{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:TBXNLG7II3OIPJTNYBPZS4UV6J","short_pith_number":"pith:TBXNLG7I","canonical_record":{"source":{"id":"2109.04953","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-10T15:54:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ae519c968ef7f4378493f1e16c7040c677dc4ee549f5256cd49501496fe9a4a8","abstract_canon_sha256":"4e31cadf5e7c3a0fdb0d5c309fe9c68cbe85f51082257669c90d3ec1036e3bd7"},"schema_version":"1.0"},"canonical_sha256":"986ed59be846dc87a66dc05f997295f2589262bdba6d6ab67c5e704d94c74a54","source":{"kind":"arxiv","id":"2109.04953","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.04953","created_at":"2026-07-05T03:13:11Z"},{"alias_kind":"arxiv_version","alias_value":"2109.04953v1","created_at":"2026-07-05T03:13:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.04953","created_at":"2026-07-05T03:13:11Z"},{"alias_kind":"pith_short_12","alias_value":"TBXNLG7II3OI","created_at":"2026-07-05T03:13:11Z"},{"alias_kind":"pith_short_16","alias_value":"TBXNLG7II3OIPJTN","created_at":"2026-07-05T03:13:11Z"},{"alias_kind":"pith_short_8","alias_value":"TBXNLG7I","created_at":"2026-07-05T03:13:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:TBXNLG7II3OIPJTNYBPZS4UV6J","target":"record","payload":{"canonical_record":{"source":{"id":"2109.04953","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-10T15:54:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ae519c968ef7f4378493f1e16c7040c677dc4ee549f5256cd49501496fe9a4a8","abstract_canon_sha256":"4e31cadf5e7c3a0fdb0d5c309fe9c68cbe85f51082257669c90d3ec1036e3bd7"},"schema_version":"1.0"},"canonical_sha256":"986ed59be846dc87a66dc05f997295f2589262bdba6d6ab67c5e704d94c74a54","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:11.922747Z","signature_b64":"XTx4zaIxnBpXpjpBA2ykvERzlHsg3KKHbJQ0l1zKxzLHMDCYZj6zWBDd+kGoRJEsiPicV6uKebvhMX56N/j1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"986ed59be846dc87a66dc05f997295f2589262bdba6d6ab67c5e704d94c74a54","last_reissued_at":"2026-07-05T03:13:11.922351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:11.922351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.04953","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":"2026-07-05T03:13:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ongtKEBC2cvtwU1kTYGCuJOcEgksm88zKeR4hCnUBeAkWpqO9ZaMKZzvlFWpoT67x0h9UqfDybAe5aiqaUY0Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T08:47:53.253732Z"},"content_sha256":"e55674ca3f482fa4847f8874cf55be531a19ad0e43accd962e967793c92a5294","schema_version":"1.0","event_id":"sha256:e55674ca3f482fa4847f8874cf55be531a19ad0e43accd962e967793c92a5294"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:TBXNLG7II3OIPJTNYBPZS4UV6J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Does Pretraining for Summarization Require Knowledge Transfer?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jeffrey Bigham, Kundan Krishna, Zachary C. Lipton","submitted_at":"2021-09-10T15:54:15Z","abstract_excerpt":"Pretraining techniques leveraging enormous datasets have driven recent advances in text summarization. While folk explanations suggest that knowledge transfer accounts for pretraining's benefits, little is known about why it works or what makes a pretraining task or dataset suitable. In this paper, we challenge the knowledge transfer story, showing that pretraining on documents consisting of character n-grams selected at random, we can nearly match the performance of models pretrained on real corpora. This work holds the promise of eliminating upstream corpora, which may alleviate some concern"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.04953","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2109.04953/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T03:13:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Zv1IFcQU7mCvG6LNkATpyP8/WTFL6eqPkjbkLHVYhx3DTRFqpLdcrcilSYgeCFy5uI8rdwHBBxqt6Y7eiTbAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T08:47:53.254205Z"},"content_sha256":"4124491156c3a061bb70b2f5884c1e93c1292be2d21467d7ce410470b9b80058","schema_version":"1.0","event_id":"sha256:4124491156c3a061bb70b2f5884c1e93c1292be2d21467d7ce410470b9b80058"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TBXNLG7II3OIPJTNYBPZS4UV6J/bundle.json","state_url":"https://pith