{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:X22MUTQPO7YD6NHP5BJLCZGULW","short_pith_number":"pith:X22MUTQP","canonical_record":{"source":{"id":"1704.01617","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-04-05T19:16:58Z","cross_cats_sorted":[],"title_canon_sha256":"6ededffc731be6f8e31ad97303f2fa29d40fa6eabe8a9602b83d7f2a5468acb2","abstract_canon_sha256":"32b711d9fbc935a4d7a7ee74829a8a92dca75e64b5846c1945fb4482d368cdd5"},"schema_version":"1.0"},"canonical_sha256":"beb4ca4e0f77f03f34efe852b164d45da8f8e7a98770f9c21f32335493e54422","source":{"kind":"arxiv","id":"1704.01617","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.01617","created_at":"2026-05-18T00:46:54Z"},{"alias_kind":"arxiv_version","alias_value":"1704.01617v1","created_at":"2026-05-18T00:46:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.01617","created_at":"2026-05-18T00:46:54Z"},{"alias_kind":"pith_short_12","alias_value":"X22MUTQPO7YD","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"X22MUTQPO7YD6NHP","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"X22MUTQP","created_at":"2026-05-18T12:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:X22MUTQPO7YD6NHP5BJLCZGULW","target":"record","payload":{"canonical_record":{"source":{"id":"1704.01617","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-04-05T19:16:58Z","cross_cats_sorted":[],"title_canon_sha256":"6ededffc731be6f8e31ad97303f2fa29d40fa6eabe8a9602b83d7f2a5468acb2","abstract_canon_sha256":"32b711d9fbc935a4d7a7ee74829a8a92dca75e64b5846c1945fb4482d368cdd5"},"schema_version":"1.0"},"canonical_sha256":"beb4ca4e0f77f03f34efe852b164d45da8f8e7a98770f9c21f32335493e54422","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:54.749207Z","signature_b64":"FbOyIcR0RnsHTVBsthwVZUw+wwpvwARzVg6X+sqqHRqmg0ne0YNDt8lIh/cnLfZtN7f2qncQC1j6gqeHCtDFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"beb4ca4e0f77f03f34efe852b164d45da8f8e7a98770f9c21f32335493e54422","last_reissued_at":"2026-05-18T00:46:54.748610Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:54.748610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.01617","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":"2026-05-18T00:46:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gzyWbR7CoynrBb6QtZeSubX1Exx0flfSj6Ixn42fsqpERNTN9fcs3Nt12uRRzbtqyHgiW/qLylzmKWazbPePBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T22:37:09.476977Z"},"content_sha256":"28923abce9140ef4448551a88f9822cfa8825386a846b5ee239b551bdd4addd8","schema_version":"1.0","event_id":"sha256:28923abce9140ef4448551a88f9822cfa8825386a846b5ee239b551bdd4addd8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:X22MUTQPO7YD6NHP5BJLCZGULW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Part of Speech Based Term Weighting for Information Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Christina Lioma, Roi Blanco","submitted_at":"2017-04-05T19:16:58Z","abstract_excerpt":"Automatic language processing tools typically assign to terms so-called weights corresponding to the contribution of terms to information content. Traditionally, term weights are computed from lexical statistics, e.g., term frequencies. We propose a new type of term weight that is computed from part of speech (POS) n-gram statistics. The proposed POS-based term weight represents how informative a term is in general, based on the POS contexts in which it generally occurs in language. We suggest five different computations of POS-based term weights by extending existing statistical approximation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.01617","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":"2026-05-18T00:46:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NhBnCtUIsBkSfCzqnOqOWOc/CjQetpwj3uE747qqpskwAtfCRzsHBZS/rOVRKgkLZCXHtffyJS0EiuBtKUmXCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T22:37:09.477717Z"},"content_sha256":"a76928e9718a2265c30fe56607887bb7a0987fb74c0e0ddf69086a31e445847d","schema_version":"1.0","event_id":"sha256:a76928e9718a2265c30fe56607887bb7a0987fb74c0e0ddf69086a31e445847d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X22MUTQPO7YD6NHP5BJLCZGULW/bundle.json","state_url":"https://