{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:GYJMTQMHWREDOJGVGVHWKLQQNC","short_pith_number":"pith:GYJMTQMH","canonical_record":{"source":{"id":"1506.02626","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2015-06-08T19:28:43Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"81c56c392cf92cfa4b105a13d0ae7d69a6dac5da37a8e4c461d57dd490993ff6","abstract_canon_sha256":"885621ca943528824e3ae71366f8d373619c2f91ebc3e80aaab5c0a10389a896"},"schema_version":"1.0"},"canonical_sha256":"3612c9c187b4483724d5354f652e10689f25fe86db76bbbe58918a81e058b8d5","source":{"kind":"arxiv","id":"1506.02626","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.02626","created_at":"2026-05-18T01:28:14Z"},{"alias_kind":"arxiv_version","alias_value":"1506.02626v3","created_at":"2026-05-18T01:28:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.02626","created_at":"2026-05-18T01:28:14Z"},{"alias_kind":"pith_short_12","alias_value":"GYJMTQMHWRED","created_at":"2026-05-18T12:29:22Z"},{"alias_kind":"pith_short_16","alias_value":"GYJMTQMHWREDOJGV","created_at":"2026-05-18T12:29:22Z"},{"alias_kind":"pith_short_8","alias_value":"GYJMTQMH","created_at":"2026-05-18T12:29:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:GYJMTQMHWREDOJGVGVHWKLQQNC","target":"record","payload":{"canonical_record":{"source":{"id":"1506.02626","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2015-06-08T19:28:43Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"81c56c392cf92cfa4b105a13d0ae7d69a6dac5da37a8e4c461d57dd490993ff6","abstract_canon_sha256":"885621ca943528824e3ae71366f8d373619c2f91ebc3e80aaab5c0a10389a896"},"schema_version":"1.0"},"canonical_sha256":"3612c9c187b4483724d5354f652e10689f25fe86db76bbbe58918a81e058b8d5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:28:14.125365Z","signature_b64":"teVqvG7HGcMP4QFsVy/oGhJDelgj8JiNiOEVnMz/u/F5Gax9gCCl0TAcWHkaDmiFN6723xmSATqLSlClfcJJBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3612c9c187b4483724d5354f652e10689f25fe86db76bbbe58918a81e058b8d5","last_reissued_at":"2026-05-18T01:28:14.124657Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:28:14.124657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1506.02626","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:28:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N/kUpF8KTzpZuHNEzXHXz0YV1shrjnd8pD5qPwk8XYoDaKQMKKh0EYgoKyowKLlfxZyz2ATgmh1BXNHP7G9PBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T18:22:22.135772Z"},"content_sha256":"aed01fad339df6aec38914736a95430dfbe898d75f06bd1abddf5a0851f37ddb","schema_version":"1.0","event_id":"sha256:aed01fad339df6aec38914736a95430dfbe898d75f06bd1abddf5a0851f37ddb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:GYJMTQMHWREDOJGVGVHWKLQQNC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning both Weights and Connections for Efficient Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.NE","authors_text":"Jeff Pool, John Tran, Song Han, William J. Dally","submitted_at":"2015-06-08T19:28:43Z","abstract_excerpt":"Neural networks are both computationally intensive and memory intensive, making them difficult to deploy on embedded systems. Also, conventional networks fix the architecture before training starts; as a result, training cannot improve the architecture. To address these limitations, we describe a method to reduce the storage and computation required by neural networks by an order of magnitude without affecting their accuracy by learning only the important connections. Our method prunes redundant connections using a three-step method. First, we train the network to learn which connections are i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.02626","kind":"arxiv","version":3},"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":"2026-05-18T01:28:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+biaqSOGYgN8k1KUUx8iPW51NnlpjFODG96sRvpIZC968kAzhcgKtpstOi9h11THnNkqTdvA5370QCXQVoK1BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T18:22:22.136540Z"},"content_sha256":"687a691aa8bbf1695d766dc377e4fc1f1a0ed20875325cc487beb3d6d63238c5","schema_version":"1.0","event_id":"sha256:687a691aa8bbf1695d766dc377e4fc1f1a0ed20875325cc487beb3d6d63238c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GYJMTQMHWREDOJGVGVHWKLQQNC/bundle.json","state_url":"https://pith.science