{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:M3WCMPQP44D7YAELGA3AOZ4JYE","short_pith_number":"pith:M3WCMPQP","canonical_record":{"source":{"id":"2103.12778","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2021-03-23T18:23:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"44590c46b1aeb2399ecdae896d2be3bb0aa67a2163e9071e09c34906bb13306c","abstract_canon_sha256":"6a20433688bc54a8dfcb87cd30f7c63eecca9f1bd45c38538aad73ffa59dd325"},"schema_version":"1.0"},"canonical_sha256":"66ec263e0fe707fc008b3036076789c10df0402c736185cdc5050d6677d592e8","source":{"kind":"arxiv","id":"2103.12778","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.12778","created_at":"2026-07-05T02:25:51Z"},{"alias_kind":"arxiv_version","alias_value":"2103.12778v1","created_at":"2026-07-05T02:25:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.12778","created_at":"2026-07-05T02:25:51Z"},{"alias_kind":"pith_short_12","alias_value":"M3WCMPQP44D7","created_at":"2026-07-05T02:25:51Z"},{"alias_kind":"pith_short_16","alias_value":"M3WCMPQP44D7YAEL","created_at":"2026-07-05T02:25:51Z"},{"alias_kind":"pith_short_8","alias_value":"M3WCMPQP","created_at":"2026-07-05T02:25:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:M3WCMPQP44D7YAELGA3AOZ4JYE","target":"record","payload":{"canonical_record":{"source":{"id":"2103.12778","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2021-03-23T18:23:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"44590c46b1aeb2399ecdae896d2be3bb0aa67a2163e9071e09c34906bb13306c","abstract_canon_sha256":"6a20433688bc54a8dfcb87cd30f7c63eecca9f1bd45c38538aad73ffa59dd325"},"schema_version":"1.0"},"canonical_sha256":"66ec263e0fe707fc008b3036076789c10df0402c736185cdc5050d6677d592e8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:25:51.672496Z","signature_b64":"SbKRZzKWhtawG+0bd2IN5l0g6UJw9DZwb8fFh99rdoyE+PhotyZ4/gih5j26et6lc4CXZmLUTzec4ESGe16wCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66ec263e0fe707fc008b3036076789c10df0402c736185cdc5050d6677d592e8","last_reissued_at":"2026-07-05T02:25:51.672036Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:25:51.672036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.12778","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":"2026-07-05T02:25:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eLLFI1AF1rceiB68He6+9ONpbjnGncRE/E7dH0iwy+CPmi/jEWoGYNw3NytYVp/17mFIoo+6RMYrQlYsh7CBDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:06:43.345271Z"},"content_sha256":"282ca5ced92a6f30c87f411d0e756c46b92a639c8fe6b442ae079d855d35b846","schema_version":"1.0","event_id":"sha256:282ca5ced92a6f30c87f411d0e756c46b92a639c8fe6b442ae079d855d35b846"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:M3WCMPQP44D7YAELGA3AOZ4JYE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PSIMiner: A Tool for Mining Rich Abstract Syntax Trees from Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Egor Bogomolov, Egor Spirin, Timofey Bryksin, Vladimir Kovalenko","submitted_at":"2021-03-23T18:23:45Z","abstract_excerpt":"The application of machine learning algorithms to source code has grown in the past years. Since these algorithms are quite sensitive to input data, it is not surprising that researchers experiment with input representations. Nowadays, a popular starting point to represent code is abstract syntax trees (ASTs). Abstract syntax trees have been used for a long time in various software engineering domains, and in particular in IDEs. The API of modern IDEs allows to manipulate and traverse ASTs, resolve references between code elements, etc. Such algorithms can enrich ASTs with new data and therefo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.12778","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/2103.12778/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":"2026-07-05T02:25:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kQuDPsDJxKdWRkXmb5TeS5zVk36I1n71MWCrYaDd2TdBWSWeQMvMPMSz9a3lw3glzFmZN+CRdZFJyrupw8CmAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:06:43.346633Z"},"content_sha256":"8911b25e4d7e43721c92cd3e051d68a2e699b86e218112555c3d3bc3da3e13c5","schema_version":"1.0","event_id":"sha256:8911b25e4d7e43721c92cd3e051d68a2e699b86e218112555c3d3bc3da3e13c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M3WCMPQP44D7YAELGA3AOZ4JYE/bundle.json","state_url":"https://pith.science/