{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2011:NPDLNDXZUFCVJFKFWAXY462NYB","short_pith_number":"pith:NPDLNDXZ","canonical_record":{"source":{"id":"1107.3022","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2011-07-15T09:39:57Z","cross_cats_sorted":[],"title_canon_sha256":"46c0204d626cbc935a0a6a315d576e11f1ae5103e735d9d9d42487b087f3b567","abstract_canon_sha256":"e8aff07c525011d2cc5e02c2803895d91eb0da937d2b5785096a3acac7020cec"},"schema_version":"1.0"},"canonical_sha256":"6bc6b68ef9a145549545b02f8e7b4dc05efe12379774f3cfbe87d6dbc40a8124","source":{"kind":"arxiv","id":"1107.3022","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1107.3022","created_at":"2026-05-18T04:18:14Z"},{"alias_kind":"arxiv_version","alias_value":"1107.3022v1","created_at":"2026-05-18T04:18:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1107.3022","created_at":"2026-05-18T04:18:14Z"},{"alias_kind":"pith_short_12","alias_value":"NPDLNDXZUFCV","created_at":"2026-05-18T12:26:37Z"},{"alias_kind":"pith_short_16","alias_value":"NPDLNDXZUFCVJFKF","created_at":"2026-05-18T12:26:37Z"},{"alias_kind":"pith_short_8","alias_value":"NPDLNDXZ","created_at":"2026-05-18T12:26:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2011:NPDLNDXZUFCVJFKFWAXY462NYB","target":"record","payload":{"canonical_record":{"source":{"id":"1107.3022","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2011-07-15T09:39:57Z","cross_cats_sorted":[],"title_canon_sha256":"46c0204d626cbc935a0a6a315d576e11f1ae5103e735d9d9d42487b087f3b567","abstract_canon_sha256":"e8aff07c525011d2cc5e02c2803895d91eb0da937d2b5785096a3acac7020cec"},"schema_version":"1.0"},"canonical_sha256":"6bc6b68ef9a145549545b02f8e7b4dc05efe12379774f3cfbe87d6dbc40a8124","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:18:14.889888Z","signature_b64":"uRczBd8eJDq61jP1QVH6kVfMmj7biXd4LFqMw+O3Ma7E0B/6RDyXEZ/dCYbW3itHIfUx7CvQY7IWzcS6RcW8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bc6b68ef9a145549545b02f8e7b4dc05efe12379774f3cfbe87d6dbc40a8124","last_reissued_at":"2026-05-18T04:18:14.889469Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:18:14.889469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1107.3022","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":"2026-05-18T04:18:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uYGsVIqwdgu4yK8Jov/KGOVAJLi6c4jGsmoM21OWI/YE09/bBPWhakGPjUZG3WeviOrnY75VMDJp/Uar/HHhBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T12:08:57.107190Z"},"content_sha256":"88671f00861b398f138aef58512962917c6e2a1f3d11d78c78d3e0b2c5c1b688","schema_version":"1.0","event_id":"sha256:88671f00861b398f138aef58512962917c6e2a1f3d11d78c78d3e0b2c5c1b688"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2011:NPDLNDXZUFCVJFKFWAXY462NYB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Computing q-gram Non-overlapping Frequencies on SLP Compressed Texts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Hideo Bannai, Keisuke Goto, Masayuki Takeda, Shunsuke Inenaga","submitted_at":"2011-07-15T09:39:57Z","abstract_excerpt":"Length-$q$ substrings, or $q$-grams, can represent important characteristics of text data, and determining the frequencies of all $q$-grams contained in the data is an important problem with many applications in the field of data mining and machine learning. In this paper, we consider the problem of calculating the {\\em non-overlapping frequencies} of all $q$-grams in a text given in compressed form, namely, as a straight line program (SLP). We show that the problem can be solved in $O(q^2n)$ time and $O(qn)$ space where $n$ is the size of the SLP. This generalizes and greatly improves previou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1107.3022","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":""},"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":"2026-05-18T04:18:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"03YMi+Ilj5C4wvZ5yT3Sz9BJVLwxJVQK2wqOXgfGZpN2roVwC4SmWIPqQWtFA0Nqh1gEJ12/okcnPSDepOEgAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T12:08:57.107558Z"},"content_sha256":"52cf071f57602114f75c6de2fc8d049fed37832cc5fc3faccd91ed94a6b708d9","schema_version":"1.0","event_id":"sha256:52cf071f57602114f75c6de2fc8d049fed37832cc5fc3faccd91ed94a6b708d9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NPDLNDXZUFCVJFKFWAXY462NYB/bundle.json","state_url":"https://pith.science/pith/NPDLNDXZUFCVJFKFWAXY462NYB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NPDLNDXZUFCVJFKFWAXY462NYB/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":"2026-05-28T12:08:57Z","links":{"resolver":"https://pith.science/pith/NPDLNDXZUFCVJFKFWAXY462NYB","bundle":"https://pith.science/pith/NPDLNDXZUFCVJFKFWAXY462NYB/bundle.json","state":"https://pith.science/pith/NPDLNDXZUFCVJFKFWAXY462NYB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NPDLNDXZUFCVJFKFWAXY462NYB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2011:NPDLNDXZUFCVJFKFWAXY462NYB","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":"e8aff07c525011d2cc5e02c2803895d91eb0da937d2b5785096a3acac7020cec","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2011-07-15T09:39:57Z","title_canon_sha256":"46c0204d626cbc935a0a6a315d576e11f1ae5103e735d9d9d42487b087f3b567"},"schema_version":"1.0","source":{"id":"1107.3022","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1107.3022","created_at":"2026-05-18T04:18:14Z"},{"alias_kind":"arxiv_version","alias_value":"1107.3022v1","created_at":"2026-05-18T04:18:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1107.3022","created_at":"2026-05-18T04:18:14Z"},{"alias_kind":"pith_short_12","alias_value":"NPDLNDXZUFCV","created_at":"2026-05-18T12:26:37Z"},{"alias_kind":"pith_short_16","alias_value":"NPDLNDXZUFCVJFKF","created_at":"2026-05-18T12:26:37Z"},{"alias_kind":"pith_short_8","alias_value":"NPDLNDXZ","created_at":"2026-05-18T12:26:37Z"}],"graph_snapshots":[{"event_id":"sha256:52cf071f57602114f75c6de2fc8d049fed37832cc5fc3faccd91ed94a6b708d9","target":"graph","created_at":"2026-05-18T04:18:14Z","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"},"paper":{"abstract_excerpt":"Length-$q$ substrings, or $q$-grams, can represent important characteristics of text data, and determining the frequencies of all $q$-grams contained in the data is an important problem with many applications in the field of data mining and machine learning. In this paper, we consider the problem of calculating the {\\em non-overlapping frequencies} of all $q$-grams in a text given in compressed form, namely, as a straight line program (SLP). We show that the problem can be solved in $O(q^2n)$ time and $O(qn)$ space where $n$ is the size of the SLP. This generalizes and greatly improves previou","authors_text":"Hideo Bannai, Keisuke Goto, Masayuki Takeda, Shunsuke Inenaga","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2011-07-15T09:39:57Z","title":"Computing q-gram Non-overlapping Frequencies on SLP Compressed Texts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1107.3022","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":"sha256:88671f00861b398f138aef58512962917c6e2a1f3d11d78c78d3e0b2c5c1b688","target":"record","created_at":"2026-05-18T04:18:14Z","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":"e8aff07c525011d2cc5e02c2803895d91eb0da937d2b5785096a3acac7020cec","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2011-07-15T09:39:57Z","title_canon_sha256":"46c0204d626cbc935a0a6a315d576e11f1ae5103e735d9d9d42487b087f3b567"},"schema_version":"1.0","source":{"id":"1107.3022","kind":"arxiv","version":1}},"canonical_sha256":"6bc6b68ef9a145549545b02f8e7b4dc05efe12379774f3cfbe87d6dbc40a8124","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6bc6b68ef9a145549545b02f8e7b4dc05efe12379774f3cfbe87d6dbc40a8124","first_computed_at":"2026-05-18T04:18:14.889469Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:18:14.889469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uRczBd8eJDq61jP1QVH6kVfMmj7biXd4LFqMw+O3Ma7E0B/6RDyXEZ/dCYbW3itHIfUx7CvQY7IWzcS6RcW8AQ==","signature_status":"signed_v1","signed_at":"2026-05-18T04:18:14.889888Z","signed_message":"canonical_sha256_bytes"},"source_id":"1107.3022","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88671f00861b398f138aef58512962917c6e2a1f3d11d78c78d3e0b2c5c1b688","sha256:52cf071f57602114f75c6de2fc8d049fed37832cc5fc3faccd91ed94a6b708d9"],"state_sha256":"2ed08a14abe3be6fcce3289ad4ba61206fc8631515ba7c1ad4ac6b8b45eb3bc8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+tYxRHIgWa1Pi7/F2E7zmtaV+pbrk8ZLNw3yLMXqqc6cVnLmxJxXaJb8T70PXvdRnsAcJdS/x8MkAE1jtsUJAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T12:08:57.109477Z","bundle_sha256":"50e616b63b156711fd8d88ded191bcbd7eef13e38f29ae9ddc9fe63f88e3995d"}}