{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QVADTLOFOY5MSCXVR3ONMQ7T3L","short_pith_number":"pith:QVADTLOF","canonical_record":{"source":{"id":"2505.13947","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-20T05:25:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b32ffa46e3e41f24d6e4233e774f63ed4a9e842032fdeb701819502048fd1296","abstract_canon_sha256":"ae13dcc5b6ddacd9b63a87889f615fec78742846945b10c8e13c151c122848b9"},"schema_version":"1.0"},"canonical_sha256":"854039adc5763ac90af58edcd643f3dac5128ddd421b179183f665befa0c62fe","source":{"kind":"arxiv","id":"2505.13947","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13947","created_at":"2026-07-05T11:07:25Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13947v2","created_at":"2026-07-05T11:07:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13947","created_at":"2026-07-05T11:07:25Z"},{"alias_kind":"pith_short_12","alias_value":"QVADTLOFOY5M","created_at":"2026-07-05T11:07:25Z"},{"alias_kind":"pith_short_16","alias_value":"QVADTLOFOY5MSCXV","created_at":"2026-07-05T11:07:25Z"},{"alias_kind":"pith_short_8","alias_value":"QVADTLOF","created_at":"2026-07-05T11:07:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QVADTLOFOY5MSCXVR3ONMQ7T3L","target":"record","payload":{"canonical_record":{"source":{"id":"2505.13947","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-20T05:25:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b32ffa46e3e41f24d6e4233e774f63ed4a9e842032fdeb701819502048fd1296","abstract_canon_sha256":"ae13dcc5b6ddacd9b63a87889f615fec78742846945b10c8e13c151c122848b9"},"schema_version":"1.0"},"canonical_sha256":"854039adc5763ac90af58edcd643f3dac5128ddd421b179183f665befa0c62fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:25.124775Z","signature_b64":"sIWYbGFQ5qIMaDzkc0em+eYg/b3utNoox/JQtgt1f6sxMH9p+/9HRs49bpPaPL/rUNLVl6UsY4BDN371EwkIBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"854039adc5763ac90af58edcd643f3dac5128ddd421b179183f665befa0c62fe","last_reissued_at":"2026-07-05T11:07:25.124284Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:25.124284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.13947","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:07:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eyOwBxfDl05rY8QXAhBHjZ2F3Z9KOHp3CRLYQXSWll3FqKybcIRtqjl2NsS4WZHG9YzuTD6OtE/iuLDbo1iRCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:02:42.902429Z"},"content_sha256":"f97d814cb2dab7604c3c99a62f438973fc669952cba3be63036469659379a12a","schema_version":"1.0","event_id":"sha256:f97d814cb2dab7604c3c99a62f438973fc669952cba3be63036469659379a12a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QVADTLOFOY5MSCXVR3ONMQ7T3L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Probabilistic Perspective on Model Collapse","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Guang Cheng, Hengzhi He, Shirong Xu","submitted_at":"2025-05-20T05:25:29Z","abstract_excerpt":"In recent years, model collapse has become a critical issue in language model training, making it essential to understand the underlying mechanisms driving this phenomenon. In this paper, we investigate recursive parametric model training from a probabilistic perspective, aiming to characterize the conditions under which model collapse occurs and, crucially, how it can be mitigated. We conceptualize the recursive training process as a random walk of the model estimate, highlighting how the sample size influences the step size and how the estimation procedure determines the direction and potent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13947","kind":"arxiv","version":2},"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/2505.13947/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":"2026-07-05T11:07:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s5bsDjwTX6oCzx6nf66PN/aL1WEgrjgnfRxDJbeSwaDhbAidIX/1YJ2xnJev0E9uAoWeL3Obzg+M20XfdEP0AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:02:42.902737Z"},"content_sha256":"65a63bf5aa8f61895ab017278a35cc13754cdd3ac7ade879d383ba9d3e0a3676","schema_version":"1.0","event_id":"sha256:65a63bf5aa8f61895ab017278a35cc13754cdd3ac7ade879d383ba9d3e0a3676"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QVADTLOFOY5MSCXVR3ONMQ7T3L/bundle.json","state_url":"https://pith