{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:NJGT5Z5ZATKXNHRZ7SVSCFC53N","short_pith_number":"pith:NJGT5Z5Z","canonical_record":{"source":{"id":"2007.14917","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-29T15:43:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d38bf9634c2caea0ecc3c07123ffb070c526a3f65a2e6f9dbd6aacb994bd7b27","abstract_canon_sha256":"904b52726f718389f818ec90ba49de3ba85d83063831b3f3d47ca61a5729d360"},"schema_version":"1.0"},"canonical_sha256":"6a4d3ee7b904d5769e39fcab21145ddb41ff01a5169a44c70654a9363004c8ae","source":{"kind":"arxiv","id":"2007.14917","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.14917","created_at":"2026-07-05T01:23:20Z"},{"alias_kind":"arxiv_version","alias_value":"2007.14917v1","created_at":"2026-07-05T01:23:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.14917","created_at":"2026-07-05T01:23:20Z"},{"alias_kind":"pith_short_12","alias_value":"NJGT5Z5ZATKX","created_at":"2026-07-05T01:23:20Z"},{"alias_kind":"pith_short_16","alias_value":"NJGT5Z5ZATKXNHRZ","created_at":"2026-07-05T01:23:20Z"},{"alias_kind":"pith_short_8","alias_value":"NJGT5Z5Z","created_at":"2026-07-05T01:23:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:NJGT5Z5ZATKXNHRZ7SVSCFC53N","target":"record","payload":{"canonical_record":{"source":{"id":"2007.14917","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-29T15:43:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d38bf9634c2caea0ecc3c07123ffb070c526a3f65a2e6f9dbd6aacb994bd7b27","abstract_canon_sha256":"904b52726f718389f818ec90ba49de3ba85d83063831b3f3d47ca61a5729d360"},"schema_version":"1.0"},"canonical_sha256":"6a4d3ee7b904d5769e39fcab21145ddb41ff01a5169a44c70654a9363004c8ae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:23:20.241752Z","signature_b64":"8RE0I5vaG8VJIc41k65q2n/8oRuanw88AMz9DIB7rbrWiPOFwrVieti7rsYxsglfU/DxzKHvhRXfc4fyYmWLDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a4d3ee7b904d5769e39fcab21145ddb41ff01a5169a44c70654a9363004c8ae","last_reissued_at":"2026-07-05T01:23:20.241403Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:23:20.241403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.14917","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":"2026-07-05T01:23:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vIJWYdENM11bFWXe7HNqKY5H4r7eqvAIorghWIuxcDPw5i1tlW2vTrBa6d4Ku5/exGy+wo01vydw7bjHTvJmAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:45:25.906720Z"},"content_sha256":"2c8e54404c2086d171388d574f82612f662a5cafeb648a33d1041289a76506f5","schema_version":"1.0","event_id":"sha256:2c8e54404c2086d171388d574f82612f662a5cafeb648a33d1041289a76506f5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:NJGT5Z5ZATKXNHRZ7SVSCFC53N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Compressing Deep Neural Networks via Layer Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aram Galstyan, Greg Ver Steeg, James O' Neill","submitted_at":"2020-07-29T15:43:19Z","abstract_excerpt":"This paper proposes \\textit{layer fusion} - a model compression technique that discovers which weights to combine and then fuses weights of similar fully-connected, convolutional and attention layers. Layer fusion can significantly reduce the number of layers of the original network with little additional computation overhead, while maintaining competitive performance. From experiments on CIFAR-10, we find that various deep convolution neural networks can remain within 2\\% accuracy points of the original networks up to a compression ratio of 3.33 when iteratively retrained with layer fusion. F"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.14917","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/2007.14917/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":"2026-07-05T01:23:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ysp9F+rEEXob2CMwtzCZaOMGYCl69DgfOt0irQ9ZjfSdKUxvxtMRbN9Q2+NhvAIUEQQHJrYomHJyrfC1KV+FAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:45:25.907585Z"},"content_sha256":"1fee402176c50cd9d4dc1733867be0e6cfec4ecdf76185826a7792bba85acdfc","schema_version":"1.0","event_id":"sha256:1fee402176c50cd9d4dc1733867be0e6cfec4ecdf76185826a7792bba85acdfc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NJGT5Z5ZATKXNHRZ7SVSCFC53N/bundle.json","state_url":"https://