{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:2RPNNBJPYAYMII6L7FKD6RPLC2","short_pith_number":"pith:2RPNNBJP","schema_version":"1.0","canonical_sha256":"d45ed6852fc030c423cbf9543f45eb16b44ea5c7f4dc03bb252ae3ac9de4450d","source":{"kind":"arxiv","id":"1706.04313","version":1},"attestation_state":"computed","paper":{"title":"Teaching Compositionality to CNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Austin Stone, Dileep George, D. Scott Phoenix, Huayan Wang, Michael Stark, Yi Liu","submitted_at":"2017-06-14T04:34:59Z","abstract_excerpt":"Convolutional neural networks (CNNs) have shown great success in computer vision, approaching human-level performance when trained for specific tasks via application-specific loss functions. In this paper, we propose a method for augmenting and training CNNs so that their learned features are compositional. It encourages networks to form representations that disentangle objects from their surroundings and from each other, thereby promoting better generalization. Our method is agnostic to the specific details of the underlying CNN to which it is applied and can in principle be used with any CNN"},"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":"1706.04313","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-14T04:34:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7522635d1a5945faa381dd1209d2961f829365857703defa85af544aceef2c05","abstract_canon_sha256":"f3cb90ded7140474de2e8eb93bc82bf7e5bff5e32625f210a63b24fa551794de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:23.018363Z","signature_b64":"AqLanpA1AAi+nDNE/Da91u9IRJDTVLPF8lBeL2ezmqEdXVbQQ781t9fIr4FopkAGANPuFG9JX3uoHTVWD1UkDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d45ed6852fc030c423cbf9543f45eb16b44ea5c7f4dc03bb252ae3ac9de4450d","last_reissued_at":"2026-05-18T00:42:23.017953Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:23.017953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Teaching Compositionality to CNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Austin Stone, Dileep George, D. Scott Phoenix, Huayan Wang, Michael Stark, Yi Liu","submitted_at":"2017-06-14T04:34:59Z","abstract_excerpt":"Convolutional neural networks (CNNs) have shown great success in computer vision, approaching human-level performance when trained for specific tasks via application-specific loss functions. In this paper, we propose a method for augmenting and training CNNs so that their learned features are compositional. It encourages networks to form representations that disentangle objects from their surroundings and from each other, thereby promoting better generalization. Our method is agnostic to the specific details of the underlying CNN to which it is applied and can in principle be used with any CNN"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.04313","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1706.04313","created_at":"2026-05-18T00:42:23.018011+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.04313v1","created_at":"2026-05-18T00:42:23.018011+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.04313","created_at":"2026-05-18T00:42:23.018011+00:00"},{"alias_kind":"pith_short_12","alias_value":"2RPNNBJPYAYM","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_16","alias_value":"2RPNNBJPYAYMII6L","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_8","alias_value":"2RPNNBJP","created_at":"2026-05-18T12:30:55.937587+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/2RPNNBJPYAYMII6L7FKD6RPLC2","json":"https://pith.science/pith/2RPNNBJPYAYMII6L7FKD6RPLC2.json","graph_json":"https://pith.science/api/pith-number/2RPNNBJPYAYMII6L7FKD6RPLC2/graph.json","events_json":"https://pith.science/api/pith-number/2RPNNBJPYAYMII6L7FKD6RPLC2/events.json","paper":"https://pith.science/paper/2RPNNBJP"},"agent_actions":{"view_html":"https://pith.science/pith/2RPNNBJPYAYMII6L7FKD6RPLC2","download_json":"https://pith.science/pith/2RPNNBJPYAYMII6L7FKD6RPLC2.json","view_paper":"https://pith.science/paper/2RPNNBJP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.04313&json=true","fetch_graph":"https://pith.science/api/pith-number/2RPNNBJPYAYMII6L7FKD6RPLC2/graph.json","fetch_events":"https://pith.science/api/pith-number/2RPNNBJPYAYMII6L7FKD6RPLC2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2RPNNBJPYAYMII6L7FKD6RPLC2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2RPNNBJPYAYMII6L7FKD6RPLC2/action/storage_attestation","attest_author":"https://pith.science/pith/2RPNNBJPYAYMII6L7FKD6RPLC2/action/author_attestation","sign_citation":"https://pith.science/pith/2RPNNBJPYAYMII6L7FKD6RPLC2/action/citation_signature","submit_replication":"https://pith.science/pith/2RPNNBJPYAYMII6L7FKD6RPLC2/action/replication_record"}},"created_at":"2026-05-18T00:42:23.018011+00:00","updated_at":"2026-05-18T00:42:23.018011+00:00"}