/pith/GYJMTQMHWREDOJGVGVHWKLQQNC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GYJMTQMHWREDOJGVGVHWKLQQNC/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":"2026-05-30T18:22:22Z","links":{"resolver":"https://pith.science/pith/GYJMTQMHWREDOJGVGVHWKLQQNC","bundle":"https://pith.science/pith/GYJMTQMHWREDOJGVGVHWKLQQNC/bundle.json","state":"https://pith.science/pith/GYJMTQMHWREDOJGVGVHWKLQQNC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GYJMTQMHWREDOJGVGVHWKLQQNC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:GYJMTQMHWREDOJGVGVHWKLQQNC","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":"885621ca943528824e3ae71366f8d373619c2f91ebc3e80aaab5c0a10389a896","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2015-06-08T19:28:43Z","title_canon_sha256":"81c56c392cf92cfa4b105a13d0ae7d69a6dac5da37a8e4c461d57dd490993ff6"},"schema_version":"1.0","source":{"id":"1506.02626","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.02626","created_at":"2026-05-18T01:28:14Z"},{"alias_kind":"arxiv_version","alias_value":"1506.02626v3","created_at":"2026-05-18T01:28:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.02626","created_at":"2026-05-18T01:28:14Z"},{"alias_kind":"pith_short_12","alias_value":"GYJMTQMHWRED","created_at":"2026-05-18T12:29:22Z"},{"alias_kind":"pith_short_16","alias_value":"GYJMTQMHWREDOJGV","created_at":"2026-05-18T12:29:22Z"},{"alias_kind":"pith_short_8","alias_value":"GYJMTQMH","created_at":"2026-05-18T12:29:22Z"}],"graph_snapshots":[{"event_id":"sha256:687a691aa8bbf1695d766dc377e4fc1f1a0ed20875325cc487beb3d6d63238c5","target":"graph","created_at":"2026-05-18T01:28:14Z","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":"Neural networks are both computationally intensive and memory intensive, making them difficult to deploy on embedded systems. Also, conventional networks fix the architecture before training starts; as a result, training cannot improve the architecture. To address these limitations, we describe a method to reduce the storage and computation required by neural networks by an order of magnitude without affecting their accuracy by learning only the important connections. Our method prunes redundant connections using a three-step method. First, we train the network to learn which connections are i","authors_text":"Jeff Pool, John Tran, Song Han, William J. Dally","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2015-06-08T19:28:43Z","title":"Learning both Weights and Connections for Efficient Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.02626","kind":"arxiv","version":3},"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:aed01fad339df6aec38914736a95430dfbe898d75f06bd1abddf5a0851f37ddb","target":"record","created_at":"2026-05-18T01:28:14Z","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":"885621ca943528824e3ae71366f8d373619c2f91ebc3e80aaab5c0a10389a896","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2015-06-08T19:28:43Z","title_canon_sha256":"81c56c392cf92cfa4b105a13d0ae7d69a6dac5da37a8e4c461d57dd490993ff6"},"schema_version":"1.0","source":{"id":"1506.02626","kind":"arxiv","version":3}},"canonical_sha256":"3612c9c187b4483724d5354f652e10689f25fe86db76bbbe58918a81e058b8d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3612c9c187b4483724d5354f652e10689f25fe86db76bbbe58918a81e058b8d5","first_computed_at":"2026-05-18T01:28:14.124657Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:28:14.124657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"teVqvG7HGcMP4QFsVy/oGhJDelgj8JiNiOEVnMz/u/F5Gax9gCCl0TAcWHkaDmiFN6723xmSATqLSlClfcJJBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:28:14.125365Z","signed_message":"canonical_sha256_bytes"},"source_id":"1506.02626","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aed01fad339df6aec38914736a95430dfbe898d75f06bd1abddf5a0851f37ddb","sha256:687a691aa8bbf1695d766dc377e4fc1f1a0ed20875325cc487beb3d6d63238c5"],"state_sha256":"2a6324e8ea4059af5551bb6fa7abaf247475475c45519f5d1a469bd3afd58e73"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8z+ieprGxfrEb6FGnBf71xhsfsLhNmeUk8UZKau/FRgDu9NTkN65gmj5UQ7yRByYDJHAstaKjO5I/hN+9nNrAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T18:22:22.140613Z","bundle_sha256":"9dff4e1ef02a11e63a37422671067dc21c908c4d828452eef8dc2190db011d0c"}}