.science/pith/QVADTLOFOY5MSCXVR3ONMQ7T3L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QVADTLOFOY5MSCXVR3ONMQ7T3L/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":"2026-08-04T23:02:42Z","links":{"resolver":"https://pith.science/pith/QVADTLOFOY5MSCXVR3ONMQ7T3L","bundle":"https://pith.science/pith/QVADTLOFOY5MSCXVR3ONMQ7T3L/bundle.json","state":"https://pith.science/pith/QVADTLOFOY5MSCXVR3ONMQ7T3L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QVADTLOFOY5MSCXVR3ONMQ7T3L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QVADTLOFOY5MSCXVR3ONMQ7T3L","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":"ae13dcc5b6ddacd9b63a87889f615fec78742846945b10c8e13c151c122848b9","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-20T05:25:29Z","title_canon_sha256":"b32ffa46e3e41f24d6e4233e774f63ed4a9e842032fdeb701819502048fd1296"},"schema_version":"1.0","source":{"id":"2505.13947","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13947","created_at":"2026-07-05T11:07:25Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13947v2","created_at":"2026-07-05T11:07:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13947","created_at":"2026-07-05T11:07:25Z"},{"alias_kind":"pith_short_12","alias_value":"QVADTLOFOY5M","created_at":"2026-07-05T11:07:25Z"},{"alias_kind":"pith_short_16","alias_value":"QVADTLOFOY5MSCXV","created_at":"2026-07-05T11:07:25Z"},{"alias_kind":"pith_short_8","alias_value":"QVADTLOF","created_at":"2026-07-05T11:07:25Z"}],"graph_snapshots":[{"event_id":"sha256:65a63bf5aa8f61895ab017278a35cc13754cdd3ac7ade879d383ba9d3e0a3676","target":"graph","created_at":"2026-07-05T11:07:25Z","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/2505.13947/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, model collapse has become a critical issue in language model training, making it essential to understand the underlying mechanisms driving this phenomenon. In this paper, we investigate recursive parametric model training from a probabilistic perspective, aiming to characterize the conditions under which model collapse occurs and, crucially, how it can be mitigated. We conceptualize the recursive training process as a random walk of the model estimate, highlighting how the sample size influences the step size and how the estimation procedure determines the direction and potent","authors_text":"Guang Cheng, Hengzhi He, Shirong Xu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-20T05:25:29Z","title":"A Probabilistic Perspective on Model Collapse"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13947","kind":"arxiv","version":2},"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:f97d814cb2dab7604c3c99a62f438973fc669952cba3be63036469659379a12a","target":"record","created_at":"2026-07-05T11:07:25Z","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":"ae13dcc5b6ddacd9b63a87889f615fec78742846945b10c8e13c151c122848b9","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-20T05:25:29Z","title_canon_sha256":"b32ffa46e3e41f24d6e4233e774f63ed4a9e842032fdeb701819502048fd1296"},"schema_version":"1.0","source":{"id":"2505.13947","kind":"arxiv","version":2}},"canonical_sha256":"854039adc5763ac90af58edcd643f3dac5128ddd421b179183f665befa0c62fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"854039adc5763ac90af58edcd643f3dac5128ddd421b179183f665befa0c62fe","first_computed_at":"2026-07-05T11:07:25.124284Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:25.124284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sIWYbGFQ5qIMaDzkc0em+eYg/b3utNoox/JQtgt1f6sxMH9p+/9HRs49bpPaPL/rUNLVl6UsY4BDN371EwkIBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:25.124775Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13947","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f97d814cb2dab7604c3c99a62f438973fc669952cba3be63036469659379a12a","sha256:65a63bf5aa8f61895ab017278a35cc13754cdd3ac7ade879d383ba9d3e0a3676"],"state_sha256":"1e3976dde6fb640bac19ae6eb2fe06a2fe1d42bfea24a1902b9ec90630eaeb28"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SoLN3hbTo5gcjaindKnk3hV77vuLrhC8rQLGJI5UqVmXjoiKFfYqSQmlqn22XglLHWcz8GYXby9Co3732eOfBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T23:02:42.905703Z","bundle_sha256":"b9894690f2af4bfa40cded3d3a10167990124891a73e8fb357377b577318f492"}}