{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:XP27INWXI36Q5TRIU4ENDBT5EW","short_pith_number":"pith:XP27INWX","canonical_record":{"source":{"id":"2109.02575","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-06T16:20:47Z","cross_cats_sorted":[],"title_canon_sha256":"092bba4d0f43e0978f6a50681463453b74d73a67430833fc5aa02588d4fcdea3","abstract_canon_sha256":"fec5938346993c968cc7c505180fd7025c63c74a78919d00bc66f209251c7698"},"schema_version":"1.0"},"canonical_sha256":"bbf5f436d746fd0ece28a708d1867d25a2a03ed78333a360454a4801c3ed94f8","source":{"kind":"arxiv","id":"2109.02575","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.02575","created_at":"2026-07-05T03:11:49Z"},{"alias_kind":"arxiv_version","alias_value":"2109.02575v1","created_at":"2026-07-05T03:11:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.02575","created_at":"2026-07-05T03:11:49Z"},{"alias_kind":"pith_short_12","alias_value":"XP27INWXI36Q","created_at":"2026-07-05T03:11:49Z"},{"alias_kind":"pith_short_16","alias_value":"XP27INWXI36Q5TRI","created_at":"2026-07-05T03:11:49Z"},{"alias_kind":"pith_short_8","alias_value":"XP27INWX","created_at":"2026-07-05T03:11:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:XP27INWXI36Q5TRIU4ENDBT5EW","target":"record","payload":{"canonical_record":{"source":{"id":"2109.02575","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-06T16:20:47Z","cross_cats_sorted":[],"title_canon_sha256":"092bba4d0f43e0978f6a50681463453b74d73a67430833fc5aa02588d4fcdea3","abstract_canon_sha256":"fec5938346993c968cc7c505180fd7025c63c74a78919d00bc66f209251c7698"},"schema_version":"1.0"},"canonical_sha256":"bbf5f436d746fd0ece28a708d1867d25a2a03ed78333a360454a4801c3ed94f8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:11:49.963445Z","signature_b64":"KHtv2lfoHRwklDPIvIZwQt4Vb256YFMXGlwW19Au/kWNhm0Tt6yi3G1rkL1FBkA6sBHDjvzLCSD3DsphnD1LBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbf5f436d746fd0ece28a708d1867d25a2a03ed78333a360454a4801c3ed94f8","last_reissued_at":"2026-07-05T03:11:49.963059Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:11:49.963059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.02575","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":"2026-07-05T03:11:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bcw2tsxQ7TeM8pWnLB+lG/J89dWuAyg1yhDhfeNaBNgw7Jn1ZatzlEe7lVCF2Orvz4Miw7434ca3YoNUSSLjCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:57:29.769492Z"},"content_sha256":"97136143209e447d6041226b9121de8cddd2b6f5d71a45ab0fb62a934fe5a6f8","schema_version":"1.0","event_id":"sha256:97136143209e447d6041226b9121de8cddd2b6f5d71a45ab0fb62a934fe5a6f8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:XP27INWXI36Q5TRIU4ENDBT5EW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Finding needles in a haystack: Sampling Structurally-diverse Training Sets from Synthetic Data for Compositional Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Inbar Oren, Jonathan Berant, Jonathan Herzig","submitted_at":"2021-09-06T16:20:47Z","abstract_excerpt":"Modern semantic parsers suffer from two principal limitations. First, training requires expensive collection of utterance-program pairs. Second, semantic parsers fail to generalize at test time to new compositions/structures that have not been observed during training. Recent research has shown that automatic generation of synthetic utterance-program pairs can alleviate the first problem, but its potential for the second has thus far been under-explored. In this work, we investigate automatic generation of synthetic utterance-program pairs for improving compositional generalization in semantic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.02575","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/2109.02575/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":"2026-07-05T03:11:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YRiJ0bLtYV6ED2cyhdLs6YH8omMYzacHGKq7N1mdOnHqIUUpDOGN2+Zdvcvgclm6tIKmlIwkgQSLI5P5hF+sAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:57:29.770067Z"},"content_sha256":"cbb094c45a906b8673ad652b802b4b8690d4c81340445bbc9a6c651b74cebea0","schema_version":"1.0","event_id":"sha256:cbb094c45a906b8673ad652b802b4b8690d4c81340445bbc9a6c651b74cebea0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XP27INWXI36Q5TRIU4ENDBT5EW/bundle.json","state_url":"https://pith.science/