{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:J52AS6GLU2Y7CFMGR2YF7R36UZ","short_pith_number":"pith:J52AS6GL","schema_version":"1.0","canonical_sha256":"4f740978cba6b1f115868eb05fc77ea654b6655bccab19c24e5c816479b07d17","source":{"kind":"arxiv","id":"2207.01744","version":1},"attestation_state":"computed","paper":{"title":"Discrete Tree Flows via Tree-Structured Permutations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David I. Inouye, Jim Lim, Mai Elkady","submitted_at":"2022-07-04T23:11:04Z","abstract_excerpt":"While normalizing flows for continuous data have been extensively researched, flows for discrete data have only recently been explored. These prior models, however, suffer from limitations that are distinct from those of continuous flows. Most notably, discrete flow-based models cannot be straightforwardly optimized with conventional deep learning methods because gradients of discrete functions are undefined or zero. Previous works approximate pseudo-gradients of the discrete functions but do not solve the problem on a fundamental level. In addition to that, backpropagation can be computationa"},"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":"2207.01744","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-04T23:11:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b27befdb720144ac811b474d0cab888193217823a5a6dff4e7b315bfe58dc5d3","abstract_canon_sha256":"b8744b9ccb0f16a7981065b9dd37aee6daebc8b512fffa7307b1044dbf238d29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:37:43.848699Z","signature_b64":"RS1ZXxRzqzzOy77VpcMADg/j/c/thutMezbEi7ErEYu/ztb8PlxPcLQkwnjq7Kao7l9ktdU4fwOUqyPsfIGKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f740978cba6b1f115868eb05fc77ea654b6655bccab19c24e5c816479b07d17","last_reissued_at":"2026-07-05T04:37:43.848258Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:37:43.848258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discrete Tree Flows via Tree-Structured Permutations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David I. Inouye, Jim Lim, Mai Elkady","submitted_at":"2022-07-04T23:11:04Z","abstract_excerpt":"While normalizing flows for continuous data have been extensively researched, flows for discrete data have only recently been explored. These prior models, however, suffer from limitations that are distinct from those of continuous flows. Most notably, discrete flow-based models cannot be straightforwardly optimized with conventional deep learning methods because gradients of discrete functions are undefined or zero. Previous works approximate pseudo-gradients of the discrete functions but do not solve the problem on a fundamental level. In addition to that, backpropagation can be computationa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.01744","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2207.01744/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":"2207.01744","created_at":"2026-07-05T04:37:43.848324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.01744v1","created_at":"2026-07-05T04:37:43.848324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.01744","created_at":"2026-07-05T04:37:43.848324+00:00"},{"alias_kind":"pith_short_12","alias_value":"J52AS6GLU2Y7","created_at":"2026-07-05T04:37:43.848324+00:00"},{"alias_kind":"pith_short_16","alias_value":"J52AS6GLU2Y7CFMG","created_at":"2026-07-05T04:37:43.848324+00:00"},{"alias_kind":"pith_short_8","alias_value":"J52AS6GL","created_at":"2026-07-05T04:37:43.848324+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/J52AS6GLU2Y7CFMGR2YF7R36UZ","json":"https://pith.science/pith/J52AS6GLU2Y7CFMGR2YF7R36UZ.json","graph_json":"https://pith.science/api/pith-number/J52AS6GLU2Y7CFMGR2YF7R36UZ/graph.json","events_json":"https://pith.science/api/pith-number/J52AS6GLU2Y7CFMGR2YF7R36UZ/events.json","paper":"https://pith.science/paper/J52AS6GL"},"agent_actions":{"view_html":"https://pith.science/pith/J52AS6GLU2Y7CFMGR2YF7R36UZ","download_json":"https://pith.science/pith/J52AS6GLU2Y7CFMGR2YF7R36UZ.json","view_paper":"https://pith.science/paper/J52AS6GL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.01744&json=true","fetch_graph":"https://pith.science/api/pith-number/J52AS6GLU2Y7CFMGR2YF7R36UZ/graph.json","fetch_events":"https://pith.science/api/pith-number/J52AS6GLU2Y7CFMGR2YF7R36UZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J52AS6GLU2Y7CFMGR2YF7R36UZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J52AS6GLU2Y7CFMGR2YF7R36UZ/action/storage_attestation","attest_author":"https://pith.science/pith/J52AS6GLU2Y7CFMGR2YF7R36UZ/action/author_attestation","sign_citation":"https://pith.science/pith/J52AS6GLU2Y7CFMGR2YF7R36UZ/action/citation_signature","submit_replication":"https://pith.science/pith/J52AS6GLU2Y7CFMGR2YF7R36UZ/action/replication_record"}},"created_at":"2026-07-05T04:37:43.848324+00:00","updated_at":"2026-07-05T04:37:43.848324+00:00"}