{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:B2HNKGDBZQZMZBSTJWE55TOJGJ","short_pith_number":"pith:B2HNKGDB","canonical_record":{"source":{"id":"2412.13023","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-17T15:41:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d7b0fcd9285d8c27783772ccb31385119b5c8d991ad8eaf294a9b0365e98339d","abstract_canon_sha256":"2ae01e3ba9d1d3da22efc099aaaa9be5f7bfbf3ecf927deb265a0594e3e3b937"},"schema_version":"1.0"},"canonical_sha256":"0e8ed51861cc32cc86534d89decdc9324dbec1a3e40deb20f03a3423c46d3818","source":{"kind":"arxiv","id":"2412.13023","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13023","created_at":"2026-07-05T09:50:39Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13023v1","created_at":"2026-07-05T09:50:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13023","created_at":"2026-07-05T09:50:39Z"},{"alias_kind":"pith_short_12","alias_value":"B2HNKGDBZQZM","created_at":"2026-07-05T09:50:39Z"},{"alias_kind":"pith_short_16","alias_value":"B2HNKGDBZQZMZBST","created_at":"2026-07-05T09:50:39Z"},{"alias_kind":"pith_short_8","alias_value":"B2HNKGDB","created_at":"2026-07-05T09:50:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:B2HNKGDBZQZMZBSTJWE55TOJGJ","target":"record","payload":{"canonical_record":{"source":{"id":"2412.13023","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-17T15:41:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d7b0fcd9285d8c27783772ccb31385119b5c8d991ad8eaf294a9b0365e98339d","abstract_canon_sha256":"2ae01e3ba9d1d3da22efc099aaaa9be5f7bfbf3ecf927deb265a0594e3e3b937"},"schema_version":"1.0"},"canonical_sha256":"0e8ed51861cc32cc86534d89decdc9324dbec1a3e40deb20f03a3423c46d3818","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:39.207827Z","signature_b64":"GYNGyS6TVCwlflNcSvlRcU3+06o73QWk40NqdwT9zipawHJXsfSzBphEwk25xRvAfNA2G6RSEFS6jgmiGan0BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e8ed51861cc32cc86534d89decdc9324dbec1a3e40deb20f03a3423c46d3818","last_reissued_at":"2026-07-05T09:50:39.207220Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:39.207220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.13023","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":"2026-07-05T09:50:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eDFhm9Bjs4W5QPtqLwJw/f+FyfAcyDkMJsud8qjXuw8ZbKXgv2sb+t2jdbQ+qn0XpA2FxoMTQdcWHipeXkDoAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T01:30:52.087887Z"},"content_sha256":"6e6ecf354dcc05dd5f6179b0cf2f6c114ad2c02a40e3a25065ba723f9af342eb","schema_version":"1.0","event_id":"sha256:6e6ecf354dcc05dd5f6179b0cf2f6c114ad2c02a40e3a25065ba723f9af342eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:B2HNKGDBZQZMZBSTJWE55TOJGJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Relational Neurosymbolic Markov Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Gabriele Venturato, Giuseppe Marra, Lennert De Smet, Luc De Raedt","submitted_at":"2024-12-17T15:41:51Z","abstract_excerpt":"Sequential problems are ubiquitous in AI, such as in reinforcement learning or natural language processing. State-of-the-art deep sequential models, like transformers, excel in these settings but fail to guarantee the satisfaction of constraints necessary for trustworthy deployment. In contrast, neurosymbolic AI (NeSy) provides a sound formalism to enforce constraints in deep probabilistic models but scales exponentially on sequential problems. To overcome these limitations, we introduce relational neurosymbolic Markov models (NeSy-MMs), a new class of end-to-end differentiable sequential mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13023","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/2412.13023/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":"2026-07-05T09:50:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wLNgJ7xEC+MZg3qseHL6M4XBHh8BWsn82vUru74i4K4kutUeT5G5cBfcjokXG/kDUG/B9VY4lCNjMjunHpTCAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T01:30:52.088415Z"},"content_sha256":"537b34c314322d54689856631f3fc530af966167bd30f19dc3f6b761a4df1a56","schema_version":"1.0","event_id":"sha256:537b34c314322d54689856631f3fc530af966167bd30f19dc3f6b761a4df1a56"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B2HNKGDBZQZMZBSTJWE55TOJGJ/bundle.json","state_url":"https://pith.science