{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:DGS7FJUBVPMXQYZMIZQD6JHB7K","short_pith_number":"pith:DGS7FJUB","canonical_record":{"source":{"id":"2106.02965","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-05T21:19:42Z","cross_cats_sorted":["cs.FL"],"title_canon_sha256":"6df1dd01d363776cdbe6303c435e72ba6db076ed9c300bbe58600d10a7ef3178","abstract_canon_sha256":"4771d0ab5e6934667f8c7ef8602e1aa7dc035159fb7696704ea02b0d6bfb1542"},"schema_version":"1.0"},"canonical_sha256":"19a5f2a681abd978632c46603f24e1fab20dc1e6c3cedc507608983074f6d32c","source":{"kind":"arxiv","id":"2106.02965","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.02965","created_at":"2026-07-05T03:00:09Z"},{"alias_kind":"arxiv_version","alias_value":"2106.02965v2","created_at":"2026-07-05T03:00:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.02965","created_at":"2026-07-05T03:00:09Z"},{"alias_kind":"pith_short_12","alias_value":"DGS7FJUBVPMX","created_at":"2026-07-05T03:00:09Z"},{"alias_kind":"pith_short_16","alias_value":"DGS7FJUBVPMXQYZM","created_at":"2026-07-05T03:00:09Z"},{"alias_kind":"pith_short_8","alias_value":"DGS7FJUB","created_at":"2026-07-05T03:00:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:DGS7FJUBVPMXQYZMIZQD6JHB7K","target":"record","payload":{"canonical_record":{"source":{"id":"2106.02965","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-05T21:19:42Z","cross_cats_sorted":["cs.FL"],"title_canon_sha256":"6df1dd01d363776cdbe6303c435e72ba6db076ed9c300bbe58600d10a7ef3178","abstract_canon_sha256":"4771d0ab5e6934667f8c7ef8602e1aa7dc035159fb7696704ea02b0d6bfb1542"},"schema_version":"1.0"},"canonical_sha256":"19a5f2a681abd978632c46603f24e1fab20dc1e6c3cedc507608983074f6d32c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:09.687055Z","signature_b64":"RYzoKlLS3dmMH66L997Iv4x4QYOUoGgdIfAci1DoF2NniUbuZD5SOWHWqINVQtUA/eZIi8O7O9KPYMrfXNFeDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19a5f2a681abd978632c46603f24e1fab20dc1e6c3cedc507608983074f6d32c","last_reissued_at":"2026-07-05T03:00:09.686472Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:09.686472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.02965","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:00:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n5zG9sJtcSb86iX9qxzyxNFAHTiML+Rx2qFudlbEFlxUp+177g44D6ZHAav2z2P7Y58E84uXn4UrDshiLTWNBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:33:38.949903Z"},"content_sha256":"c2205b9ce4deb7da81c841482a89e7f9a45ed3b7ef9ad24346590885f66c274b","schema_version":"1.0","event_id":"sha256:c2205b9ce4deb7da81c841482a89e7f9a45ed3b7ef9ad24346590885f66c274b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:DGS7FJUBVPMXQYZMIZQD6JHB7K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Extracting Weighted Automata for Approximate Minimization in Language Modelling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.FL"],"primary_cat":"cs.LG","authors_text":"Clara Lacroce, Guillaume Rabusseau, Prakash Panangaden","submitted_at":"2021-06-05T21:19:42Z","abstract_excerpt":"In this paper we study the approximate minimization problem for language modelling. We assume we are given some language model as a black box. The objective is to obtain a weighted finite automaton (WFA) that fits within a given size constraint and which mimics the behaviour of the original model while minimizing some notion of distance between the black box and the extracted WFA. We provide an algorithm for the approximate minimization of black boxes trained for language modelling of sequential data over a one-letter alphabet. By reformulating the problem in terms of Hankel matrices, we lever"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.02965","kind":"arxiv","version":2},"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/2106.02965/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":"2026-07-05T03:00:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MdAp0Rg0PHhzVFmGkG28M9slpSs5V9jGMO4QiNXngpe+igJbJz3mMMlxzKLsM0mnOTABVWdYDAIWWq6IxPaCCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:33:38.950437Z"},"content_sha256":"51739c8d3e33dd7280df6b5c001bad832931bb72be233388f20e138388240073","schema_version":"1.0","event_id":"sha256:51739c8d3e33dd7280df6b5c001bad832931bb72be233388f20e138388240073"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DGS7FJUBVPMXQYZMIZQD6JHB7K/bundle.json","state_url":"https://pith.science/pith