{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:FES5ZBLQEX4I6LCI4LQBRHX5XZ","short_pith_number":"pith:FES5ZBLQ","canonical_record":{"source":{"id":"1703.00565","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-02T00:48:15Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"9431d1265fdc9813b636a15da95821513f70c38ec40aa6d9cc728ca858d6891c","abstract_canon_sha256":"5925235bc9fc8716a459be8dce7915272b84dbb5961c13d373a7292db6483a1d"},"schema_version":"1.0"},"canonical_sha256":"2925dc857025f88f2c48e2e0189efdbe560031d9ddc0e93d8fc800cfea408bc0","source":{"kind":"arxiv","id":"1703.00565","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.00565","created_at":"2026-05-18T00:46:00Z"},{"alias_kind":"arxiv_version","alias_value":"1703.00565v3","created_at":"2026-05-18T00:46:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.00565","created_at":"2026-05-18T00:46:00Z"},{"alias_kind":"pith_short_12","alias_value":"FES5ZBLQEX4I","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"FES5ZBLQEX4I6LCI","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"FES5ZBLQ","created_at":"2026-05-18T12:31:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:FES5ZBLQEX4I6LCI4LQBRHX5XZ","target":"record","payload":{"canonical_record":{"source":{"id":"1703.00565","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-02T00:48:15Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"9431d1265fdc9813b636a15da95821513f70c38ec40aa6d9cc728ca858d6891c","abstract_canon_sha256":"5925235bc9fc8716a459be8dce7915272b84dbb5961c13d373a7292db6483a1d"},"schema_version":"1.0"},"canonical_sha256":"2925dc857025f88f2c48e2e0189efdbe560031d9ddc0e93d8fc800cfea408bc0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:00.268111Z","signature_b64":"5vFnW6XUdX1fqpZ2cFeeEj8la2KSlAt9tBat1BCG1EOOAujmsekAoJkLuvr5eBFrRUBkNKL1EQBQR/uQ6vNbBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2925dc857025f88f2c48e2e0189efdbe560031d9ddc0e93d8fc800cfea408bc0","last_reissued_at":"2026-05-18T00:46:00.267379Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:00.267379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.00565","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:46:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZBjm2rVhuo08wsRw1/pEBwCq9gzQXmjray+gqocoGp+1oLQQOIp86vF7c23h8Zu4rmXked+ya9kGpcVx6DmgDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T13:06:27.332437Z"},"content_sha256":"bd8bbc256dd5614e2259fa8714ba1a30afcd953482dd1693d9f2116184a8c4b1","schema_version":"1.0","event_id":"sha256:bd8bbc256dd5614e2259fa8714ba1a30afcd953482dd1693d9f2116184a8c4b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:FES5ZBLQEX4I6LCI4LQBRHX5XZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scattertext: a Browser-Based Tool for Visualizing how Corpora Differ","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Jason S. Kessler","submitted_at":"2017-03-02T00:48:15Z","abstract_excerpt":"Scattertext is an open source tool for visualizing linguistic variation between document categories in a language-independent way. The tool presents a scatterplot, where each axis corresponds to the rank-frequency a term occurs in a category of documents. Through a tie-breaking strategy, the tool is able to display thousands of visible term-representing points and find space to legibly label hundreds of them. Scattertext also lends itself to a query-based visualization of how the use of terms with similar embeddings differs between document categories, as well as a visualization for comparing "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.00565","kind":"arxiv","version":3},"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":"2026-05-18T00:46:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rspP4cVbYji4OxXREhNGVistCWXAKWgM2D3HB7Rc/QwuzBrKGeQ8GHRfeljJAXLU91YR5xWH6M4Z6fIRXjPEAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T13:06:27.332777Z"},"content_sha256":"35770145718f2ee142fb977adb772adc5fb6a4b53831bda3a1b044fe156f29e5","schema_version":"1.0","event_id":"sha256:35770145718f2ee142fb977adb772adc5fb6a4b53831bda3a1b044fe156f29e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FES5ZBLQEX4I6LCI4LQBRHX5XZ/bundle.json","state_url":"https://pith.science