{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:GAL6SLBEXKAFSWYBFMNHJQZJRR","short_pith_number":"pith:GAL6SLBE","canonical_record":{"source":{"id":"1205.6396","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2012-05-29T15:37:46Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c57e01bc395ea06a6bb82fa8556b4e5ed7b4c20c3d1110c8015d49b4833b34dc","abstract_canon_sha256":"186ac9b69774013e0b86710b1f3a330c798cd3ca62a61dfb01d2443223b74240"},"schema_version":"1.0"},"canonical_sha256":"3017e92c24ba80595b012b1a74c3298c4ca1c8bda22f5a270af32d09ef5aec3f","source":{"kind":"arxiv","id":"1205.6396","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1205.6396","created_at":"2026-05-18T03:54:47Z"},{"alias_kind":"arxiv_version","alias_value":"1205.6396v1","created_at":"2026-05-18T03:54:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1205.6396","created_at":"2026-05-18T03:54:47Z"},{"alias_kind":"pith_short_12","alias_value":"GAL6SLBEXKAF","created_at":"2026-05-18T12:27:06Z"},{"alias_kind":"pith_short_16","alias_value":"GAL6SLBEXKAFSWYB","created_at":"2026-05-18T12:27:06Z"},{"alias_kind":"pith_short_8","alias_value":"GAL6SLBE","created_at":"2026-05-18T12:27:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:GAL6SLBEXKAFSWYBFMNHJQZJRR","target":"record","payload":{"canonical_record":{"source":{"id":"1205.6396","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2012-05-29T15:37:46Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c57e01bc395ea06a6bb82fa8556b4e5ed7b4c20c3d1110c8015d49b4833b34dc","abstract_canon_sha256":"186ac9b69774013e0b86710b1f3a330c798cd3ca62a61dfb01d2443223b74240"},"schema_version":"1.0"},"canonical_sha256":"3017e92c24ba80595b012b1a74c3298c4ca1c8bda22f5a270af32d09ef5aec3f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:54:47.133072Z","signature_b64":"aO8gmOIz6oSzqcLSgxy/NGB5E1xNB18Ndy0iNbM3iky9WKFgFvsNjI/UuoRxmQLIyWvXf5TpUVOOhRVFfLWbDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3017e92c24ba80595b012b1a74c3298c4ca1c8bda22f5a270af32d09ef5aec3f","last_reissued_at":"2026-05-18T03:54:47.132401Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:54:47.132401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1205.6396","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":"2026-05-18T03:54:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BdkU9XlLTxO6VaCO5RXp3HKX1RmICvvWZeHyvoiNjSy7gbNpimYM3eFbuKiFJk63Lx4BMaAfSPwXOYerm+NzAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T07:20:16.315211Z"},"content_sha256":"ac0f5c552aa969e0853518e77b6bb4135a72e1203f392d697f3c4e5ce6b24d70","schema_version":"1.0","event_id":"sha256:ac0f5c552aa969e0853518e77b6bb4135a72e1203f392d697f3c4e5ce6b24d70"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:GAL6SLBEXKAFSWYBFMNHJQZJRR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Effective Listings of Function Stop words for Twitter","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Murphy Choy","submitted_at":"2012-05-29T15:37:46Z","abstract_excerpt":"Many words in documents recur very frequently but are essentially meaningless as they are used to join words together in a sentence. It is commonly understood that stop words do not contribute to the context or content of textual documents. Due to their high frequency of occurrence, their presence in text mining presents an obstacle to the understanding of the content in the documents. To eliminate the bias effects, most text mining software or approaches make use of stop words list to identify and remove those words. However, the development of such top words list is difficult and inconsisten"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1205.6396","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":"2026-05-18T03:54:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u/d18NWu9eKgucCOEbLBPuJTlHJkkyyyTt3gYrUQ+Bg4M9NOx6jXoNaLQ8dpVGLBJ791yPXpeJwYe0oOtjokAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T07:20:16.315638Z"},"content_sha256":"8e40eb7259f6d130bdf5b6fc921cd0bb9da102ba5f467c6c38bb6a9a30f06d6e","schema_version":"1.0","event_id":"sha256:8e40eb7259f6d130bdf5b6fc921cd0bb9da102ba5f467c6c38bb6a9a30f06d6e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GAL6SLBEXKAFSWYBFMNHJQZJRR/bundle.json","state_url":"https://pith