/DGS7FJUBVPMXQYZMIZQD6JHB7K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DGS7FJUBVPMXQYZMIZQD6JHB7K/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":"2026-08-04T21:33:38Z","links":{"resolver":"https://pith.science/pith/DGS7FJUBVPMXQYZMIZQD6JHB7K","bundle":"https://pith.science/pith/DGS7FJUBVPMXQYZMIZQD6JHB7K/bundle.json","state":"https://pith.science/pith/DGS7FJUBVPMXQYZMIZQD6JHB7K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DGS7FJUBVPMXQYZMIZQD6JHB7K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:DGS7FJUBVPMXQYZMIZQD6JHB7K","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":"4771d0ab5e6934667f8c7ef8602e1aa7dc035159fb7696704ea02b0d6bfb1542","cross_cats_sorted":["cs.FL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-05T21:19:42Z","title_canon_sha256":"6df1dd01d363776cdbe6303c435e72ba6db076ed9c300bbe58600d10a7ef3178"},"schema_version":"1.0","source":{"id":"2106.02965","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.02965","created_at":"2026-07-05T03:00:09Z"},{"alias_kind":"arxiv_version","alias_value":"2106.02965v2","created_at":"2026-07-05T03:00:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.02965","created_at":"2026-07-05T03:00:09Z"},{"alias_kind":"pith_short_12","alias_value":"DGS7FJUBVPMX","created_at":"2026-07-05T03:00:09Z"},{"alias_kind":"pith_short_16","alias_value":"DGS7FJUBVPMXQYZM","created_at":"2026-07-05T03:00:09Z"},{"alias_kind":"pith_short_8","alias_value":"DGS7FJUB","created_at":"2026-07-05T03:00:09Z"}],"graph_snapshots":[{"event_id":"sha256:51739c8d3e33dd7280df6b5c001bad832931bb72be233388f20e138388240073","target":"graph","created_at":"2026-07-05T03:00:09Z","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/2106.02965/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper we study the approximate minimization problem for language modelling. We assume we are given some language model as a black box. The objective is to obtain a weighted finite automaton (WFA) that fits within a given size constraint and which mimics the behaviour of the original model while minimizing some notion of distance between the black box and the extracted WFA. We provide an algorithm for the approximate minimization of black boxes trained for language modelling of sequential data over a one-letter alphabet. By reformulating the problem in terms of Hankel matrices, we lever","authors_text":"Clara Lacroce, Guillaume Rabusseau, Prakash Panangaden","cross_cats":["cs.FL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-05T21:19:42Z","title":"Extracting Weighted Automata for Approximate Minimization in Language Modelling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.02965","kind":"arxiv","version":2},"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:c2205b9ce4deb7da81c841482a89e7f9a45ed3b7ef9ad24346590885f66c274b","target":"record","created_at":"2026-07-05T03:00:09Z","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":"4771d0ab5e6934667f8c7ef8602e1aa7dc035159fb7696704ea02b0d6bfb1542","cross_cats_sorted":["cs.FL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-05T21:19:42Z","title_canon_sha256":"6df1dd01d363776cdbe6303c435e72ba6db076ed9c300bbe58600d10a7ef3178"},"schema_version":"1.0","source":{"id":"2106.02965","kind":"arxiv","version":2}},"canonical_sha256":"19a5f2a681abd978632c46603f24e1fab20dc1e6c3cedc507608983074f6d32c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19a5f2a681abd978632c46603f24e1fab20dc1e6c3cedc507608983074f6d32c","first_computed_at":"2026-07-05T03:00:09.686472Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:00:09.686472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RYzoKlLS3dmMH66L997Iv4x4QYOUoGgdIfAci1DoF2NniUbuZD5SOWHWqINVQtUA/eZIi8O7O9KPYMrfXNFeDw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:00:09.687055Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.02965","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2205b9ce4deb7da81c841482a89e7f9a45ed3b7ef9ad24346590885f66c274b","sha256:51739c8d3e33dd7280df6b5c001bad832931bb72be233388f20e138388240073"],"state_sha256":"9374d515f438809886bb06ea91269634bc760d472cdd705fd1a49cd3820bf708"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N7yKIsz7HTvGCq/t5p66n+ZR6dG2/hRuuaI0PtPTC7ZwPxg3hhVIedGc0Uujtap1iRslouXLr5lmq+iZjEJqAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:33:38.956149Z","bundle_sha256":"036dd36eac6d537f8f54dfdc452bb2cd7b377a535e5c2f0f47214d6476251d97"}}