/pith/FES5ZBLQEX4I6LCI4LQBRHX5XZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FES5ZBLQEX4I6LCI4LQBRHX5XZ/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":"2026-06-29T13:06:27Z","links":{"resolver":"https://pith.science/pith/FES5ZBLQEX4I6LCI4LQBRHX5XZ","bundle":"https://pith.science/pith/FES5ZBLQEX4I6LCI4LQBRHX5XZ/bundle.json","state":"https://pith.science/pith/FES5ZBLQEX4I6LCI4LQBRHX5XZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FES5ZBLQEX4I6LCI4LQBRHX5XZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:FES5ZBLQEX4I6LCI4LQBRHX5XZ","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":"5925235bc9fc8716a459be8dce7915272b84dbb5961c13d373a7292db6483a1d","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-02T00:48:15Z","title_canon_sha256":"9431d1265fdc9813b636a15da95821513f70c38ec40aa6d9cc728ca858d6891c"},"schema_version":"1.0","source":{"id":"1703.00565","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.00565","created_at":"2026-05-18T00:46:00Z"},{"alias_kind":"arxiv_version","alias_value":"1703.00565v3","created_at":"2026-05-18T00:46:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.00565","created_at":"2026-05-18T00:46:00Z"},{"alias_kind":"pith_short_12","alias_value":"FES5ZBLQEX4I","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"FES5ZBLQEX4I6LCI","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"FES5ZBLQ","created_at":"2026-05-18T12:31:15Z"}],"graph_snapshots":[{"event_id":"sha256:35770145718f2ee142fb977adb772adc5fb6a4b53831bda3a1b044fe156f29e5","target":"graph","created_at":"2026-05-18T00:46:00Z","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":"Scattertext is an open source tool for visualizing linguistic variation between document categories in a language-independent way. The tool presents a scatterplot, where each axis corresponds to the rank-frequency a term occurs in a category of documents. Through a tie-breaking strategy, the tool is able to display thousands of visible term-representing points and find space to legibly label hundreds of them. Scattertext also lends itself to a query-based visualization of how the use of terms with similar embeddings differs between document categories, as well as a visualization for comparing ","authors_text":"Jason S. Kessler","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-02T00:48:15Z","title":"Scattertext: a Browser-Based Tool for Visualizing how Corpora Differ"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.00565","kind":"arxiv","version":3},"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:bd8bbc256dd5614e2259fa8714ba1a30afcd953482dd1693d9f2116184a8c4b1","target":"record","created_at":"2026-05-18T00:46:00Z","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":"5925235bc9fc8716a459be8dce7915272b84dbb5961c13d373a7292db6483a1d","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-02T00:48:15Z","title_canon_sha256":"9431d1265fdc9813b636a15da95821513f70c38ec40aa6d9cc728ca858d6891c"},"schema_version":"1.0","source":{"id":"1703.00565","kind":"arxiv","version":3}},"canonical_sha256":"2925dc857025f88f2c48e2e0189efdbe560031d9ddc0e93d8fc800cfea408bc0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2925dc857025f88f2c48e2e0189efdbe560031d9ddc0e93d8fc800cfea408bc0","first_computed_at":"2026-05-18T00:46:00.267379Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:46:00.267379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5vFnW6XUdX1fqpZ2cFeeEj8la2KSlAt9tBat1BCG1EOOAujmsekAoJkLuvr5eBFrRUBkNKL1EQBQR/uQ6vNbBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:46:00.268111Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.00565","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd8bbc256dd5614e2259fa8714ba1a30afcd953482dd1693d9f2116184a8c4b1","sha256:35770145718f2ee142fb977adb772adc5fb6a4b53831bda3a1b044fe156f29e5"],"state_sha256":"c6c799c799489e78e81abb9cd7f6108ce592a8905ba23f0db28c68ed96722819"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G6Q/scKOQS7LwHCwQHS9EajDXete0d+lAa9ISdA/YF58AMCFEFBYVjfPAeSUN4h8vKizPxZeg3YBsVShruLaCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T13:06:27.334595Z","bundle_sha256":"78308067e90108e4a65a212964ef77a1afa50c1ef4fe32c5238f4078310c6e36"}}