{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:DKO6Z3STPEUH52R3WWDUBTZHLZ","short_pith_number":"pith:DKO6Z3ST","canonical_record":{"source":{"id":"1503.05543","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-03-18T19:44:06Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"4209602a0929a67e6f4faca02e82cba618c32c84fb9ed9ac70419467ae35b359","abstract_canon_sha256":"fd267b19d27e74fd752289c721bc1fedd461f93330425ab45934045d9a64ef0c"},"schema_version":"1.0"},"canonical_sha256":"1a9decee5379287eea3bb58740cf275e7733a90110f7c6ab1ab0eedb1bcf0489","source":{"kind":"arxiv","id":"1503.05543","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1503.05543","created_at":"2026-05-18T02:21:26Z"},{"alias_kind":"arxiv_version","alias_value":"1503.05543v1","created_at":"2026-05-18T02:21:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.05543","created_at":"2026-05-18T02:21:26Z"},{"alias_kind":"pith_short_12","alias_value":"DKO6Z3STPEUH","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_16","alias_value":"DKO6Z3STPEUH52R3","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_8","alias_value":"DKO6Z3ST","created_at":"2026-05-18T12:29:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:DKO6Z3STPEUH52R3WWDUBTZHLZ","target":"record","payload":{"canonical_record":{"source":{"id":"1503.05543","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-03-18T19:44:06Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"4209602a0929a67e6f4faca02e82cba618c32c84fb9ed9ac70419467ae35b359","abstract_canon_sha256":"fd267b19d27e74fd752289c721bc1fedd461f93330425ab45934045d9a64ef0c"},"schema_version":"1.0"},"canonical_sha256":"1a9decee5379287eea3bb58740cf275e7733a90110f7c6ab1ab0eedb1bcf0489","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:21:26.116794Z","signature_b64":"s+F7ByZ0zD0TJKIwlA16vvR4ueGl81rJSzLhXb+5l6GOviAse/o4/o3F7FnO1KyTny8tdq+oN3T1YJL06FUyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a9decee5379287eea3bb58740cf275e7733a90110f7c6ab1ab0eedb1bcf0489","last_reissued_at":"2026-05-18T02:21:26.116212Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:21:26.116212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1503.05543","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":"2026-05-18T02:21:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tqb9MoJ1fmeeYovxBQMuHPSQkfmyQjA1d/0Keq2gQUTifM/3gzkvcxTlcIv3Si7Cf9cFlg86z2K3cXTCXnFLDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T15:40:54.782850Z"},"content_sha256":"45ac12721e5285cc7e793ef956e24fad2d8471bfc51189d78f3fb97279512c84","schema_version":"1.0","event_id":"sha256:45ac12721e5285cc7e793ef956e24fad2d8471bfc51189d78f3fb97279512c84"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:DKO6Z3STPEUH52R3WWDUBTZHLZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text Segmentation based on Semantic Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Alexander A Alemi, Paul Ginsparg","submitted_at":"2015-03-18T19:44:06Z","abstract_excerpt":"We explore the use of semantic word embeddings in text segmentation algorithms, including the C99 segmentation algorithm and new algorithms inspired by the distributed word vector representation. By developing a general framework for discussing a class of segmentation objectives, we study the effectiveness of greedy versus exact optimization approaches and suggest a new iterative refinement technique for improving the performance of greedy strategies. We compare our results to known benchmarks, using known metrics. We demonstrate state-of-the-art performance for an untrained method with our Co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.05543","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":"2026-05-18T02:21:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PzdsYJ8v30oB0Mj3PlhEsr39dwseNVlRr32j+Wx52bQV3LL492lNow9NG7v/j4MHVvxoaIaSE+bjhEiXqd2uBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T15:40:54.783565Z"},"content_sha256":"5355716211c63f1e8509b0179fe6573b35647e71a7a4190b8e0d8b1f694cb35f","schema_version":"1.0","event_id":"sha256:5355716211c63f1e8509b0179fe6573b35647e71a7a4190b8e0d8b1f694cb35f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DKO6Z3STPEUH52R3WWDUBTZHLZ/bundle.json","state_url":"https://pith.science