pith/XP27INWXI36Q5TRIU4ENDBT5EW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XP27INWXI36Q5TRIU4ENDBT5EW/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":"2026-08-05T09:57:29Z","links":{"resolver":"https://pith.science/pith/XP27INWXI36Q5TRIU4ENDBT5EW","bundle":"https://pith.science/pith/XP27INWXI36Q5TRIU4ENDBT5EW/bundle.json","state":"https://pith.science/pith/XP27INWXI36Q5TRIU4ENDBT5EW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XP27INWXI36Q5TRIU4ENDBT5EW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:XP27INWXI36Q5TRIU4ENDBT5EW","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":"fec5938346993c968cc7c505180fd7025c63c74a78919d00bc66f209251c7698","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-06T16:20:47Z","title_canon_sha256":"092bba4d0f43e0978f6a50681463453b74d73a67430833fc5aa02588d4fcdea3"},"schema_version":"1.0","source":{"id":"2109.02575","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.02575","created_at":"2026-07-05T03:11:49Z"},{"alias_kind":"arxiv_version","alias_value":"2109.02575v1","created_at":"2026-07-05T03:11:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.02575","created_at":"2026-07-05T03:11:49Z"},{"alias_kind":"pith_short_12","alias_value":"XP27INWXI36Q","created_at":"2026-07-05T03:11:49Z"},{"alias_kind":"pith_short_16","alias_value":"XP27INWXI36Q5TRI","created_at":"2026-07-05T03:11:49Z"},{"alias_kind":"pith_short_8","alias_value":"XP27INWX","created_at":"2026-07-05T03:11:49Z"}],"graph_snapshots":[{"event_id":"sha256:cbb094c45a906b8673ad652b802b4b8690d4c81340445bbc9a6c651b74cebea0","target":"graph","created_at":"2026-07-05T03:11:49Z","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/2109.02575/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern semantic parsers suffer from two principal limitations. First, training requires expensive collection of utterance-program pairs. Second, semantic parsers fail to generalize at test time to new compositions/structures that have not been observed during training. Recent research has shown that automatic generation of synthetic utterance-program pairs can alleviate the first problem, but its potential for the second has thus far been under-explored. In this work, we investigate automatic generation of synthetic utterance-program pairs for improving compositional generalization in semantic","authors_text":"Inbar Oren, Jonathan Berant, Jonathan Herzig","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-06T16:20:47Z","title":"Finding needles in a haystack: Sampling Structurally-diverse Training Sets from Synthetic Data for Compositional Generalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.02575","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":"sha256:97136143209e447d6041226b9121de8cddd2b6f5d71a45ab0fb62a934fe5a6f8","target":"record","created_at":"2026-07-05T03:11:49Z","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":"fec5938346993c968cc7c505180fd7025c63c74a78919d00bc66f209251c7698","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-06T16:20:47Z","title_canon_sha256":"092bba4d0f43e0978f6a50681463453b74d73a67430833fc5aa02588d4fcdea3"},"schema_version":"1.0","source":{"id":"2109.02575","kind":"arxiv","version":1}},"canonical_sha256":"bbf5f436d746fd0ece28a708d1867d25a2a03ed78333a360454a4801c3ed94f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbf5f436d746fd0ece28a708d1867d25a2a03ed78333a360454a4801c3ed94f8","first_computed_at":"2026-07-05T03:11:49.963059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:11:49.963059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KHtv2lfoHRwklDPIvIZwQt4Vb256YFMXGlwW19Au/kWNhm0Tt6yi3G1rkL1FBkA6sBHDjvzLCSD3DsphnD1LBg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:11:49.963445Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.02575","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97136143209e447d6041226b9121de8cddd2b6f5d71a45ab0fb62a934fe5a6f8","sha256:cbb094c45a906b8673ad652b802b4b8690d4c81340445bbc9a6c651b74cebea0"],"state_sha256":"703ba2dcb1e0eacedce17149ad1dfa9cc2f17d62b959e1cd4710cc266357babb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IcjcmcMO4pqDCZxsJY4XHSeBFryCwTKwUNLynigbk9OOIOwllTuian0Vky8kRYsxuvXsnkNNy/EtbXa3fg9AAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T09:57:29.773791Z","bundle_sha256":"88cb69f75652898d4ee6a5bae871bfa2f8569313cd53e61efd9fd8b44a610212"}}