{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3G5DJAJ6VFPHRU5NX2SZ5W7ORH","short_pith_number":"pith:3G5DJAJ6","canonical_record":{"source":{"id":"2307.14193","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-26T13:47:52Z","cross_cats_sorted":[],"title_canon_sha256":"bc02f18d68c88eac3987788c2206a8b69fb88e6d83fb6e85a432e385fc3bb5b1","abstract_canon_sha256":"c8c5da03d36a0ea2b7202fd69d1a6b875e7185966643f8fe1bf1a10cdf1921c9"},"schema_version":"1.0"},"canonical_sha256":"d9ba34813ea95e78d3adbea59edbee89d62cb10e5f7e0f4220a7dfdafa1815a6","source":{"kind":"arxiv","id":"2307.14193","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.14193","created_at":"2026-07-05T06:34:58Z"},{"alias_kind":"arxiv_version","alias_value":"2307.14193v1","created_at":"2026-07-05T06:34:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.14193","created_at":"2026-07-05T06:34:58Z"},{"alias_kind":"pith_short_12","alias_value":"3G5DJAJ6VFPH","created_at":"2026-07-05T06:34:58Z"},{"alias_kind":"pith_short_16","alias_value":"3G5DJAJ6VFPHRU5N","created_at":"2026-07-05T06:34:58Z"},{"alias_kind":"pith_short_8","alias_value":"3G5DJAJ6","created_at":"2026-07-05T06:34:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3G5DJAJ6VFPHRU5NX2SZ5W7ORH","target":"record","payload":{"canonical_record":{"source":{"id":"2307.14193","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-26T13:47:52Z","cross_cats_sorted":[],"title_canon_sha256":"bc02f18d68c88eac3987788c2206a8b69fb88e6d83fb6e85a432e385fc3bb5b1","abstract_canon_sha256":"c8c5da03d36a0ea2b7202fd69d1a6b875e7185966643f8fe1bf1a10cdf1921c9"},"schema_version":"1.0"},"canonical_sha256":"d9ba34813ea95e78d3adbea59edbee89d62cb10e5f7e0f4220a7dfdafa1815a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:34:58.887797Z","signature_b64":"C6xqDl7X1NRrAiwMMUfr9Y1dA9n/N70PQ5mnZ/ZKSerM2k96MwAvhmacI8N02bwfdX3Auo2T6X+gHzk79dFuAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9ba34813ea95e78d3adbea59edbee89d62cb10e5f7e0f4220a7dfdafa1815a6","last_reissued_at":"2026-07-05T06:34:58.887362Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:34:58.887362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.14193","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:34:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wd4uTwveyzEkx333ZfTdB9BIcHFtOaEMVus0+3WjA6rKn+1URFneT3vpzoCqn4979VBt1LP6TPcPLmIKkbQgAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:09:01.819903Z"},"content_sha256":"126a43c987309300ebfb3d44feb4858bcbdd7a5e21585454f21caad197972ab6","schema_version":"1.0","event_id":"sha256:126a43c987309300ebfb3d44feb4858bcbdd7a5e21585454f21caad197972ab6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3G5DJAJ6VFPHRU5NX2SZ5W7ORH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Learning of Discrete-Continuous Computation Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"David Friede, Mathias Niepert","submitted_at":"2023-07-26T13:47:52Z","abstract_excerpt":"Numerous models for supervised and reinforcement learning benefit from combinations of discrete and continuous model components. End-to-end learnable discrete-continuous models are compositional, tend to generalize better, and are more interpretable. A popular approach to building discrete-continuous computation graphs is that of integrating discrete probability distributions into neural networks using stochastic softmax tricks. Prior work has mainly focused on computation graphs with a single discrete component on each of the graph's execution paths. We analyze the behavior of more complex st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.14193","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/2307.14193/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:34:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H4J3PIvtgvJch/B4bw2iZjAT2uSAA5rGF2erdISo7tkeN7t5ixj0D6zKkUHi3a7XLeg+enoLZx7sR+3OYSvSCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:09:01.820417Z"},"content_sha256":"d6395bae61d0105a95bef9429b0ea7a594ad337e972db3c586bdfa48d71aacc8","schema_version":"1.0","event_id":"sha256:d6395bae61d0105a95bef9429b0ea7a594ad337e972db3c586bdfa48d71aacc8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3G5DJAJ6VFPHRU5NX2SZ5W7ORH/bundle.json","state_url":"https://pith.science