no retraining, is easy to implement, and obtains state-of-the-art compression performance across a wide variety of CNN architectures. Coupled with quantization and Huffman coding, we create networks that provide AlexNet-like accuracy, with a memory footprint that is $832\\times$ smaller than the original AlexNet, while al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.09810","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":""},"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":"2026-05-18T00:09:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IkoJRX6paowUkuH9jMSwkUCR8pB18E0CTXgMkRWTCBAgur2QASLSsevl/hpqsu2BNdwfCf/qUvuCBaHtdHVtDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T10:01:29.166729Z"},"content_sha256":"fa2814ce8da919c4e0d5e317f14d8826f2ad162ed7148fd2048fcd5f50a7bfee","schema_version":"1.0","event_id":"sha256:fa2814ce8da919c4e0d5e317f14d8826f2ad162ed7148fd2048fcd5f50a7bfee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EPY4VOHZ6SIB44UK7BCSA5U5QR/bundle.json","state_url":"https://pith.science/pith/EPY4VOHZ6SIB44UK7BCSA5U5QR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EPY4VOHZ6SIB44UK7BCSA5U5QR/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":"2026-06-04T10:01:29Z","links":{"resolver":"https://pith.science/pith/EPY4VOHZ6SIB44UK7BCSA5U5QR","bundle":"https://pith.science/pith/EPY4VOHZ6SIB44UK7BCSA5U5QR/bundle.json","state":"https://pith.science/pith/EPY4VOHZ6SIB44UK7BCSA5U5QR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EPY4VOHZ6SIB44UK7BCSA5U5QR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:EPY4VOHZ6SIB44UK7BCSA5U5QR","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":"db4bdc8dad5c756200232e9c7147f51c6328e90215381b541e780707d499c08a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-25T18:26:49Z","title_canon_sha256":"e0e63349c977c732539d36d56cb9adb75f910efd8b3d166acc040d4b515ab286"},"schema_version":"1.0","source":{"id":"1807.09810","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.09810","created_at":"2026-05-18T00:09:46Z"},{"alias_kind":"arxiv_version","alias_value":"1807.09810v1","created_at":"2026-05-18T00:09:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.09810","created_at":"2026-05-18T00:09:46Z"},{"alias_kind":"pith_short_12","alias_value":"EPY4VOHZ6SIB","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EPY4VOHZ6SIB44UK","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EPY4VOHZ","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:fa2814ce8da919c4e0d5e317f14d8826f2ad162ed7148fd2048fcd5f50a7bfee","target":"graph","created_at":"2026-05-18T00:09:46Z","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"},"paper":{"abstract_excerpt":"We propose a novel Convolutional Neural Network (CNN) compression algorithm based on coreset representations of filters. We exploit the redundancies extant in the space of CNN weights and neuronal activations (across samples) in order to obtain compression. Our method requires no retraining, is easy to implement, and obtains state-of-the-art compression performance across a wide variety of CNN architectures. Coupled with quantization and Huffman coding, we create networks that provide AlexNet-like accuracy, with a memory footprint that is $832\\times$ smaller than the original AlexNet, while al","authors_text":"Abhimanyu Dubey, Moitreya Chatterjee, Narendra Ahuja","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-25T18:26:49Z","title":"Coreset-Based Neural Network Compression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.09810","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:f5b5c94cf17ddf6efe2c8859b708e486cec2fc865bcc53cfea668dae6679bf45","target":"record","created_at":"2026-05-18T00:09:46Z","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":"db4bdc8dad5c756200232e9c7147f51c6328e90215381b541e780707d499c08a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-25T18:26:49Z","title_canon_sha256":"e0e63349c977c732539d36d56cb9adb75f910efd8b3d166acc040d4b515ab286"},"schema_version":"1.0","source":{"id":"1807.09810","kind":"arxiv","version":1}},"canonical_sha256":"23f1cab8f9f4901e728af84520769d844181ae4b7347302d8e31fa44b27d5dfe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23f1cab8f9f4901e728af84520769d844181ae4b7347302d8e31fa44b27d5dfe","first_computed_at":"2026-05-18T00:09:46.556271Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:09:46.556271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oOnEfKK+n8LsAkrebTpWl2dCOOz+bfl4DNcQL4FZRJyj8vYNPWyjfugsPVuZBh6Q8wrcizmrIWdlHo0YquvOCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:09:46.556995Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.09810","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5b5c94cf17ddf6efe2c8859b708e486cec2fc865bcc53cfea668dae6679bf45","sha256:fa2814ce8da919c4e0d5e317f14d8826f2ad162ed7148fd2048fcd5f50a7bfee"],"state_sha256":"140331b7720d08da087fd2b9cccbc588b64cf68d57f9f3bc0a929d0d0c237001"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ol88U0BDHnKfdZqLkZaTmmObp8hvYPyVo9Xq0aFGuVFWS9LJ+kP1TdtWlL+lzduzwKbCitQBFYHhox8X2zjqCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T10:01:29.168794Z","bundle_sha256":"17672941639b742457adae794e6c46638842111cb1d5c9605d0fb0fd8064c331"}}