pith.science/pith/NJGT5Z5ZATKXNHRZ7SVSCFC53N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NJGT5Z5ZATKXNHRZ7SVSCFC53N/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":"2026-08-04T07:45:25Z","links":{"resolver":"https://pith.science/pith/NJGT5Z5ZATKXNHRZ7SVSCFC53N","bundle":"https://pith.science/pith/NJGT5Z5ZATKXNHRZ7SVSCFC53N/bundle.json","state":"https://pith.science/pith/NJGT5Z5ZATKXNHRZ7SVSCFC53N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NJGT5Z5ZATKXNHRZ7SVSCFC53N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:NJGT5Z5ZATKXNHRZ7SVSCFC53N","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":"904b52726f718389f818ec90ba49de3ba85d83063831b3f3d47ca61a5729d360","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-29T15:43:19Z","title_canon_sha256":"d38bf9634c2caea0ecc3c07123ffb070c526a3f65a2e6f9dbd6aacb994bd7b27"},"schema_version":"1.0","source":{"id":"2007.14917","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.14917","created_at":"2026-07-05T01:23:20Z"},{"alias_kind":"arxiv_version","alias_value":"2007.14917v1","created_at":"2026-07-05T01:23:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.14917","created_at":"2026-07-05T01:23:20Z"},{"alias_kind":"pith_short_12","alias_value":"NJGT5Z5ZATKX","created_at":"2026-07-05T01:23:20Z"},{"alias_kind":"pith_short_16","alias_value":"NJGT5Z5ZATKXNHRZ","created_at":"2026-07-05T01:23:20Z"},{"alias_kind":"pith_short_8","alias_value":"NJGT5Z5Z","created_at":"2026-07-05T01:23:20Z"}],"graph_snapshots":[{"event_id":"sha256:1fee402176c50cd9d4dc1733867be0e6cfec4ecdf76185826a7792bba85acdfc","target":"graph","created_at":"2026-07-05T01:23:20Z","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/2007.14917/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes \\textit{layer fusion} - a model compression technique that discovers which weights to combine and then fuses weights of similar fully-connected, convolutional and attention layers. Layer fusion can significantly reduce the number of layers of the original network with little additional computation overhead, while maintaining competitive performance. From experiments on CIFAR-10, we find that various deep convolution neural networks can remain within 2\\% accuracy points of the original networks up to a compression ratio of 3.33 when iteratively retrained with layer fusion. F","authors_text":"Aram Galstyan, Greg Ver Steeg, James O' Neill","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-29T15:43:19Z","title":"Compressing Deep Neural Networks via Layer Fusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.14917","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":"sha256:2c8e54404c2086d171388d574f82612f662a5cafeb648a33d1041289a76506f5","target":"record","created_at":"2026-07-05T01:23:20Z","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":"904b52726f718389f818ec90ba49de3ba85d83063831b3f3d47ca61a5729d360","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-29T15:43:19Z","title_canon_sha256":"d38bf9634c2caea0ecc3c07123ffb070c526a3f65a2e6f9dbd6aacb994bd7b27"},"schema_version":"1.0","source":{"id":"2007.14917","kind":"arxiv","version":1}},"canonical_sha256":"6a4d3ee7b904d5769e39fcab21145ddb41ff01a5169a44c70654a9363004c8ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a4d3ee7b904d5769e39fcab21145ddb41ff01a5169a44c70654a9363004c8ae","first_computed_at":"2026-07-05T01:23:20.241403Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:23:20.241403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8RE0I5vaG8VJIc41k65q2n/8oRuanw88AMz9DIB7rbrWiPOFwrVieti7rsYxsglfU/DxzKHvhRXfc4fyYmWLDg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:23:20.241752Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.14917","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c8e54404c2086d171388d574f82612f662a5cafeb648a33d1041289a76506f5","sha256:1fee402176c50cd9d4dc1733867be0e6cfec4ecdf76185826a7792bba85acdfc"],"state_sha256":"2f5436cb6207bfb7ce73f9470f089567d5b19d07edf8b9fc9a70ead2e2e0be04"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gSGJXSu1WEQH7zApdzkJbw+740dIprfgcniLXOaLXtZb5iATjJKLlhaTu+gJd+xYE1K0Vgp/wh20siFt0SexDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T07:45:25.942326Z","bundle_sha256":"9e54e7fee88b64f7345746507ee114e3a4cdf77be54293f74fbae4e88b5179a4"}}