.science/pith/TBXNLG7II3OIPJTNYBPZS4UV6J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TBXNLG7II3OIPJTNYBPZS4UV6J/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":"2026-08-15T08:47:53Z","links":{"resolver":"https://pith.science/pith/TBXNLG7II3OIPJTNYBPZS4UV6J","bundle":"https://pith.science/pith/TBXNLG7II3OIPJTNYBPZS4UV6J/bundle.json","state":"https://pith.science/pith/TBXNLG7II3OIPJTNYBPZS4UV6J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TBXNLG7II3OIPJTNYBPZS4UV6J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TBXNLG7II3OIPJTNYBPZS4UV6J","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":"4e31cadf5e7c3a0fdb0d5c309fe9c68cbe85f51082257669c90d3ec1036e3bd7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-10T15:54:15Z","title_canon_sha256":"ae519c968ef7f4378493f1e16c7040c677dc4ee549f5256cd49501496fe9a4a8"},"schema_version":"1.0","source":{"id":"2109.04953","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.04953","created_at":"2026-07-05T03:13:11Z"},{"alias_kind":"arxiv_version","alias_value":"2109.04953v1","created_at":"2026-07-05T03:13:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.04953","created_at":"2026-07-05T03:13:11Z"},{"alias_kind":"pith_short_12","alias_value":"TBXNLG7II3OI","created_at":"2026-07-05T03:13:11Z"},{"alias_kind":"pith_short_16","alias_value":"TBXNLG7II3OIPJTN","created_at":"2026-07-05T03:13:11Z"},{"alias_kind":"pith_short_8","alias_value":"TBXNLG7I","created_at":"2026-07-05T03:13:11Z"}],"graph_snapshots":[{"event_id":"sha256:4124491156c3a061bb70b2f5884c1e93c1292be2d21467d7ce410470b9b80058","target":"graph","created_at":"2026-07-05T03:13:11Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2109.04953/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretraining techniques leveraging enormous datasets have driven recent advances in text summarization. While folk explanations suggest that knowledge transfer accounts for pretraining's benefits, little is known about why it works or what makes a pretraining task or dataset suitable. In this paper, we challenge the knowledge transfer story, showing that pretraining on documents consisting of character n-grams selected at random, we can nearly match the performance of models pretrained on real corpora. This work holds the promise of eliminating upstream corpora, which may alleviate some concern","authors_text":"Jeffrey Bigham, Kundan Krishna, Zachary C. Lipton","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-10T15:54:15Z","title":"Does Pretraining for Summarization Require Knowledge Transfer?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.04953","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:e55674ca3f482fa4847f8874cf55be531a19ad0e43accd962e967793c92a5294","target":"record","created_at":"2026-07-05T03:13:11Z","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":"4e31cadf5e7c3a0fdb0d5c309fe9c68cbe85f51082257669c90d3ec1036e3bd7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-10T15:54:15Z","title_canon_sha256":"ae519c968ef7f4378493f1e16c7040c677dc4ee549f5256cd49501496fe9a4a8"},"schema_version":"1.0","source":{"id":"2109.04953","kind":"arxiv","version":1}},"canonical_sha256":"986ed59be846dc87a66dc05f997295f2589262bdba6d6ab67c5e704d94c74a54","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"986ed59be846dc87a66dc05f997295f2589262bdba6d6ab67c5e704d94c74a54","first_computed_at":"2026-07-05T03:13:11.922351Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:13:11.922351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XTx4zaIxnBpXpjpBA2ykvERzlHsg3KKHbJQ0l1zKxzLHMDCYZj6zWBDd+kGoRJEsiPicV6uKebvhMX56N/j1DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:13:11.922747Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.04953","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e55674ca3f482fa4847f8874cf55be531a19ad0e43accd962e967793c92a5294","sha256:4124491156c3a061bb70b2f5884c1e93c1292be2d21467d7ce410470b9b80058"],"state_sha256":"45a8f6fa79bb0ad8c48a8ab7d18e92ffc60095bcbc25b59c9f2f895bd6cc762a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fzxXTlrTNCeeJPQF0IIbIjjkpjq2CmD/mht6IphWyaCZ20YazQ6dxJpVcDGEp1RXGJZM8CS6lOyx3pgADb0ABQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T08:47:53.258490Z","bundle_sha256":"6e58440ff78c93877fc1b106081299e00141d66bfe76633dc60869b42fa5a6db"}}