{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:FWXJA7Y2JJEUZHIJGFUJLE3O3Q","short_pith_number":"pith:FWXJA7Y2","canonical_record":{"source":{"id":"1404.7362","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-04-29T13:53:38Z","cross_cats_sorted":["stat.AP"],"title_canon_sha256":"16a4dad07af5ca06843c4305753ed469ee1f37fa4cde22a7989c78cd0d25dad2","abstract_canon_sha256":"15c08c4b342717a948972ad25918af57b48d380cf22c5760402bf3b8482a875e"},"schema_version":"1.0"},"canonical_sha256":"2dae907f1a4a494c9d09316895936edc386a6ebf89f2e603d4561e0c25c769b4","source":{"kind":"arxiv","id":"1404.7362","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1404.7362","created_at":"2026-05-18T02:52:56Z"},{"alias_kind":"arxiv_version","alias_value":"1404.7362v1","created_at":"2026-05-18T02:52:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1404.7362","created_at":"2026-05-18T02:52:56Z"},{"alias_kind":"pith_short_12","alias_value":"FWXJA7Y2JJEU","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"FWXJA7Y2JJEUZHIJ","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"FWXJA7Y2","created_at":"2026-05-18T12:28:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:FWXJA7Y2JJEUZHIJGFUJLE3O3Q","target":"record","payload":{"canonical_record":{"source":{"id":"1404.7362","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-04-29T13:53:38Z","cross_cats_sorted":["stat.AP"],"title_canon_sha256":"16a4dad07af5ca06843c4305753ed469ee1f37fa4cde22a7989c78cd0d25dad2","abstract_canon_sha256":"15c08c4b342717a948972ad25918af57b48d380cf22c5760402bf3b8482a875e"},"schema_version":"1.0"},"canonical_sha256":"2dae907f1a4a494c9d09316895936edc386a6ebf89f2e603d4561e0c25c769b4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:52:56.772491Z","signature_b64":"XXcXnt+KgOAnXRKe0Xj6SabfdvhaHSdvVdLX7PnhZlcuTnxzj3tlil/Bk/ULQrLlsWgPCZSb32PuN36SQN6gAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2dae907f1a4a494c9d09316895936edc386a6ebf89f2e603d4561e0c25c769b4","last_reissued_at":"2026-05-18T02:52:56.771732Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:52:56.771732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1404.7362","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":"2026-05-18T02:52:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5pObsW09h2TP+5/wJbrHMn+/Tx1cPZaIp6BjDvS3FVOcKEiSkTxtwJp4DEw8gygUmviy1nhDgxlD39lFjTe9Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T03:00:00.510782Z"},"content_sha256":"03565d70218671db6b5b345191ddeff5116e0eb7b1e2f3b5ec486c5732560050","schema_version":"1.0","event_id":"sha256:03565d70218671db6b5b345191ddeff5116e0eb7b1e2f3b5ec486c5732560050"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:FWXJA7Y2JJEUZHIJGFUJLE3O3Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Concise comparative summaries (CCS) of large text corpora with a human experiment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP"],"primary_cat":"cs.CL","authors_text":"Bin Yu, Brian Gawalt, Jinzhu Jia, Laurent El Ghaoui, Luke Barnesmoore, Luke Miratrix, Sophie Clavier","submitted_at":"2014-04-29T13:53:38Z","abstract_excerpt":"In this paper we propose a general framework for topic-specific summarization of large text corpora and illustrate how it can be used for the analysis of news databases. Our framework, concise comparative summarization (CCS), is built on sparse classification methods. CCS is a lightweight and flexible tool that offers a compromise between simple word frequency based methods currently in wide use and more heavyweight, model-intensive methods such as latent Dirichlet allocation (LDA). We argue that sparse methods have much to offer for text analysis and hope CCS opens the door for a new branch o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1404.7362","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":"2026-05-18T02:52:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p2Nsk6kFCaI3n9bH0PWUsgQZji9OCkpw8chTp6r+/LwtXij47TyARYGuYG7xstVt1L3JUW3Y1q+h9hS+njjuBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T03:00:00.511518Z"},"content_sha256":"663a3b54a8d98978ddad1dfbe83b487de23a94a4b2e7d9e95cc991c56d4ab0d6","schema_version":"1.0","event_id":"sha256:663a3b54a8d98978ddad1dfbe83b487de23a94a4b2e7d9e95cc991c56d4ab0d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FWXJA7Y2JJEUZHIJGFUJLE3O3Q/bundle.json","state_url":"https://pith.science/pith/FWXJA7Y2JJEUZHIJGFUJLE3O3Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FWXJA7Y2JJEUZHIJGFUJLE3O3Q/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":"2026-06-08T03:00:00Z","links":{"resolver":"https://pith.science/pith/FWXJA7Y2JJEUZHIJGFUJLE3O3Q","bundle":"https://pith.science/pith/FWXJA7Y2JJEUZHIJGFUJLE3O3Q/bundle.json","state":"https://pith.science/pith/FWXJA7Y2JJEUZHIJGFUJLE3O3Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FWXJA7Y2JJEUZHIJGFUJLE3O3Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:FWXJA7Y2JJEUZHIJGFUJLE3O3Q","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":"15c08c4b342717a948972ad25918af57b48d380cf22c5760402bf3b8482a875e","cross_cats_sorted":["stat.AP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-04-29T13:53:38Z","title_canon_sha256":"16a4dad07af5ca06843c4305753ed469ee1f37fa4cde22a7989c78cd0d25dad2"},"schema_version":"1.0","source":{"id":"1404.7362","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1404.7362","created_at":"2026-05-18T02:52:56Z"},{"alias_kind":"arxiv_version","alias_value":"1404.7362v1","created_at":"2026-05-18T02:52:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1404.7362","created_at":"2026-05-18T02:52:56Z"},{"alias_kind":"pith_short_12","alias_value":"FWXJA7Y2JJEU","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"FWXJA7Y2JJEUZHIJ","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"FWXJA7Y2","created_at":"2026-05-18T12:28:28Z"}],"graph_snapshots":[{"event_id":"sha256:663a3b54a8d98978ddad1dfbe83b487de23a94a4b2e7d9e95cc991c56d4ab0d6","target":"graph","created_at":"2026-05-18T02:52:56Z","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":"In this paper we propose a general framework for topic-specific summarization of large text corpora and illustrate how it can be used for the analysis of news databases. Our framework, concise comparative summarization (CCS), is built on sparse classification methods. CCS is a lightweight and flexible tool that offers a compromise between simple word frequency based methods currently in wide use and more heavyweight, model-intensive methods such as latent Dirichlet allocation (LDA). We argue that sparse methods have much to offer for text analysis and hope CCS opens the door for a new branch o","authors_text":"Bin Yu, Brian Gawalt, Jinzhu Jia, Laurent El Ghaoui, Luke Barnesmoore, Luke Miratrix, Sophie Clavier","cross_cats":["stat.AP"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-04-29T13:53:38Z","title":"Concise comparative summaries (CCS) of large text corpora with a human experiment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1404.7362","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":"sha256:03565d70218671db6b5b345191ddeff5116e0eb7b1e2f3b5ec486c5732560050","target":"record","created_at":"2026-05-18T02:52:56Z","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":"15c08c4b342717a948972ad25918af57b48d380cf22c5760402bf3b8482a875e","cross_cats_sorted":["stat.AP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-04-29T13:53:38Z","title_canon_sha256":"16a4dad07af5ca06843c4305753ed469ee1f37fa4cde22a7989c78cd0d25dad2"},"schema_version":"1.0","source":{"id":"1404.7362","kind":"arxiv","version":1}},"canonical_sha256":"2dae907f1a4a494c9d09316895936edc386a6ebf89f2e603d4561e0c25c769b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2dae907f1a4a494c9d09316895936edc386a6ebf89f2e603d4561e0c25c769b4","first_computed_at":"2026-05-18T02:52:56.771732Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:52:56.771732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XXcXnt+KgOAnXRKe0Xj6SabfdvhaHSdvVdLX7PnhZlcuTnxzj3tlil/Bk/ULQrLlsWgPCZSb32PuN36SQN6gAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:52:56.772491Z","signed_message":"canonical_sha256_bytes"},"source_id":"1404.7362","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03565d70218671db6b5b345191ddeff5116e0eb7b1e2f3b5ec486c5732560050","sha256:663a3b54a8d98978ddad1dfbe83b487de23a94a4b2e7d9e95cc991c56d4ab0d6"],"state_sha256":"4ade5fb6848874963d2e1e115a55a83737ec13311806c1d720575125a390b5e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wDZyaprlKAG3aWLoQgWIVzFAzZzVdGQjyOt775+0RAWeNV2C92bNz3lp/JLm5+LiYeaZS85JxS+6u+mnWsjwAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T03:00:00.515469Z","bundle_sha256":"abda295ab5a90629caa782706c0e4f5a6183e48be074a0ce43fd98312ed0b069"}}