{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:YXQ47Y6O226WOAH67KGGVROPY3","short_pith_number":"pith:YXQ47Y6O","schema_version":"1.0","canonical_sha256":"c5e1cfe3ced6bd6700fefa8c6ac5cfc6d9861d730eea00d06699ab1c55c8665e","source":{"kind":"arxiv","id":"1602.03001","version":2},"attestation_state":"computed","paper":{"title":"A Convolutional Attention Network for Extreme Summarization of Source Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SE"],"primary_cat":"cs.LG","authors_text":"Charles Sutton, Hao Peng, Miltiadis Allamanis","submitted_at":"2016-02-09T14:36:49Z","abstract_excerpt":"Attention mechanisms in neural networks have proved useful for problems in which the input and output do not have fixed dimension. Often there exist features that are locally translation invariant and would be valuable for directing the model's attention, but previous attentional architectures are not constructed to learn such features specifically. We introduce an attentional neural network that employs convolution on the input tokens to detect local time-invariant and long-range topical attention features in a context-dependent way. We apply this architecture to the problem of extreme summar"},"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":"1602.03001","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-09T14:36:49Z","cross_cats_sorted":["cs.CL","cs.SE"],"title_canon_sha256":"2a2defa09434a2eecc6c627fbc0164844039f94c8f52137dfa944c25ec40896c","abstract_canon_sha256":"d65571735355b20a614974683ad511de026cd4a26d58f645b2cf1bd2918830f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:13:39.784698Z","signature_b64":"E2u6o4ke9Z/01cqVG9qIRsZHwzBMjOMTGXAwMICv9SbKP59+adm6aNNtLB6zr12F6Oc1TsLACeLRyN/WiDxTCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5e1cfe3ced6bd6700fefa8c6ac5cfc6d9861d730eea00d06699ab1c55c8665e","last_reissued_at":"2026-05-18T01:13:39.784022Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:13:39.784022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Convolutional Attention Network for Extreme Summarization of Source Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SE"],"primary_cat":"cs.LG","authors_text":"Charles Sutton, Hao Peng, Miltiadis Allamanis","submitted_at":"2016-02-09T14:36:49Z","abstract_excerpt":"Attention mechanisms in neural networks have proved useful for problems in which the input and output do not have fixed dimension. Often there exist features that are locally translation invariant and would be valuable for directing the model's attention, but previous attentional architectures are not constructed to learn such features specifically. We introduce an attentional neural network that employs convolution on the input tokens to detect local time-invariant and long-range topical attention features in a context-dependent way. We apply this architecture to the problem of extreme summar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.03001","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":"1602.03001","created_at":"2026-05-18T01:13:39.784103+00:00"},{"alias_kind":"arxiv_version","alias_value":"1602.03001v2","created_at":"2026-05-18T01:13:39.784103+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.03001","created_at":"2026-05-18T01:13:39.784103+00:00"},{"alias_kind":"pith_short_12","alias_value":"YXQ47Y6O226W","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_16","alias_value":"YXQ47Y6O226WOAH6","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_8","alias_value":"YXQ47Y6O","created_at":"2026-05-18T12:30:53.716459+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.26523","citing_title":"RepoDoc: A Knowledge Graph-Based Framework to Automatic Documentation Generation and Incremental Updates","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YXQ47Y6O226WOAH67KGGVROPY3","json":"https://pith.science/pith/YXQ47Y6O226WOAH67KGGVROPY3.json","graph_json":"https://pith.science/api/pith-number/YXQ47Y6O226WOAH67KGGVROPY3/graph.json","events_json":"https://pith.science/api/pith-number/YXQ47Y6O226WOAH67KGGVROPY3/events.json","paper":"https://pith.science/paper/YXQ47Y6O"},"agent_actions":{"view_html":"https://pith.science/pith/YXQ47Y6O226WOAH67KGGVROPY3","download_json":"https://pith.science/pith/YXQ47Y6O226WOAH67KGGVROPY3.json","view_paper":"https://pith.science/paper/YXQ47Y6O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1602.03001&json=true","fetch_graph":"https://pith.science/api/pith-number/YXQ47Y6O226WOAH67KGGVROPY3/graph.json","fetch_events":"https://pith.science/api/pith-number/YXQ47Y6O226WOAH67KGGVROPY3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YXQ47Y6O226WOAH67KGGVROPY3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YXQ47Y6O226WOAH67KGGVROPY3/action/storage_attestation","attest_author":"https://pith.science/pith/YXQ47Y6O226WOAH67KGGVROPY3/action/author_attestation","sign_citation":"https://pith.science/pith/YXQ47Y6O226WOAH67KGGVROPY3/action/citation_signature","submit_replication":"https://pith.science/pith/YXQ47Y6O226WOAH67KGGVROPY3/action/replication_record"}},"created_at":"2026-05-18T01:13:39.784103+00:00","updated_at":"2026-05-18T01:13:39.784103+00:00"}