/pith/DKO6Z3STPEUH52R3WWDUBTZHLZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DKO6Z3STPEUH52R3WWDUBTZHLZ/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":"2026-05-30T15:40:54Z","links":{"resolver":"https://pith.science/pith/DKO6Z3STPEUH52R3WWDUBTZHLZ","bundle":"https://pith.science/pith/DKO6Z3STPEUH52R3WWDUBTZHLZ/bundle.json","state":"https://pith.science/pith/DKO6Z3STPEUH52R3WWDUBTZHLZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DKO6Z3STPEUH52R3WWDUBTZHLZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:DKO6Z3STPEUH52R3WWDUBTZHLZ","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":"fd267b19d27e74fd752289c721bc1fedd461f93330425ab45934045d9a64ef0c","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-03-18T19:44:06Z","title_canon_sha256":"4209602a0929a67e6f4faca02e82cba618c32c84fb9ed9ac70419467ae35b359"},"schema_version":"1.0","source":{"id":"1503.05543","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1503.05543","created_at":"2026-05-18T02:21:26Z"},{"alias_kind":"arxiv_version","alias_value":"1503.05543v1","created_at":"2026-05-18T02:21:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.05543","created_at":"2026-05-18T02:21:26Z"},{"alias_kind":"pith_short_12","alias_value":"DKO6Z3STPEUH","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_16","alias_value":"DKO6Z3STPEUH52R3","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_8","alias_value":"DKO6Z3ST","created_at":"2026-05-18T12:29:17Z"}],"graph_snapshots":[{"event_id":"sha256:5355716211c63f1e8509b0179fe6573b35647e71a7a4190b8e0d8b1f694cb35f","target":"graph","created_at":"2026-05-18T02:21:26Z","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":"We explore the use of semantic word embeddings in text segmentation algorithms, including the C99 segmentation algorithm and new algorithms inspired by the distributed word vector representation. By developing a general framework for discussing a class of segmentation objectives, we study the effectiveness of greedy versus exact optimization approaches and suggest a new iterative refinement technique for improving the performance of greedy strategies. We compare our results to known benchmarks, using known metrics. We demonstrate state-of-the-art performance for an untrained method with our Co","authors_text":"Alexander A Alemi, Paul Ginsparg","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-03-18T19:44:06Z","title":"Text Segmentation based on Semantic Word Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.05543","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":"sha256:45ac12721e5285cc7e793ef956e24fad2d8471bfc51189d78f3fb97279512c84","target":"record","created_at":"2026-05-18T02:21:26Z","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":"fd267b19d27e74fd752289c721bc1fedd461f93330425ab45934045d9a64ef0c","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-03-18T19:44:06Z","title_canon_sha256":"4209602a0929a67e6f4faca02e82cba618c32c84fb9ed9ac70419467ae35b359"},"schema_version":"1.0","source":{"id":"1503.05543","kind":"arxiv","version":1}},"canonical_sha256":"1a9decee5379287eea3bb58740cf275e7733a90110f7c6ab1ab0eedb1bcf0489","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a9decee5379287eea3bb58740cf275e7733a90110f7c6ab1ab0eedb1bcf0489","first_computed_at":"2026-05-18T02:21:26.116212Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:21:26.116212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s+F7ByZ0zD0TJKIwlA16vvR4ueGl81rJSzLhXb+5l6GOviAse/o4/o3F7FnO1KyTny8tdq+oN3T1YJL06FUyDw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:21:26.116794Z","signed_message":"canonical_sha256_bytes"},"source_id":"1503.05543","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:45ac12721e5285cc7e793ef956e24fad2d8471bfc51189d78f3fb97279512c84","sha256:5355716211c63f1e8509b0179fe6573b35647e71a7a4190b8e0d8b1f694cb35f"],"state_sha256":"7fb4b72fc6b821a626e3c059f481db4e004d5b73f8f744787a1e5fc528860ce7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h3hdWhIuzIBAz2jRURcA+qyGVchY1/S7qwZi5jpuVpm0i2/jK0KRSlaYmSi9KxEgJNXmsYYVY2azofBFMxBPCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T15:40:54.787373Z","bundle_sha256":"d34b0ce07ac8ca4223c615f32a542e0bd4f7fa3d9d9dcd8d549803eb99e23b6e"}}