{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:H3SJ66UWTTGKKTOEXDBWNHHXV3","short_pith_number":"pith:H3SJ66UW","schema_version":"1.0","canonical_sha256":"3ee49f7a969ccca54dc4b8c3669cf7aec958a6bedc2c61b6ab2e0588939d6f20","source":{"kind":"arxiv","id":"1511.07356","version":2},"attestation_state":"computed","paper":{"title":"Recombinator Networks: Learning Coarse-to-Fine Feature Aggregation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christopher Pal, Jason Yosinski, Pascal Vincent, Sina Honari","submitted_at":"2015-11-23T18:42:36Z","abstract_excerpt":"Deep neural networks with alternating convolutional, max-pooling and decimation layers are widely used in state of the art architectures for computer vision. Max-pooling purposefully discards precise spatial information in order to create features that are more robust, and typically organized as lower resolution spatial feature maps. On some tasks, such as whole-image classification, max-pooling derived features are well suited; however, for tasks requiring precise localization, such as pixel level prediction and segmentation, max-pooling destroys exactly the information required to perform we"},"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":"1511.07356","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-23T18:42:36Z","cross_cats_sorted":[],"title_canon_sha256":"aff481eb90dc170266c4e0e2b81ea20be834757e39f898b29b767f8beeb264f4","abstract_canon_sha256":"682d56a32eec3176b2cfa7ab88cd0117bdca77b29856b6a9cc914725251b7660"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:16:59.955701Z","signature_b64":"hul8C1dEn4w7wR1M4kai3SNG8uRVFNZ6tn+mTneCRQwwxTW0vx7Gjv9ouSw3oh2FaGkrWepUhSpc8Yv88BprCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ee49f7a969ccca54dc4b8c3669cf7aec958a6bedc2c61b6ab2e0588939d6f20","last_reissued_at":"2026-05-18T01:16:59.954993Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:16:59.954993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recombinator Networks: Learning Coarse-to-Fine Feature Aggregation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christopher Pal, Jason Yosinski, Pascal Vincent, Sina Honari","submitted_at":"2015-11-23T18:42:36Z","abstract_excerpt":"Deep neural networks with alternating convolutional, max-pooling and decimation layers are widely used in state of the art architectures for computer vision. Max-pooling purposefully discards precise spatial information in order to create features that are more robust, and typically organized as lower resolution spatial feature maps. On some tasks, such as whole-image classification, max-pooling derived features are well suited; however, for tasks requiring precise localization, such as pixel level prediction and segmentation, max-pooling destroys exactly the information required to perform we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.07356","kind":"arxiv","version":2},"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":"1511.07356","created_at":"2026-05-18T01:16:59.955112+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.07356v2","created_at":"2026-05-18T01:16:59.955112+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.07356","created_at":"2026-05-18T01:16:59.955112+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3SJ66UWTTGK","created_at":"2026-05-18T12:29:22.688609+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3SJ66UWTTGKKTOE","created_at":"2026-05-18T12:29:22.688609+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3SJ66UW","created_at":"2026-05-18T12:29:22.688609+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/H3SJ66UWTTGKKTOEXDBWNHHXV3","json":"https://pith.science/pith/H3SJ66UWTTGKKTOEXDBWNHHXV3.json","graph_json":"https://pith.science/api/pith-number/H3SJ66UWTTGKKTOEXDBWNHHXV3/graph.json","events_json":"https://pith.science/api/pith-number/H3SJ66UWTTGKKTOEXDBWNHHXV3/events.json","paper":"https://pith.science/paper/H3SJ66UW"},"agent_actions":{"view_html":"https://pith.science/pith/H3SJ66UWTTGKKTOEXDBWNHHXV3","download_json":"https://pith.science/pith/H3SJ66UWTTGKKTOEXDBWNHHXV3.json","view_paper":"https://pith.science/paper/H3SJ66UW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.07356&json=true","fetch_graph":"https://pith.science/api/pith-number/H3SJ66UWTTGKKTOEXDBWNHHXV3/graph.json","fetch_events":"https://pith.science/api/pith-number/H3SJ66UWTTGKKTOEXDBWNHHXV3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3SJ66UWTTGKKTOEXDBWNHHXV3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3SJ66UWTTGKKTOEXDBWNHHXV3/action/storage_attestation","attest_author":"https://pith.science/pith/H3SJ66UWTTGKKTOEXDBWNHHXV3/action/author_attestation","sign_citation":"https://pith.science/pith/H3SJ66UWTTGKKTOEXDBWNHHXV3/action/citation_signature","submit_replication":"https://pith.science/pith/H3SJ66UWTTGKKTOEXDBWNHHXV3/action/replication_record"}},"created_at":"2026-05-18T01:16:59.955112+00:00","updated_at":"2026-05-18T01:16:59.955112+00:00"}