{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:Q4E46TI45GN46IJHUQVTN72REQ","short_pith_number":"pith:Q4E46TI4","schema_version":"1.0","canonical_sha256":"8709cf4d1ce99bcf2127a42b36ff5124212b499f89c358217a284d33388b1555","source":{"kind":"arxiv","id":"1606.05262","version":3},"attestation_state":"computed","paper":{"title":"Convolutional Residual Memory Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christopher Pal, Joel Moniz","submitted_at":"2016-06-16T16:54:39Z","abstract_excerpt":"Very deep convolutional neural networks (CNNs) yield state of the art results on a wide variety of visual recognition problems. A number of state of the the art methods for image recognition are based on networks with well over 100 layers and the performance vs. depth trend is moving towards networks in excess of 1000 layers. In such extremely deep architectures the vanishing or exploding gradient problem becomes a key issue. Recent evidence also indicates that convolutional networks could benefit from an interface to explicitly constructed memory mechanisms interacting with a CNN feature proc"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1606.05262","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-16T16:54:39Z","cross_cats_sorted":[],"title_canon_sha256":"f3251314cf64e939eec2b48ebced07d3c262db279bc7bebe8210d5f5cd36f116","abstract_canon_sha256":"70edae097de6d11753189a2985d249f8347a6c513f5e0dbcdcc69a78b993e7ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:11:04.636949Z","signature_b64":"t4AQ4UOYL/WeacnhTJTFZfT2hl8Wfv8VQ9cyKY+N9y2zQWkZCCW2U4oc2WjKoeNFrC26r4K3nSClnxqEqyt1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8709cf4d1ce99bcf2127a42b36ff5124212b499f89c358217a284d33388b1555","last_reissued_at":"2026-05-18T01:11:04.636564Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:11:04.636564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convolutional Residual Memory Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christopher Pal, Joel Moniz","submitted_at":"2016-06-16T16:54:39Z","abstract_excerpt":"Very deep convolutional neural networks (CNNs) yield state of the art results on a wide variety of visual recognition problems. A number of state of the the art methods for image recognition are based on networks with well over 100 layers and the performance vs. depth trend is moving towards networks in excess of 1000 layers. In such extremely deep architectures the vanishing or exploding gradient problem becomes a key issue. Recent evidence also indicates that convolutional networks could benefit from an interface to explicitly constructed memory mechanisms interacting with a CNN feature proc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.05262","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1606.05262","created_at":"2026-05-18T01:11:04.636630+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.05262v3","created_at":"2026-05-18T01:11:04.636630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.05262","created_at":"2026-05-18T01:11:04.636630+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q4E46TI45GN4","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q4E46TI45GN46IJH","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q4E46TI4","created_at":"2026-05-18T12:30:39.010887+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q4E46TI45GN46IJHUQVTN72REQ","json":"https://pith.science/pith/Q4E46TI45GN46IJHUQVTN72REQ.json","graph_json":"https://pith.science/api/pith-number/Q4E46TI45GN46IJHUQVTN72REQ/graph.json","events_json":"https://pith.science/api/pith-number/Q4E46TI45GN46IJHUQVTN72REQ/events.json","paper":"https://pith.science/paper/Q4E46TI4"},"agent_actions":{"view_html":"https://pith.science/pith/Q4E46TI45GN46IJHUQVTN72REQ","download_json":"https://pith.science/pith/Q4E46TI45GN46IJHUQVTN72REQ.json","view_paper":"https://pith.science/paper/Q4E46TI4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.05262&json=true","fetch_graph":"https://pith.science/api/pith-number/Q4E46TI45GN46IJHUQVTN72REQ/graph.json","fetch_events":"https://pith.science/api/pith-number/Q4E46TI45GN46IJHUQVTN72REQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q4E46TI45GN46IJHUQVTN72REQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q4E46TI45GN46IJHUQVTN72REQ/action/storage_attestation","attest_author":"https://pith.science/pith/Q4E46TI45GN46IJHUQVTN72REQ/action/author_attestation","sign_citation":"https://pith.science/pith/Q4E46TI45GN46IJHUQVTN72REQ/action/citation_signature","submit_replication":"https://pith.science/pith/Q4E46TI45GN46IJHUQVTN72REQ/action/replication_record"}},"created_at":"2026-05-18T01:11:04.636630+00:00","updated_at":"2026-05-18T01:11:04.636630+00:00"}