{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TLTFCKSU7DIAT2NMKC6CUKN7OM","short_pith_number":"pith:TLTFCKSU","schema_version":"1.0","canonical_sha256":"9ae6512a54f8d009e9ac50bc2a29bf733f170776935a417105e94c26bd7dcf41","source":{"kind":"arxiv","id":"1902.01780","version":3},"attestation_state":"computed","paper":{"title":"Learning Decision Trees Recurrently Through Communication","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bernt Schiele, Diego Marcos, Stephan Alaniz, Zeynep Akata","submitted_at":"2019-02-05T16:40:34Z","abstract_excerpt":"Integrated interpretability without sacrificing the prediction accuracy of decision making algorithms has the potential of greatly improving their value to the user. Instead of assigning a label to an image directly, we propose to learn iterative binary sub-decisions, inducing sparsity and transparency in the decision making process. The key aspect of our model is its ability to build a decision tree whose structure is encoded into the memory representation of a Recurrent Neural Network jointly learned by two models communicating through message passing. In addition, our model assigns a semant"},"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":"1902.01780","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-05T16:40:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"541d49be8232004550ccacbe5e21285d13d12a5ecf2f00a4def9a17538026aa5","abstract_canon_sha256":"13954c5bc270cf6b1015a206cb38f3a96c292bb87c76dbc5773000533e5c8c68"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:30:54.795222Z","signature_b64":"cCo6DOdw/QeTm9I3YZ+Fuqy1faY0HpTzf161ArHTSAs+H3HnMmuazJUOktTvERqMsnJWyPRL7hMzQG2HkrFjBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ae6512a54f8d009e9ac50bc2a29bf733f170776935a417105e94c26bd7dcf41","last_reissued_at":"2026-07-05T02:30:54.794788Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:30:54.794788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Decision Trees Recurrently Through Communication","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bernt Schiele, Diego Marcos, Stephan Alaniz, Zeynep Akata","submitted_at":"2019-02-05T16:40:34Z","abstract_excerpt":"Integrated interpretability without sacrificing the prediction accuracy of decision making algorithms has the potential of greatly improving their value to the user. Instead of assigning a label to an image directly, we propose to learn iterative binary sub-decisions, inducing sparsity and transparency in the decision making process. The key aspect of our model is its ability to build a decision tree whose structure is encoded into the memory representation of a Recurrent Neural Network jointly learned by two models communicating through message passing. In addition, our model assigns a semant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.01780","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1902.01780/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1902.01780","created_at":"2026-07-05T02:30:54.794849+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.01780v3","created_at":"2026-07-05T02:30:54.794849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.01780","created_at":"2026-07-05T02:30:54.794849+00:00"},{"alias_kind":"pith_short_12","alias_value":"TLTFCKSU7DIA","created_at":"2026-07-05T02:30:54.794849+00:00"},{"alias_kind":"pith_short_16","alias_value":"TLTFCKSU7DIAT2NM","created_at":"2026-07-05T02:30:54.794849+00:00"},{"alias_kind":"pith_short_8","alias_value":"TLTFCKSU","created_at":"2026-07-05T02:30:54.794849+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.04052","citing_title":"Decision Trees That Remember: Gradient-Based Learning of Recurrent Decision Trees with Memory","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TLTFCKSU7DIAT2NMKC6CUKN7OM","json":"https://pith.science/pith/TLTFCKSU7DIAT2NMKC6CUKN7OM.json","graph_json":"https://pith.science/api/pith-number/TLTFCKSU7DIAT2NMKC6CUKN7OM/graph.json","events_json":"https://pith.science/api/pith-number/TLTFCKSU7DIAT2NMKC6CUKN7OM/events.json","paper":"https://pith.science/paper/TLTFCKSU"},"agent_actions":{"view_html":"https://pith.science/pith/TLTFCKSU7DIAT2NMKC6CUKN7OM","download_json":"https://pith.science/pith/TLTFCKSU7DIAT2NMKC6CUKN7OM.json","view_paper":"https://pith.science/paper/TLTFCKSU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.01780&json=true","fetch_graph":"https://pith.science/api/pith-number/TLTFCKSU7DIAT2NMKC6CUKN7OM/graph.json","fetch_events":"https://pith.science/api/pith-number/TLTFCKSU7DIAT2NMKC6CUKN7OM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TLTFCKSU7DIAT2NMKC6CUKN7OM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TLTFCKSU7DIAT2NMKC6CUKN7OM/action/storage_attestation","attest_author":"https://pith.science/pith/TLTFCKSU7DIAT2NMKC6CUKN7OM/action/author_attestation","sign_citation":"https://pith.science/pith/TLTFCKSU7DIAT2NMKC6CUKN7OM/action/citation_signature","submit_replication":"https://pith.science/pith/TLTFCKSU7DIAT2NMKC6CUKN7OM/action/replication_record"}},"created_at":"2026-07-05T02:30:54.794849+00:00","updated_at":"2026-07-05T02:30:54.794849+00:00"}