/pith/B2HNKGDBZQZMZBSTJWE55TOJGJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B2HNKGDBZQZMZBSTJWE55TOJGJ/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":"2026-08-16T01:30:52Z","links":{"resolver":"https://pith.science/pith/B2HNKGDBZQZMZBSTJWE55TOJGJ","bundle":"https://pith.science/pith/B2HNKGDBZQZMZBSTJWE55TOJGJ/bundle.json","state":"https://pith.science/pith/B2HNKGDBZQZMZBSTJWE55TOJGJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B2HNKGDBZQZMZBSTJWE55TOJGJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:B2HNKGDBZQZMZBSTJWE55TOJGJ","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":"2ae01e3ba9d1d3da22efc099aaaa9be5f7bfbf3ecf927deb265a0594e3e3b937","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-17T15:41:51Z","title_canon_sha256":"d7b0fcd9285d8c27783772ccb31385119b5c8d991ad8eaf294a9b0365e98339d"},"schema_version":"1.0","source":{"id":"2412.13023","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13023","created_at":"2026-07-05T09:50:39Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13023v1","created_at":"2026-07-05T09:50:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13023","created_at":"2026-07-05T09:50:39Z"},{"alias_kind":"pith_short_12","alias_value":"B2HNKGDBZQZM","created_at":"2026-07-05T09:50:39Z"},{"alias_kind":"pith_short_16","alias_value":"B2HNKGDBZQZMZBST","created_at":"2026-07-05T09:50:39Z"},{"alias_kind":"pith_short_8","alias_value":"B2HNKGDB","created_at":"2026-07-05T09:50:39Z"}],"graph_snapshots":[{"event_id":"sha256:537b34c314322d54689856631f3fc530af966167bd30f19dc3f6b761a4df1a56","target":"graph","created_at":"2026-07-05T09:50:39Z","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/2412.13023/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sequential problems are ubiquitous in AI, such as in reinforcement learning or natural language processing. State-of-the-art deep sequential models, like transformers, excel in these settings but fail to guarantee the satisfaction of constraints necessary for trustworthy deployment. In contrast, neurosymbolic AI (NeSy) provides a sound formalism to enforce constraints in deep probabilistic models but scales exponentially on sequential problems. To overcome these limitations, we introduce relational neurosymbolic Markov models (NeSy-MMs), a new class of end-to-end differentiable sequential mode","authors_text":"Gabriele Venturato, Giuseppe Marra, Lennert De Smet, Luc De Raedt","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-17T15:41:51Z","title":"Relational Neurosymbolic Markov Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13023","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":"sha256:6e6ecf354dcc05dd5f6179b0cf2f6c114ad2c02a40e3a25065ba723f9af342eb","target":"record","created_at":"2026-07-05T09:50:39Z","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":"2ae01e3ba9d1d3da22efc099aaaa9be5f7bfbf3ecf927deb265a0594e3e3b937","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-17T15:41:51Z","title_canon_sha256":"d7b0fcd9285d8c27783772ccb31385119b5c8d991ad8eaf294a9b0365e98339d"},"schema_version":"1.0","source":{"id":"2412.13023","kind":"arxiv","version":1}},"canonical_sha256":"0e8ed51861cc32cc86534d89decdc9324dbec1a3e40deb20f03a3423c46d3818","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e8ed51861cc32cc86534d89decdc9324dbec1a3e40deb20f03a3423c46d3818","first_computed_at":"2026-07-05T09:50:39.207220Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:39.207220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GYNGyS6TVCwlflNcSvlRcU3+06o73QWk40NqdwT9zipawHJXsfSzBphEwk25xRvAfNA2G6RSEFS6jgmiGan0BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:39.207827Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.13023","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e6ecf354dcc05dd5f6179b0cf2f6c114ad2c02a40e3a25065ba723f9af342eb","sha256:537b34c314322d54689856631f3fc530af966167bd30f19dc3f6b761a4df1a56"],"state_sha256":"edec7d24e2230d4b35d2475393482c01b913923628f2111f9f79c34bf017ed46"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"57+/vD/kpA1vmAx3/CtyITsj7PXLIMHTZIoWUsEpJaENWFpjUpsoN5epuT+rysBMS+B+ijN5Fn91VJjXpn9dBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T01:30:52.093864Z","bundle_sha256":"ae6e34d70cd134500a6f4e87d85e0105fe0310d3222afa58272d22bcc19ed264"}}