pith.science/pith/X22MUTQPO7YD6NHP5BJLCZGULW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X22MUTQPO7YD6NHP5BJLCZGULW/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":"2026-06-10T22:37:09Z","links":{"resolver":"https://pith.science/pith/X22MUTQPO7YD6NHP5BJLCZGULW","bundle":"https://pith.science/pith/X22MUTQPO7YD6NHP5BJLCZGULW/bundle.json","state":"https://pith.science/pith/X22MUTQPO7YD6NHP5BJLCZGULW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X22MUTQPO7YD6NHP5BJLCZGULW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:X22MUTQPO7YD6NHP5BJLCZGULW","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":"32b711d9fbc935a4d7a7ee74829a8a92dca75e64b5846c1945fb4482d368cdd5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-04-05T19:16:58Z","title_canon_sha256":"6ededffc731be6f8e31ad97303f2fa29d40fa6eabe8a9602b83d7f2a5468acb2"},"schema_version":"1.0","source":{"id":"1704.01617","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.01617","created_at":"2026-05-18T00:46:54Z"},{"alias_kind":"arxiv_version","alias_value":"1704.01617v1","created_at":"2026-05-18T00:46:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.01617","created_at":"2026-05-18T00:46:54Z"},{"alias_kind":"pith_short_12","alias_value":"X22MUTQPO7YD","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"X22MUTQPO7YD6NHP","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"X22MUTQP","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:a76928e9718a2265c30fe56607887bb7a0987fb74c0e0ddf69086a31e445847d","target":"graph","created_at":"2026-05-18T00:46:54Z","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":"Automatic language processing tools typically assign to terms so-called weights corresponding to the contribution of terms to information content. Traditionally, term weights are computed from lexical statistics, e.g., term frequencies. We propose a new type of term weight that is computed from part of speech (POS) n-gram statistics. The proposed POS-based term weight represents how informative a term is in general, based on the POS contexts in which it generally occurs in language. We suggest five different computations of POS-based term weights by extending existing statistical approximation","authors_text":"Christina Lioma, Roi Blanco","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-04-05T19:16:58Z","title":"Part of Speech Based Term Weighting for Information Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.01617","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":"sha256:28923abce9140ef4448551a88f9822cfa8825386a846b5ee239b551bdd4addd8","target":"record","created_at":"2026-05-18T00:46:54Z","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":"32b711d9fbc935a4d7a7ee74829a8a92dca75e64b5846c1945fb4482d368cdd5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-04-05T19:16:58Z","title_canon_sha256":"6ededffc731be6f8e31ad97303f2fa29d40fa6eabe8a9602b83d7f2a5468acb2"},"schema_version":"1.0","source":{"id":"1704.01617","kind":"arxiv","version":1}},"canonical_sha256":"beb4ca4e0f77f03f34efe852b164d45da8f8e7a98770f9c21f32335493e54422","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"beb4ca4e0f77f03f34efe852b164d45da8f8e7a98770f9c21f32335493e54422","first_computed_at":"2026-05-18T00:46:54.748610Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:46:54.748610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FbOyIcR0RnsHTVBsthwVZUw+wwpvwARzVg6X+sqqHRqmg0ne0YNDt8lIh/cnLfZtN7f2qncQC1j6gqeHCtDFBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:46:54.749207Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.01617","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28923abce9140ef4448551a88f9822cfa8825386a846b5ee239b551bdd4addd8","sha256:a76928e9718a2265c30fe56607887bb7a0987fb74c0e0ddf69086a31e445847d"],"state_sha256":"ba63cf70edda3ee51ae6d6efcc4ef0eb48cec69be26b4b1530e351c8fbe601ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZpOkUqZAP6jGmkZuZe0mwOi4MwyzZHPmzgtu+aOVaoEM44Ya5qE308oFLBQkIQO5nL6JnlKTIXPBCl6nc4lDCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T22:37:09.481520Z","bundle_sha256":"b72e557d0c3d36bce9feadd6dec945dec8a02eabbbf8cb533da9b2d32182bba2"}}