{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:TNT7WQYGSNE3BB7QZUEEYJ5FVJ","short_pith_number":"pith:TNT7WQYG","canonical_record":{"source":{"id":"2210.14763","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-26T14:52:44Z","cross_cats_sorted":[],"title_canon_sha256":"11da21aab9816da263d89fabcd39137fb2fd8ccd72d88e1b068a1e4413406364","abstract_canon_sha256":"2649f4fadae2719290b117ac0103735b2e6f506bdb59298e1c1a54823b5186f8"},"schema_version":"1.0"},"canonical_sha256":"9b67fb43069349b087f0cd084c27a5aa5bebd03f8db5052dc153a59267541e7a","source":{"kind":"arxiv","id":"2210.14763","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.14763","created_at":"2026-07-05T05:10:49Z"},{"alias_kind":"arxiv_version","alias_value":"2210.14763v1","created_at":"2026-07-05T05:10:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.14763","created_at":"2026-07-05T05:10:49Z"},{"alias_kind":"pith_short_12","alias_value":"TNT7WQYGSNE3","created_at":"2026-07-05T05:10:49Z"},{"alias_kind":"pith_short_16","alias_value":"TNT7WQYGSNE3BB7Q","created_at":"2026-07-05T05:10:49Z"},{"alias_kind":"pith_short_8","alias_value":"TNT7WQYG","created_at":"2026-07-05T05:10:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:TNT7WQYGSNE3BB7QZUEEYJ5FVJ","target":"record","payload":{"canonical_record":{"source":{"id":"2210.14763","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-26T14:52:44Z","cross_cats_sorted":[],"title_canon_sha256":"11da21aab9816da263d89fabcd39137fb2fd8ccd72d88e1b068a1e4413406364","abstract_canon_sha256":"2649f4fadae2719290b117ac0103735b2e6f506bdb59298e1c1a54823b5186f8"},"schema_version":"1.0"},"canonical_sha256":"9b67fb43069349b087f0cd084c27a5aa5bebd03f8db5052dc153a59267541e7a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:49.504936Z","signature_b64":"dA2pDVQlhY2j9YvLkTa7DLFVyZIZeEBbVmhroBjwgVPWQZuJNCLzz12RdDtnAtBBGnb8qUZbioOnikxc9yaoBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b67fb43069349b087f0cd084c27a5aa5bebd03f8db5052dc153a59267541e7a","last_reissued_at":"2026-07-05T05:10:49.504557Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:49.504557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.14763","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":"2026-07-05T05:10:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C/29smzW53vmdFhErMcwfpZaPxu5TslnZ1Bwn+nmXdeDpxjBQhzY475Uxd2UpfFmHksMBj4ozbL7FjCTmk8yCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T18:23:31.197532Z"},"content_sha256":"ad4d5743ccb365169feb2725cd18f1b080df7cfaceeae7965983756afb60aa23","schema_version":"1.0","event_id":"sha256:ad4d5743ccb365169feb2725cd18f1b080df7cfaceeae7965983756afb60aa23"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:TNT7WQYGSNE3BB7QZUEEYJ5FVJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ProSiT! Latent Variable Discovery with PROgressive SImilarity Thresholds","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dirk Hovy, Federico Bianchi, Tommaso Fornaciari","submitted_at":"2022-10-26T14:52:44Z","abstract_excerpt":"The most common ways to explore latent document dimensions are topic models and clustering methods. However, topic models have several drawbacks: e.g., they require us to choose the number of latent dimensions a priori, and the results are stochastic. Most clustering methods have the same issues and lack flexibility in various ways, such as not accounting for the influence of different topics on single documents, forcing word-descriptors to belong to a single topic (hard-clustering) or necessarily relying on word representations. We propose PROgressive SImilarity Thresholds - ProSiT, a determi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.14763","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/2210.14763/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":"2026-07-05T05:10:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ln/PSo4ivFp6S6P3cFPu3cZWGdr7LMS+LJ5dbgrpNyq5fD6ICHjhHfFQ48xUBMOhhiInOzJ6Nzs7s796h8S2Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T18:23:31.198887Z"},"content_sha256":"2207d812b767ca82b54426b0237f658d3ce2e9f87c3cfa8348ad0522994ee305","schema_version":"1.0","event_id":"sha256:2207d812b767ca82b54426b0237f658d3ce2e9f87c3cfa8348ad0522994ee305"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TNT7WQYGSNE3BB7QZUEEYJ5FVJ/bundle.json","state_url":"https://pith.science/pith/TNT7WQYGSNE3BB7QZUEEYJ5FVJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TNT7WQYGSNE3BB7QZUEEYJ5FVJ/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":"2026-08-13T18:23:31Z","links":{"resolver":"https://pith.science/pith/TNT7WQYGSNE3BB7QZUEEYJ5FVJ","bundle":"https://pith.science/pith/TNT7WQYGSNE3BB7QZUEEYJ5FVJ/bundle.json","state":"https://pith.science/pith/TNT7WQYGSNE3BB7QZUEEYJ5FVJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TNT7WQYGSNE3BB7QZUEEYJ5FVJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TNT7WQYGSNE3BB7QZUEEYJ5FVJ","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":"2649f4fadae2719290b117ac0103735b2e6f506bdb59298e1c1a54823b5186f8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-26T14:52:44Z","title_canon_sha256":"11da21aab9816da263d89fabcd39137fb2fd8ccd72d88e1b068a1e4413406364"},"schema_version":"1.0","source":{"id":"2210.14763","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.14763","created_at":"2026-07-05T05:10:49Z"},{"alias_kind":"arxiv_version","alias_value":"2210.14763v1","created_at":"2026-07-05T05:10:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.14763","created_at":"2026-07-05T05:10:49Z"},{"alias_kind":"pith_short_12","alias_value":"TNT7WQYGSNE3","created_at":"2026-07-05T05:10:49Z"},{"alias_kind":"pith_short_16","alias_value":"TNT7WQYGSNE3BB7Q","created_at":"2026-07-05T05:10:49Z"},{"alias_kind":"pith_short_8","alias_value":"TNT7WQYG","created_at":"2026-07-05T05:10:49Z"}],"graph_snapshots":[{"event_id":"sha256:2207d812b767ca82b54426b0237f658d3ce2e9f87c3cfa8348ad0522994ee305","target":"graph","created_at":"2026-07-05T05:10:49Z","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/2210.14763/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The most common ways to explore latent document dimensions are topic models and clustering methods. However, topic models have several drawbacks: e.g., they require us to choose the number of latent dimensions a priori, and the results are stochastic. Most clustering methods have the same issues and lack flexibility in various ways, such as not accounting for the influence of different topics on single documents, forcing word-descriptors to belong to a single topic (hard-clustering) or necessarily relying on word representations. We propose PROgressive SImilarity Thresholds - ProSiT, a determi","authors_text":"Dirk Hovy, Federico Bianchi, Tommaso Fornaciari","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-26T14:52:44Z","title":"ProSiT! Latent Variable Discovery with PROgressive SImilarity Thresholds"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.14763","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:ad4d5743ccb365169feb2725cd18f1b080df7cfaceeae7965983756afb60aa23","target":"record","created_at":"2026-07-05T05:10:49Z","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":"2649f4fadae2719290b117ac0103735b2e6f506bdb59298e1c1a54823b5186f8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-26T14:52:44Z","title_canon_sha256":"11da21aab9816da263d89fabcd39137fb2fd8ccd72d88e1b068a1e4413406364"},"schema_version":"1.0","source":{"id":"2210.14763","kind":"arxiv","version":1}},"canonical_sha256":"9b67fb43069349b087f0cd084c27a5aa5bebd03f8db5052dc153a59267541e7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b67fb43069349b087f0cd084c27a5aa5bebd03f8db5052dc153a59267541e7a","first_computed_at":"2026-07-05T05:10:49.504557Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:10:49.504557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dA2pDVQlhY2j9YvLkTa7DLFVyZIZeEBbVmhroBjwgVPWQZuJNCLzz12RdDtnAtBBGnb8qUZbioOnikxc9yaoBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:10:49.504936Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.14763","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad4d5743ccb365169feb2725cd18f1b080df7cfaceeae7965983756afb60aa23","sha256:2207d812b767ca82b54426b0237f658d3ce2e9f87c3cfa8348ad0522994ee305"],"state_sha256":"341acd929236d05f44071c72e7065423561fe20a4b4b264cc805babd5b0e5661"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+M+0/qV7KvqXVYVyRsBUreL0dyBG/LjQf2kg7pd13JbQ3q2C/TppNu8vcck9wu8IjxmhrMR0wP9H4dJGl1VFBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T18:23:31.240906Z","bundle_sha256":"62fec1dedd2f6b944d767e729e84db3e4a34847dc75e70f1b2332ab2cb6e1a14"}}