pith/M3WCMPQP44D7YAELGA3AOZ4JYE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M3WCMPQP44D7YAELGA3AOZ4JYE/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":"2026-08-03T21:06:43Z","links":{"resolver":"https://pith.science/pith/M3WCMPQP44D7YAELGA3AOZ4JYE","bundle":"https://pith.science/pith/M3WCMPQP44D7YAELGA3AOZ4JYE/bundle.json","state":"https://pith.science/pith/M3WCMPQP44D7YAELGA3AOZ4JYE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M3WCMPQP44D7YAELGA3AOZ4JYE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:M3WCMPQP44D7YAELGA3AOZ4JYE","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":"6a20433688bc54a8dfcb87cd30f7c63eecca9f1bd45c38538aad73ffa59dd325","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2021-03-23T18:23:45Z","title_canon_sha256":"44590c46b1aeb2399ecdae896d2be3bb0aa67a2163e9071e09c34906bb13306c"},"schema_version":"1.0","source":{"id":"2103.12778","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.12778","created_at":"2026-07-05T02:25:51Z"},{"alias_kind":"arxiv_version","alias_value":"2103.12778v1","created_at":"2026-07-05T02:25:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.12778","created_at":"2026-07-05T02:25:51Z"},{"alias_kind":"pith_short_12","alias_value":"M3WCMPQP44D7","created_at":"2026-07-05T02:25:51Z"},{"alias_kind":"pith_short_16","alias_value":"M3WCMPQP44D7YAEL","created_at":"2026-07-05T02:25:51Z"},{"alias_kind":"pith_short_8","alias_value":"M3WCMPQP","created_at":"2026-07-05T02:25:51Z"}],"graph_snapshots":[{"event_id":"sha256:8911b25e4d7e43721c92cd3e051d68a2e699b86e218112555c3d3bc3da3e13c5","target":"graph","created_at":"2026-07-05T02:25:51Z","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/2103.12778/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The application of machine learning algorithms to source code has grown in the past years. Since these algorithms are quite sensitive to input data, it is not surprising that researchers experiment with input representations. Nowadays, a popular starting point to represent code is abstract syntax trees (ASTs). Abstract syntax trees have been used for a long time in various software engineering domains, and in particular in IDEs. The API of modern IDEs allows to manipulate and traverse ASTs, resolve references between code elements, etc. Such algorithms can enrich ASTs with new data and therefo","authors_text":"Egor Bogomolov, Egor Spirin, Timofey Bryksin, Vladimir Kovalenko","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2021-03-23T18:23:45Z","title":"PSIMiner: A Tool for Mining Rich Abstract Syntax Trees from Code"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.12778","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":"sha256:282ca5ced92a6f30c87f411d0e756c46b92a639c8fe6b442ae079d855d35b846","target":"record","created_at":"2026-07-05T02:25:51Z","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":"6a20433688bc54a8dfcb87cd30f7c63eecca9f1bd45c38538aad73ffa59dd325","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2021-03-23T18:23:45Z","title_canon_sha256":"44590c46b1aeb2399ecdae896d2be3bb0aa67a2163e9071e09c34906bb13306c"},"schema_version":"1.0","source":{"id":"2103.12778","kind":"arxiv","version":1}},"canonical_sha256":"66ec263e0fe707fc008b3036076789c10df0402c736185cdc5050d6677d592e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66ec263e0fe707fc008b3036076789c10df0402c736185cdc5050d6677d592e8","first_computed_at":"2026-07-05T02:25:51.672036Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:25:51.672036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SbKRZzKWhtawG+0bd2IN5l0g6UJw9DZwb8fFh99rdoyE+PhotyZ4/gih5j26et6lc4CXZmLUTzec4ESGe16wCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:25:51.672496Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.12778","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:282ca5ced92a6f30c87f411d0e756c46b92a639c8fe6b442ae079d855d35b846","sha256:8911b25e4d7e43721c92cd3e051d68a2e699b86e218112555c3d3bc3da3e13c5"],"state_sha256":"0f50dfc778addd87bf099a5a56762b7dab520557337425716c8b17cb15bb42e5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qRRJzNLx9x80ZvowjGauEQiUcvGSCdsETPDZQl+o6f/aYa2JqhZW8ut6ij8hiZine+EFd0LDr36vLWeFcw+6DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T21:06:43.357873Z","bundle_sha256":"a21b2599d2f18219ae84697626447dfbccc45ba949282fc2c34742dfdb2eee1c"}}