.science/pith/GAL6SLBEXKAFSWYBFMNHJQZJRR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GAL6SLBEXKAFSWYBFMNHJQZJRR/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":"2026-06-30T07:20:16Z","links":{"resolver":"https://pith.science/pith/GAL6SLBEXKAFSWYBFMNHJQZJRR","bundle":"https://pith.science/pith/GAL6SLBEXKAFSWYBFMNHJQZJRR/bundle.json","state":"https://pith.science/pith/GAL6SLBEXKAFSWYBFMNHJQZJRR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GAL6SLBEXKAFSWYBFMNHJQZJRR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:GAL6SLBEXKAFSWYBFMNHJQZJRR","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":"186ac9b69774013e0b86710b1f3a330c798cd3ca62a61dfb01d2443223b74240","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2012-05-29T15:37:46Z","title_canon_sha256":"c57e01bc395ea06a6bb82fa8556b4e5ed7b4c20c3d1110c8015d49b4833b34dc"},"schema_version":"1.0","source":{"id":"1205.6396","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1205.6396","created_at":"2026-05-18T03:54:47Z"},{"alias_kind":"arxiv_version","alias_value":"1205.6396v1","created_at":"2026-05-18T03:54:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1205.6396","created_at":"2026-05-18T03:54:47Z"},{"alias_kind":"pith_short_12","alias_value":"GAL6SLBEXKAF","created_at":"2026-05-18T12:27:06Z"},{"alias_kind":"pith_short_16","alias_value":"GAL6SLBEXKAFSWYB","created_at":"2026-05-18T12:27:06Z"},{"alias_kind":"pith_short_8","alias_value":"GAL6SLBE","created_at":"2026-05-18T12:27:06Z"}],"graph_snapshots":[{"event_id":"sha256:8e40eb7259f6d130bdf5b6fc921cd0bb9da102ba5f467c6c38bb6a9a30f06d6e","target":"graph","created_at":"2026-05-18T03:54:47Z","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":"Many words in documents recur very frequently but are essentially meaningless as they are used to join words together in a sentence. It is commonly understood that stop words do not contribute to the context or content of textual documents. Due to their high frequency of occurrence, their presence in text mining presents an obstacle to the understanding of the content in the documents. To eliminate the bias effects, most text mining software or approaches make use of stop words list to identify and remove those words. However, the development of such top words list is difficult and inconsisten","authors_text":"Murphy Choy","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2012-05-29T15:37:46Z","title":"Effective Listings of Function Stop words for Twitter"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1205.6396","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:ac0f5c552aa969e0853518e77b6bb4135a72e1203f392d697f3c4e5ce6b24d70","target":"record","created_at":"2026-05-18T03:54:47Z","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":"186ac9b69774013e0b86710b1f3a330c798cd3ca62a61dfb01d2443223b74240","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2012-05-29T15:37:46Z","title_canon_sha256":"c57e01bc395ea06a6bb82fa8556b4e5ed7b4c20c3d1110c8015d49b4833b34dc"},"schema_version":"1.0","source":{"id":"1205.6396","kind":"arxiv","version":1}},"canonical_sha256":"3017e92c24ba80595b012b1a74c3298c4ca1c8bda22f5a270af32d09ef5aec3f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3017e92c24ba80595b012b1a74c3298c4ca1c8bda22f5a270af32d09ef5aec3f","first_computed_at":"2026-05-18T03:54:47.132401Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:54:47.132401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aO8gmOIz6oSzqcLSgxy/NGB5E1xNB18Ndy0iNbM3iky9WKFgFvsNjI/UuoRxmQLIyWvXf5TpUVOOhRVFfLWbDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:54:47.133072Z","signed_message":"canonical_sha256_bytes"},"source_id":"1205.6396","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac0f5c552aa969e0853518e77b6bb4135a72e1203f392d697f3c4e5ce6b24d70","sha256:8e40eb7259f6d130bdf5b6fc921cd0bb9da102ba5f467c6c38bb6a9a30f06d6e"],"state_sha256":"b4ea149df8223c0171ad54a6e28ee7344d4313d4223d99293456661c47e5a2e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aa98mDMUFGWz5jt386yadkHZlMoYQOTNNgQcO+RRjzWWmAoX7DAiIHFRxjk6PefaS9Flz8dzYW8Oy0upfvQJDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T07:20:16.318629Z","bundle_sha256":"c6ab9d2f6d4bc9db05fe4d8c66354baad577caf7cbdeae3e8923bde7d7c6ca2e"}}