/pith/3G5DJAJ6VFPHRU5NX2SZ5W7ORH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3G5DJAJ6VFPHRU5NX2SZ5W7ORH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T08:09:01Z","links":{"resolver":"https://pith.science/pith/3G5DJAJ6VFPHRU5NX2SZ5W7ORH","bundle":"https://pith.science/pith/3G5DJAJ6VFPHRU5NX2SZ5W7ORH/bundle.json","state":"https://pith.science/pith/3G5DJAJ6VFPHRU5NX2SZ5W7ORH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3G5DJAJ6VFPHRU5NX2SZ5W7ORH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3G5DJAJ6VFPHRU5NX2SZ5W7ORH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c8c5da03d36a0ea2b7202fd69d1a6b875e7185966643f8fe1bf1a10cdf1921c9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-26T13:47:52Z","title_canon_sha256":"bc02f18d68c88eac3987788c2206a8b69fb88e6d83fb6e85a432e385fc3bb5b1"},"schema_version":"1.0","source":{"id":"2307.14193","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.14193","created_at":"2026-07-05T06:34:58Z"},{"alias_kind":"arxiv_version","alias_value":"2307.14193v1","created_at":"2026-07-05T06:34:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.14193","created_at":"2026-07-05T06:34:58Z"},{"alias_kind":"pith_short_12","alias_value":"3G5DJAJ6VFPH","created_at":"2026-07-05T06:34:58Z"},{"alias_kind":"pith_short_16","alias_value":"3G5DJAJ6VFPHRU5N","created_at":"2026-07-05T06:34:58Z"},{"alias_kind":"pith_short_8","alias_value":"3G5DJAJ6","created_at":"2026-07-05T06:34:58Z"}],"graph_snapshots":[{"event_id":"sha256:d6395bae61d0105a95bef9429b0ea7a594ad337e972db3c586bdfa48d71aacc8","target":"graph","created_at":"2026-07-05T06:34:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2307.14193/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Numerous models for supervised and reinforcement learning benefit from combinations of discrete and continuous model components. End-to-end learnable discrete-continuous models are compositional, tend to generalize better, and are more interpretable. A popular approach to building discrete-continuous computation graphs is that of integrating discrete probability distributions into neural networks using stochastic softmax tricks. Prior work has mainly focused on computation graphs with a single discrete component on each of the graph's execution paths. We analyze the behavior of more complex st","authors_text":"David Friede, Mathias Niepert","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-26T13:47:52Z","title":"Efficient Learning of Discrete-Continuous Computation Graphs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.14193","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:126a43c987309300ebfb3d44feb4858bcbdd7a5e21585454f21caad197972ab6","target":"record","created_at":"2026-07-05T06:34:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c8c5da03d36a0ea2b7202fd69d1a6b875e7185966643f8fe1bf1a10cdf1921c9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-26T13:47:52Z","title_canon_sha256":"bc02f18d68c88eac3987788c2206a8b69fb88e6d83fb6e85a432e385fc3bb5b1"},"schema_version":"1.0","source":{"id":"2307.14193","kind":"arxiv","version":1}},"canonical_sha256":"d9ba34813ea95e78d3adbea59edbee89d62cb10e5f7e0f4220a7dfdafa1815a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9ba34813ea95e78d3adbea59edbee89d62cb10e5f7e0f4220a7dfdafa1815a6","first_computed_at":"2026-07-05T06:34:58.887362Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:34:58.887362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C6xqDl7X1NRrAiwMMUfr9Y1dA9n/N70PQ5mnZ/ZKSerM2k96MwAvhmacI8N02bwfdX3Auo2T6X+gHzk79dFuAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:34:58.887797Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.14193","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:126a43c987309300ebfb3d44feb4858bcbdd7a5e21585454f21caad197972ab6","sha256:d6395bae61d0105a95bef9429b0ea7a594ad337e972db3c586bdfa48d71aacc8"],"state_sha256":"c11fc16bbb4684e9621fb5f4b0e66b41827e19bb31eda4e73feedc885556b01c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pNG3LYL00iq+l+X+IporFfi16qV9AS+2paldAWjFLHihicXtiKKBFVFtmHlOEavFuZgBf1LOwZOokMMc3GBrBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T08:09:01.824483Z","bundle_sha256":"280733440b2901eb3dbaef31733112af9828a16072ba5efd38d132bbef050e7e"}}